Energy and resource optimization in building smart city using multiverse optimizer (mov) algorithm

LIST OF ABBREVIATIONS AEC Architecture, engineering, and construction AHA Artificial hummingbird algorithm ANN Artificial neural network BREEAM Building Research Establishment Environme

VIETNAM NATIONAL UNIVERSITY HO CHI MINH CITY

HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY

LÊ VĂN TRỌNG

ENERGY AND RESOURCE OPTIMIZATION IN BUILDING SMART CITY USING MULTIVERSE

OPTIMIZER (MOV) ALGORITHM

Major: CONSTRUCTION MANAGMENT

Major code: 8580302

MASTER’S THESIS

HO CHI MINH CITY, July 2023

THIS THESIS IS COMPLETED AT

HO CHI MINH UNIVERSITY OF TECHNOLOGY – VNU – HCM CITY

Supervisor: Associate Prof Pham Vu Hong Son

Examiner 1: Dr Nguyen Anh Thu

Examiner 2: PhD Nguyen Van Tiep

This master’s thesis is defended at HCM city University of Technology,

VNU-HCM City on 12th, July, 2023

Master’s Thesis Committee:

Approval of the Chairman of the Master’s Thesis Defense Council and the Dean of faculty of Civil Engineering after the thesis being corrected

CHAIRMAN OF THE COUNCIL DEAN OF FACULTY OF CIVIL ENGINEERING

VIETNAM NATIONAL UNIVERSITY

HO CHI MINH CITY

HO CHI MINH CITY UNIVERSITY

THE TASK SHEET OF MASTER’S THESIS

I THESIS TOPIC: Energy and Resource Optimization in Building Smart City

Using Hybrid-Multiver Optimizer (MOV) Algorithm

Tối Ưu Năng Lượng Và Tài Nguyên Trong Xây Dựng Thành Phố Thông Minh

Sử Dụng Thuật Toán Lai Đa Vũ Trụ (MVO)

II TASKS AND CONTENTS: Energy optimisation artificial intelligence (Ai) in

construction management

III TASKS STARTING DATE : October 2022.

IV TASKS ENDING DATE : August 2023.

V INSTRUCTOR : Associate Professor Pham Vu Hong Son

ACKNOWLEDGEMENT

First and foremost, I would like to show my appreciation to my enthusiastic thesis instructor and advisor, Ph.D./Associate Prof Pham Vu Hong Son, for his invaluable guidance and unwavering support throughout this research journey His expertise, constructive feedback, and insightful suggestions have played a pivotal role in guiding and give me direction for my thesis from begging to the end I am extremely appreciative for his devotion, persistence, and willingness to share his knowledge, which have greatly enriched my understanding of the subject matter I am fortunate

to have had the opportunity to work under his mentorship, and I extend my heartfelt thanks for his valuable contributions to this research

ABSTRACT

The increasing demand for clean and efficient energy for construction industry, especially for developing and managing smart cities has led to the development of microgrids Common problems with these strategies are the demand and supply of the energy constantly conflicted, as a result, the energy usage frequently inefficient

To solve this problem, optimization techniques and heuristics methods are utilized Mathematical optimization procedures can acquire optimum results, but they are only suitable for small-scale problems For large-scale situation, artificial intelligence techniques have been applied In this thesis, a Hybrid version of the multi-verse optimizer (MVO) and the Sine Cosine Algorithm (SCA) is introduced to advance the exploration and exploitation balance of the standard MVO algorithm The proposed hybrid algorithms also find improved optimal solutions for energy optimization by illustrating its searching ability with diverse search space problems

As a result, the proposed algorithm will demonstrate its availability to solve real unknown search space construction and non-construction problems

Keywords: Energy management, Hybrid multi-verse optimizer (MVO), Artificial intelligent, Smart city

TÓM TẮT LUẬN VĂN THẠC SĨ

Nhu cầu ngày càng tăng về năng lượng sạch và hiệu quả trong ngành xây dựng, đặc biệt là cho việc phát triển và quản lý các thành phố thông minh, đã dẫn đến việc phát triển các mạng lưới nhỏ Vấn đề phổ biến với các chiến lược này là sự xung đột giữa nhu cầu và cung cấp năng lượng, dẫn đến việc sử dụng năng lượng thường không hiệu quả Để giải quyết vấn đề này, các kỹ thuật tối ưu hóa và phương pháp thông minh được áp dụng Các quy trình tối ưu hóa toán học có thể đạt được kết quả tối ưu, nhưng chúng chỉ phù hợp với các vấn đề quy mô nhỏ Đối với các tình huống quy mô lớn, các kỹ thuật trí tuệ nhân tạo đã được áp dụng Trong luận văn này, một phiên bản Hybrid của thuật toán tối ưu hỗn hợp multi-verse (MVO) và thuật toán Sine Cosine (SCA) được giới thiệu để cải thiện sự cân bằng giữa việc khám phá và khai thác của thuật toán MVO tiêu chuẩn Các thuật toán hybrid được đề xuất cũng tìm kiếm các giải pháp tối ưu cải thiện cho việc tối ưu hóa năng lượng bằng cách minh họa khả năng tìm kiếm của nó với các vấn đề không gian tìm kiếm đa dạng Kết quả

là, thuật toán đề xuất sẽ chứng minh tính khả thi của nó trong việc giải quyết các vấn

đề xây dựng và không xây dựng trong không gian tìm kiếm thực sự

Từ khóa: Quản lý năng lượng, Tối ưu hỗn hợp multi-verse (MVO), Trí tuệ nhân tạo, Thành phố thông minh

AUTHOR’S COMMITMENT

The undersigned below:

Place and date of born : Ho Chi Minh City, 26th January 1992

Ho Chi Minh City

With this declaring that the master thesis entitled “Energy And Resource

Optimization in Building Smart City Using Multiverse Optimizer (MOV) Algorithm” is done by the author under supervision of the instructor All works,

ideas, and material that was gain from other references have been cited in the corrected way

Ho Chi Minh City, August 06 2023

Le Van Trong

TABLE OF CONTENTS

THE TASK SHEET OF MASTER’S THESIS i

ACKNOWLEDGEMENT ii

ABSTRACT iii

TÓM TẮT LUẬN VĂN THẠC SĨ iv

AUTHOR’S COMMITMENT v

TABLE OF CONTENTS vi

LIST OF FIRGURES viii

1 INTRODUCTION 1

1.1 Research Problem 1

1.2 Research Objectives: 7

1.3 Scope of study 10

1.4 Research Methodology 12

1.5 Academic and Practical Significances 14

2 LITERATURE REVIEW 15

2.1 Definition of Smart City 15

2.2 Energy/Resource optimization in Construction 16

2.3 Energy Optimization in Smart city construction 17

2.4 Problem Dimension: 19

2.4.1 Problem Dimension: 19

2.4.2 Constraints: 20

2.4.3 Objective Function 21

2.5 Related Studies: 22

2.6 Research Gap: 25

3 MODEL DEVELOPMENT 30

3.1 Multiverse Optimizer (MVO) 30

3.2 Sine Cosine Algorithm (SCA) 36

3.3 Hybrid Multiverse – Sincos Algorithm (hMVO) for Smart city construction energy cost effective optimization 41

3.3.1 Cost effective optimization 41

3.3.2 Hybrid Multiverse – Sincos Algorithm (hMVO) 42

3.3.3 Hybrid Multiverse – Sincos Algorithm (hMVO) for Smart city construction energy cost effective optimization 44

4 MODEL VALIDATION 47

4.1 Case Study 1: 47

4.2 Case Study 2: 52

5 CONCLUSION AND RECOMMENDATION 56

5.1 Conclusion 56

5.2 Recommendation: 59

5.2.1 Demonstration Projects, networking and education: 59

5.2.2 Government Incentives and Policies 60

5.2.3 Research and Development 61

5.3 Future Research 62

5.4 Research Implication 63

5.4.1 Practical implication 63

5.4.2 Academic implication 64

REFERENCES 66

APPENDICES 71

MVO.py 72

MVO_SCA.py 72

Model 74

Constant.py 75

Main_run.py 76

Show result 79

Run_mvo.py 79

Run_mvo_sca.py 80

Utils.py 80

Case 1 output: 83

Case 2 output: 85

PROFILE 87

LIST OF FIRGURES

Figure 1-1 Energy Optimization in smart city project 5

Figure 1-2 Research objectives 7

Figure 1-3 Scope of study 10

Figure 1-4 Research Flowchart 12

Figure 3-1 Conceptual model of the proposed MVO algorithm 31

Figure 3-2 Wormhole existence probability (WEP) versus travelling distance rate (TDR) 32 Figure 3-3 Flow chart of MVO 35

Figure 3-4 Effects of Sine and Cosine regarding equation (12) and equation (13) on the next position 37

Figure 3-5 Sine and cosine with range of [−2,2] 38

Figure 3-6 Sine and cosine with the range in [−2,2] allow a solution to go around (inside the space between them) or beyond (outside the space between them) the destination 39

Figure 3-7: The model gradually reduces the range of the Sine and Cosine functions 39

Figure 3-8 Flow chart of MVO 41

Figure 3-10 Flowchart of Hybrid Multiverse–Sincos Algorithm (hMVO) algorithm 43

Figure 4-1 Wind plants, PV plants, and CHP as DERs (Distributed Energy Resources) 48

Figure 4-2 Convergence graph at Hour 17 for Case 1 51

LIST OF TABLES

Table 2-1 List of related studies 24

Table 4-1 Required power for each hour of case 1 [19] 48

Table 4-2 The power generation of each renewable energy source per hour [19] 49

Table 4-3 Cost coefficients of DERs in microgrid in case 1 [19] 49

Table 4-4 Generation power schedule and its cost generate by CMVO 50

Table 4-5 Generation power schedule and its cost generate by hMVO 50

Table 4-6 Statistic results for each algorithm performance Case 1 51

Table 4-7 Required power for each hour of case 2 52

Table 4-8 The power generation of each renewable energy source per hour Case 2.53 Table 4-9 Generation power schedule and its cost generate by CMVO 53

Table 4-10 Generation power schedule and its cost generate by hMVO 54

Table 4-11 Statistic results for each algorithm performance Case 2 54

LIST OF ABBREVIATIONS

AEC Architecture, engineering, and construction

AHA Artificial hummingbird algorithm

ANN Artificial neural network

BREEAM Building Research Establishment Environmental Assessment Method CEM Construction engineering and management

DERs Distributed energy resources

hMVO Hybrid Multi-Verse Optimization Algorithm

LEED Leadership in Energy and Environmental Design

MVO Hybrid Multi-Verse Optimization Algorithm

TDR Travelling distance rate

WEP Wormhole existence probability

1 INTRODUCTION

 § 

In this chapter, the research problem is introduced, emphasizing the significance of optimizing power schedules to minimize generation costs Section 1.1 provides a concise overview of power schedule optimization, while Section 1.2 outlines the research objectives The scope of the study is presented in Section 1.3, after that an explanation of the research methodology is discussed in Section 1.4 The academic and practical significances of the research are addressed in Section 1.5, concluding this chapter

"Smarter Cities" marketing initiative launched in 2008, and the Smart City Expo World Congress commenced in Barcelona in 2011, becoming an annual event charting smart city development worldwide The European Commission also created the Smart Cities Marketplace in 2012 to centralize urban initiatives within the European Union Presently, more than 165 cities from 80 countries are participating

in smart city projects in various capacities

A smart city encompasses a wide array of elements, necessitating a strategic and systematic approach for effective implementation The strategic framework of a smart city comprises a hierarchical system encompassing vision, core values, and strategic goals The vision outlines the future smart cities aim to achieve, and core values and strategic goals are derived from this vision However, smart city development varies among cities, leading to differing goals and evaluation criteria in project execution

Reviewing previous smart city studies reveals trends and weaknesses in strategies While research on smart cities has increased significantly, many studies only focus on the application of smart technologies like Big Data and ICT or present case-specific anecdotes, lacking a consistent and systematic strategic approach To ensure efficient resource allocation and utilization, smart city development should prioritize selection and concentration However, current research tends to be fragmented and technology-focused, lacking a comprehensive framework for setting effective strategic goals

Energy resources optimization is a key component of sustainable construction practices in smart city projects Construction managers play a vital role in planning, designing, and executing construction projects with a focus on reducing energy consumption, optimizing energy use, and integrating renewable energy sources Energy-Efficient Building Design which stage construction managers are involved in making decisions related to building design and material selection By considering energy-efficient building design principles and technologies, they can optimize energy use and reduce operational costs throughout the building's lifecycle

Construction Equipment and Energy Management is where managers can contribute to energy resources optimization by efficiently managing construction equipment and machinery They can schedule equipment usage to avoid energy wastage and explore the use of energy-efficient machinery Construction managers also can conduct life cycle cost analysis to evaluate the long-term costs and benefits

of different energy resource optimization strategies This analysis helps in making informed decisions about energy-efficient technologies and practices

Construction engineering and management (CEM) is a specialized field that utilizes project management principles to supervise the entire lifecycle of construction projects, encompassing tasks such as planning, design, construction, and maintenance [1] Nevertheless, there are limit or none plan of quantity and schedule resources use in the project planning, execution and management phases Furthermore, the primary aim of CEM is to effectively meet the triple constraint of a project, which includes ensuring adherence to designated timelines, managing costs

within budgetary limits, and upholding high standards of quality, all while prioritizing the safety of all involved parties [2] CEM is categorized within the architecture, engineering, and construction (AEC) sector, which ranks among the largest industries globally, encompassing expenses surpassing USD 1.2 trillion every year However, despite its significant scale, the AEC industry faces challenges in productivity, with more than 98% of projects encountering cost overruns and numerous other difficulties [3] The industry face dynamic challenges such as inefficient project resource management, resulting in a high level of uncertainty that impedes productivity growth Industry leaders face significant difficulties in predicting and increasing its productivity

Many construction projects aim for green building certifications such as LEED (Leadership in Energy and Environmental Design) or BREEAM (Building Research Establishment Environmental Assessment Method) Construction managers play a significant role in meeting the criteria for these certifications, which often include energy efficiency targets Efficient energy resources optimization may lead to reduced construction waste generation, as well-designed buildings and processes can minimize material wastage Construction managers can implement waste management strategies that align with energy-efficient practices

The application of advanced data analytics techniques, such as machine learning and artificial intelligence, enhances power efficiency in construction projects By analyzing historical energy consumption data and project-specific factors, predictive algorithms can forecast energy needs accurately This foresight allows construction managers to adjust energy usage proactively, optimize schedules, and allocate resources efficiently, thereby reducing energy waste and expenses

Energy resources optimization often involves the integration of smart technologies, such as smart meters, sensors, and automation systems Construction managers need to understand and coordinate the deployment of these technologies in construction projects Construction managers may be involved in the integration of renewable energy sources, such as solar panels or wind turbines, into construction projects This includes assessing the feasibility, cost, and benefits of renewable energy adoption

After construction is complete, construction managers can contribute to energy resources optimization by ensuring the efficient operation and maintenance of buildings and infrastructure, including monitoring energy consumption and implementing energy-saving measures

The increasing demand for clean and efficient energy for construction industry, especially for developing and managing smart cities has led to Microgrid development which refers to the establishment of small-scale power systems that have the capability to operate autonomously or in collaboration with the primary electricity grid Common problems with these strategies are the demand and supply

of the energy constantly conflicted, as a result, the energy usage frequently inefficient [4] To solve the problem, optimization techniques and heuristics methods are utilized Mathematical optimization procedures can find optimal solutions, but they are exclusively suitable for small-scale problems For large-scale situation, artificial intelligence techniques have been applied [5]

Construction managers may oversee the implementation of microgrid systems in construction projects Microgrids are localized power systems that can integrate renewable energy sources and efficiently manage energy distribution, reducing reliance on the main power grid

In summary, energy resources optimization is an integral part of modern construction management practices Construction managers play a crucial role in promoting sustainable and energy-efficient construction projects, from the planning and design stages to project execution and facility management Their decisions and actions directly impact the energy performance and environmental footprint of construction projects

Here are several researches question this thesis will concentrate on:

1 How can we develop effective multi-objective optimization models that balance conflicting objectives, such as minimizing energy costs, reducing greenhouse gas emissions, and maximizing project efficiency, to achieve sustainable and efficient construction outcomes?

2 How can advanced data analytics, including artificial intelligence, be leveraged to predict energy needs and optimize energy usage in construction projects in smart city?

3 What are the potential barriers and challenges in adopting and implementing energy-efficient practices and technologies in the construction industry, and how can these barriers be overcome?

Figure 1-1 Energy Optimization in smart city project

To optimize the power generation in a microgrid, a cost-effective and efficient optimization algorithm is required This thesis will propose Hybrid Multi-Verse Optimization Algorithm (hMVO) in term of saving cost to optimize the power generation in a microgrid The proposed HMVO algorithm is compared with other meta-heuristic algorithms such as MVO, Particle Swarm Optimization (PSO), Artificial hummingbird algorithm (AHA), and Genetic Algorithms (GA), using two different scale microgrids to assess the performance of proposed algorithms regarding both cost reduction and execution time improvement

There have been many studies that focusing on optimizing power generation in microgrids using optimization algorithms One such work is " Role of optimization

techniques in microgrid energy management systems—A review " by Gokul, S et al (2022) The authors provide a comprehensive review of the different metaheuristic optimization algorithms that have been used to optimize microgrid energy management The review includes Genetic Algorithms, Particle Swarm Optimization, Ant Colony Optimization, and others [6]

Another relevant work is " Microgrid Energy Management using Improved Reinforcement Learning with Quadratic Programming " by Shu, Y, Dong, W, Yang,

Q, & Wang, Y (2021) The authors present a decent examination of various optimization approaches employed for microgrid control and energy management The analysis encompasses traditional optimization methods like Linear Programming and Quadratic Programming, as well as metaheuristic techniques such as Genetic Algorithms and Particle Swarm Optimization [7]

In addition, there have been several works that focus specifically on the Verse Optimization Algorithm (MVO) for power generation optimization in microgrids One such work is " Improved multi-verse optimizer feature selection technique with application to phishing, spam, and denial of service attacks " by Alzaqebah, M, Jawarneh, S, Mohammad, R, Alsmadi, M & Almarashdeh, I (2021) The authors apply the MVO algorithm to optimize the operation of a microgrid with renewables and energy storage systems [8]

Multi-Despite the availability of several works related to the topic, there are still several issues that need to be focused on researching and solving One such issue is the scalability of the optimization algorithms to larger and more complex microgrids Most of the existing works have focused on small-scale microgrids with only a few energy sources However, as microgrids become more widespread and complex, the optimization algorithms need to be able to handle a larger number of energy distribution resource and its storages system

Another issue is the sturdiness of the optimization algorithms in the face of uncertain and dynamic conditions The power generation in a microgrid is subject to various uncertainties such as weather conditions and demand fluctuations The optimization algorithms need to be able to adapt to these uncertain and dynamic conditions in real-time to ensure optimal power generation

Identify and analyze the potential barriers and challenges in adoption and implementation of energy-efficient practices and technologies in the construction industry

Finally, there is a need for the integration of multiple optimization objectives such as cost, reliability, and environmental impact Most of the existing works have focused on optimizing a single objective such as cost or power generation However,

in reality, there are multiple objectives that need to be considered when optimizing microgrid power generation Therefore, there is a need for the development of multi-objective optimization algorithms that can balance these different objectives

1.2 Research Objectives:

Figure 1-2 Research objectives

The first objective of this thesis is to develop and implement multi-objective optimization models that effectively balance conflicting objectives in construction projects, considering factors such as energy costs, greenhouse gas emissions, and project efficiency, to achieve sustainable and efficient outcomes Optimizing the development of the Hybrid Multi-Verse Optimization (hMVO) algorithm by analyzing different optimization techniques and heuristics methods to obtain the most efficient and cost-effective approach for power generation in microgrids This research objective concentrates on the development of the hMVO algorithm for

power generation in microgrids It highlights the importance of evaluating different optimization techniques and heuristics methods to identify the most efficient and cost-effective approach To achieve this objective, the researcher may conduct a literature review of existing optimization techniques and heuristics methods used in power generation in microgrids They may then evaluate the strengths and weaknesses of each method and determine which ones are best suited for developing the hMVO algorithm The researcher may also need to conduct simulations and experiments to test the efficiency and cost-effectiveness of the different optimization techniques and heuristics methods By comparing the results of these tests, the researcher can identify the most effective approach to optimize the power generation

in microgrids and develop the hMVO algorithm Overall, this research objective is important as it aims to develop an optimized algorithm for power generation in microgrids that is both efficient and cost-effective, which could have significant implications for the renewable energy industry

This thesis also aims to explore and apply advanced data analytics techniques, via artificial intelligence, to analyze construction project data and predict energy needs accurately as well as assess the result and performance of the hMVO algorithm

in different case studies, by comparing the results with those obtained by other different meta-heuristic algorithms such as MVO, PSO, AHA, and GA Evaluating the performance of the hMVO algorithm in different case studies is important to demonstrate its effectiveness and superiority over other commonly used optimization algorithms By comparing the results with those obtained by other meta-heuristic algorithms such as MVO, PSO, AHA, and GA, this thesis can provide a comprehensive analysis of the strengths and weaknesses of each algorithm This comparison can help researchers and practitioners to identify the most suitable algorithm for their specific microgrid optimization problem, based on factors such as cost, efficiency, and execution time Additionally, the comparison can help to establish the superiority of the hMVO algorithm, thus providing a strong case for its adoption in practical applications Overall, the comparison between hMVO algorithm with other meta-heuristic algorithms is a crucial step in demonstrating its effectiveness and practicality for power generation optimization in microgrids

After that, this thesis will aim to apply the hMVO algorithm to a new case study in a smart grid environment, aiming to optimize the energy power generation and reduce costs, while maintaining a high level of performance and reliability This objective involves applying the algorithm to a real-world problem and evaluating its effectiveness in optimizing energy power generation and reducing costs while ensuring high performance and reliability

Identifying and analyzing the potential barriers and challenges hindering the widespread adoption and implementation of energy-efficient practices and technologies in the construction industry is crucial for promoting sustainable and environmentally responsible construction practices This investigation involves a comprehensive examination of factors that impede the integration of energy-efficient measures in construction projects Researchers conduct thorough literature reviews, engage with key stakeholders, analyze energy consumption data, assess available technologies, and evaluate economic and regulatory aspects By understanding these barriers, such as high initial costs, lack of awareness, resistance to change, and limited technical expertise, effective strategies and solutions can be proposed to foster the successful integration of energy-efficient practices in the construction sector Ultimately, addressing these challenges will lead to significant environmental benefits and enhance the industry's contribution to energy conservation and sustainable development

1.3 Scope of study

Figure 1-3 Scope of study The aim of this thesis is to examine and analyze the obstacles impeding the widespread adoption and implementation of energy-efficient practices and technologies in construction projects within smart cities The construction industry's role in smart city development is critical, but achieving energy efficiency poses challenges The study encompasses articles of various publication dates, gathered from reputable databases such as Science Direct, SCOPUS, Web of Science, and others, using relevant keywords like "energy efficiency," "smart cities," "construction project management," and "sustainable construction." Additionally, credible journal articles, books, and reports were consulted to compile an exhaustive list of barriers Understanding and analyzing these challenges are pivotal in proposing effective strategies to overcome the impediments and facilitate the successful integration of energy-efficient measures in smart city construction projects By addressing these barriers, the construction industry can significantly contribute to the overall sustainability and efficiency of smart city development, promoting a greener, more sustainable future and enhancing the quality of life for city residents

This study aims to collect data from experienced professionals in the construction project management field within smart cities to investigate barriers

Conduct development of hHMVO algorithm using existing case study with same criteria

The results of existing case study will be compared with other meta-heuristic algorithms Apply new hMVO to produce optimal energy

solution for new case study

hindering the widespread adoption of energy-efficient practices and technologies The selected industry experts should have at least a decade of experience in tactical roles in the construction industry, while academic respondents will be chosen from reputable management and engineering institutes with expertise in energy efficiency

in smart cities in this case is from Binh Dương smart city construction project Through analyzing the data provided by these experts, the primary obstacles to implementing energy-efficient measures in smart city construction projects will be identified, and their interrelationships will be examined Based on the findings, recommendations will be proposed to overcome these challenges and facilitate the successful integration of energy-efficient practices and technologies in smart city construction project management, thereby contributing to the development of sustainable and eco-friendly smart cities

Firstly, the algorithm development scope involves conducting a literature review of different optimization methods and heuristics approaches to develop the Hybrid Multi-Verse Optimization (hMVO) algorithm The performance of the hMVO algorithm will be compared with other meta-heuristic algorithms such as MVO, PSO, AHA, and GA

Secondly, the hMVO algorithm will be applied to each case study, and the results will be compared with other meta-heuristic algorithms The cost reduction and execution time improvement of the hMVO algorithm in both case studies will be evaluated

Lastly, the smart grid optimization scope involves selecting a new case study

in a smart grid environment The hMVO algorithm will be applied to optimize energy power generation and reduce costs while maintaining high performance and reliability The results will be compared with other meta-heuristic algorithms, and the efficiency and usefulness of the hMVO algorithm in the smart grid context will be evaluated

1.4 Research Methodology

Figure 1-4 Research Flowchart

The research methodology for this study involves five key steps The first step

is to conduct a comprehensive review of relevant literature on smart cities, construction energy optimization, and energy-efficient practices in construction project management In which this section will focusing on analyze existing research, case studies, and publications to gain insights into the current state of energy optimization in smart city construction projects and identify gaps in knowledge Following by defining the research problem, focusing on the challenges and barriers faced in achieving energy efficiency in construction projects within smart cities as

Develop Hybrid MVO

 Apply method for hMVO algorithm

 Input data with similar criteria with original case study

Produce Hybrid MVO Algorithm

 Validate performance of Hybrid MVO algorithm with performance and results of other algorithms in the original case study

Application of the new Hybrid MVO Algorithm

 Apply new Hybrid MVO Algorithm to new case study to evaluate new algorithm performance

Conclusion, line out some limitation & suggestion for future further

research

well as formulating specific research questions and objectives that address the identified problem statement and guide the study

Define input data from case studies mean Select case studies from existing smart city construction projects that involve energy optimization initiatives Then define the relevant input data required for the analysis, including energy consumption patterns, project parameters, energy sources, and efficiency measures To finish, collect data from the selected case studies, ensuring data quality, accuracy, and relevance to the research objectives

The second step is to develop a methodology for energy optimization in smart city construction projects, considering multi-objective optimization models and artificial intelligence techniques in which hybrid Multi-Verse Optimization and sin cos algorithm (hMVO) This section will describe the hybrid model combining the Multiverse Optimization (MVO) and Sine Cosine Algorithm (SCA) to enhance the efficiency of the optimization process, wherein, detail the proposed model's working principles and algorithms to achieve energy-efficient outcomes

The third step is to produce a new hybrid method as well as authorize its performance with the results of the original case study This step will involve running the new algorithm on the input data used for the original case study and comparing its results with those obtained by the original algorithm

The fourth step is the application of the new hMVO to the new case study to review its performance By implementing the proposed hybrid model on the collected data from case studies and evaluate its performance in energy optimization for smart city construction projects this thesis will compare the results with other existing algorithms and validate the effectiveness of the proposed methodology

The final step is the summarize the research findings based on the data analysis and simulation results This section will provide recommendations and strategies for overcoming barriers and challenges identified in the research, aiming to promote energy-efficient practices in smart city construction project management It also discusses the implications of the research and suggest future directions for further improvement in the field of energy optimization in smart cities

1.5 Academic and Practical Significances

The research makes a valuable contribution to the academic and practical aspects

of energy optimization in construction management field specifically in building smart cities It addresses the power scheduling problem with a focus on ensuring consistency as well as effectiveness The optimization outcomes provide a customized and optimal energy management approach designed specifically for microgrids in smart cities that rely on renewable energy sources

1.5.1 Academically

This thesis aims to improve Multiverse Optimizer (MVO) algorithm application for energy consumption optimization in construction management field by considering iterative aspects as well as other factors that can affect renewable energy output such as variation in wind speed, air density, and temperature

1.5.2 Practically

The development of Multiverse Optimizer (MVO) algorithm also aim to be a effective decision tools to generate a optimal power generation schedule for actual construction project by minimizing cost of generating these renewable power require for smart cities

2 LITERATURE REVIEW

 § 

This chapter consist of related literature reviews summary and its findings Section 2.1 define the smart city while Section 2.2 explain the important of Energy/Resource optimization in construction Furthermore, Section 2.3 illustrate the need of energy Optimization in Smart city construction Section 2.4 further explain problem dimension by explaining the cost function formula, constrains and objective function that are related Some related studies and research gaps for this thesis will be illustrate in Section 2.5 and Section 2.6 respectively

2.1 Definition of Smart City

Smart cities represent a paradigm shift in urban development, integrating edge technologies and data-driven solutions to create more sustainable, efficient, and livable environments [2] The concept of smart cities has attracted significant scholarly attention, with researchers exploring various dimensions of this transformative urban model Key aspects examined in the literature include the integration of advanced technologies like the Internet of Things (IoT), artificial intelligence (AI), and big data analytics to optimize city services and infrastructure Sustainability is another central theme, with studies emphasizing energy-efficient practices, renewable energy adoption, and eco-friendly urban planning to mitigate environmental impact Moreover, the literature delves into the importance of citizen-centric approaches, focusing on citizen engagement, participatory planning, and e-governance to empower residents and foster inclusive urban development As smart cities continue to evolve and shape the future of urban living, ongoing research contributes essential insights into best practices, challenges, and strategies to maximize the benefits of these intelligent urban ecosystems [27]

cutting-Smart cities have emerged as a response to the complex challenges posed by rapid urbanization and the need for sustainable development The literature on smart cities delves into various aspects, including the implementation of smart infrastructure and technologies to enhance urban services, optimize resource utilization, and improve

the overall quality of life for residents Researchers have explored the integration of smart transportation systems, intelligent energy grids, and advanced waste management solutions to create more efficient and resilient urban environments Furthermore, the concept of data-driven decision-making plays a crucial role in smart city development The literature emphasizes the importance of big data analytics, AI, and machine learning to process vast amounts of data collected through IoT sensors and devices These data-driven insights enable cities to make informed decisions on issues ranging from traffic management and emergency response to energy consumption and environmental sustainability In addition to technological advancements, the literature on smart cities highlights the significance of citizen engagement and inclusivity Smart cities are designed to prioritize the needs and preferences of their residents, and researchers stress the importance of involving citizens in the planning, implementation, and evaluation of smart city initiatives Moreover, the literature explores the potential challenges of data privacy and security, as well as the importance of building trust and transparency in the use of data for urban management

The development of smart cities also requires collaboration among various stakeholders, including governments, private sector organizations, academia, and civil society Research in this area delves into governance models, public-private partnerships, and policy frameworks that facilitate effective cooperation and coordination to drive smart city initiatives forward

2.2 Energy/Resource optimization in Construction

Optimization in the context of energy-efficient construction project management in smart cities plays a crucial role in achieving sustainability and effective resource utilization Two primary types of optimization approaches are commonly employed:

Single objective optimization:

This method focuses on a single objective function or a specific set of requirements related to energy efficiency The goal may involve minimizing energy consumption, reducing greenhouse gas emissions, or maximizing the utilization of renewable energy sources By employing single objective optimization, construction

projects can identify the most effective strategies to achieve their specific energy efficiency targets [27]

Multiple objective optimization:

In the realm of energy-efficient construction project management, multiple objectives come into play, such as minimizing energy consumption while considering other sustainability factors like reducing water usage or waste generation Balancing these multiple objectives requires sophisticated optimization techniques that can handle conflicting goals and provide solutions that optimize energy efficiency while considering various sustainability criteria [32]

As construction projects in smart cities strive to become more efficient, the use of optimization methodologies becomes essential Whether focusing

energy-on single or multiple objectives, optimizatienergy-on empowers decisienergy-on-makers to make informed choices that contribute to the overall energy efficiency and sustainability of the project, aligning it with the broader goals of smart city development By efficiently managing energy resources and employing innovative solutions, construction projects can effectively contribute to the advancement of smart cities' energy-efficient infrastructure and overall sustainability

2.3 Energy Optimization in Smart city construction

The literature review explores the interconnection between energy efficiency

in smart cities and construction project management It delves into various academic works, research articles, case studies, and reports that focus on the integration of energy-efficient practices within smart city development and construction projects The review examines the significance of energy optimization in smart cities as a crucial component of sustainability and resource management It investigates how construction project management can play a pivotal role in achieving energy efficiency goals by incorporating innovative technologies and green building practices Additionally, the review analyzes the challenges faced in implementing energy-efficient measures in construction projects within the context of smart cities, including issues related to cost, technology adoption, and stakeholder engagement

By synthesizing the existing literature, the review identifies successful strategies and best practices for optimizing energy usage in construction projects, such as the use of renewable energy sources, energy-efficient building designs, and smart energy management systems It also explores the potential benefits of energy-efficient construction projects in smart cities, including reduced operational costs, lower greenhouse gas emissions, and enhanced urban resilience Furthermore, the literature review highlights the role of data analytics and advanced technologies, such

as the Internet of Things (IoT) and artificial intelligence, in enabling real-time monitoring and optimization of energy consumption in smart cities

The review also examines the importance of policy and regulatory frameworks

in promoting energy efficiency in construction projects and smart cities It looks into how government initiatives, incentives, and regulations can influence the adoption of energy-efficient practices and foster collaboration among stakeholders in the construction industry

Overall, the literature review provides valuable insights into the current state

of energy-efficient practices in smart city construction project management and identifies gaps in knowledge that warrant further research It serves as a foundation for the proposed study, guiding the investigation into effective strategies for achieving energy efficiency in construction projects within the context of smart city development For several years, artificial neural network (ANN)-based binary particle swarm optimization and ANN-based tracking search algorithm to schedule microgrids in virtual power plants, with the goal of achieving optimal scheduling with reduced fuel consumption, CO2 emissions, and increased system efficiency [5] They evaluated the system's performance under various conditions, including actual load data for trained and untrained models, and compared the results to previous works using different parameters The findings indicate that the hybrid algorithm outperformed other available algorithms

Many other outstanding studies focusing on stochastic optimization method, in which develops meta-heuristic techniques inspired by natural or social phenomena and aim to mimic the problem-solving strategies used in these phenomena that can be used to solve complex problems especially in construction management field that are

difficult to solve using traditional methods Son et al have conducted various studies related to optimization in construction procurement and logistics [9] In one study, they proposed the use of a Bayesian fuzzy-game model to optimize bargaining prices They also employed a hybrid dragonfly-particle swarm optimization technique [10] and a logistics planning model to optimize the cost of construction materials Another study involved the use of a hybrid ant lion optimizer algorithm to examine the logistics model for precast concrete members [11] In addition, they integrated a metamodel-based optimization technique with a machine learning model to forecast energy use in nonresidential buildings [13] To optimize project schedules in accordance with scarce resources, they suggested using a dependence structure matrix and the whale optimization algorithm [10] There are also many other relevant studies that have been conducted by Son et al., as referenced in their work [14-16]

2.4 Problem Dimension:

2.4.1 Problem Dimension:

Energy optimization base on the microgrid capability to provide power from its variable sources, in this case are wind plants (WP), solar panel plants The power generated and the demand at each hour vary, and the primary objective is to provide power to meet the demand load There exist several methods for distributing energy among DERs (distributed energy resources) The optimal energy management strategy in a microgrid involves minimizing the generation cost in which Cost function below this formula:

(1)

where C is the hourly cost ($), i denotes the ith DER, P is the generated power

by DER (MW), and α, β and γ are the function coefficients In order to optimize as well as balancing scheduling problems, the energy production cost minimization is expressed in Eq (3)

2.4.2 Constraints:

To ensure a seamless implementation, it is essential to maintain a continuous supply of generated power that meets or exceeds the demanded power at any given moment In cases where Distributed Energy Resources (DERs) are unable to fulfill the demand, the additional required capacity is sourced from the utility grid However, in this study, it is assumed that the load will consistently meet the power demand, eliminating the need to draw energy from the utility grid

(2)

In this context, the total generated power of the available Distributed Energy Resources (DERs) is denoted as , and represents the power demanded at a specific hour of the day The microgrid consists of a total of DER generation units, and the generated power for each hour is the combined sum of all the individual generation units' power The research explores two distinct microgrids, each featuring a varying number of generation units

Other constrains for this study are the number of power generation of each renewable energy source per hour which shown in Table 4-1 These constrains are calculated by which time of the day each power source is available to generate power

min is the minimum power generated by any generation unit, and it is supposed to be zero, whereas, max is the maximum power produced depending on the rated power capacity These also define the lower and upper bound and form the generation vector’s boundary in Table 4-2

Population size and maximum iteration for original case study are 50 and 1000 respectively

2.4.3 Objective Function

Energy production cost minimization ∑ ( )

(3) ∑ [ ]

Where is the requested power of each hour Therefore,

Decision variable is introduced for each DER, represented as [ ] This research considers three wind plants, two PV plants, and one CHP as DERs, resulting in 6 decision variables A solution can be denoted as:

[ ] (4) Where Pwp1, Pwp2, Pwp3, PPV1, PPV2 and PCHP represent the output power of wind plant 1, wind plant 2, wind plant 3, PV plant 1, PV plant 2 and CHP, respectively

Penalty function is applied to deal with equality constraints is expressed in Eq (5) below:

[∑ [ ]] ∑

(5)

Through the use of a penalty function, an optimization problem that contains equality constraints can be transformed into an optimization problem that does not contain equality constraints This modified problem has the same number of decision variables as the original case study’s problem

Penalty minimization [∑ [ ]] (6)

| | Where is the penalty factor

2.5 Related Studies:

Researchers have proposed various algorithms and models to optimize microgrids [27,28] Some studies have focused on the optimal allocation of generation sources, considering parameters such as cost, power losses, and emissions [29-31] Other studies have developed stochastic multi-objective optimization models and implemented hybrid algorithms to minimize voltage deviation, operational costs, and fuel consumption [32] The use of artificial intelligence techniques, such as artificial neural networks and particle swarm optimization, has been explored for optimal scheduling and improved system efficiency [33] Additionally, algorithms like quantum-based optimization and lightning search algorithm have been applied to microgrids to achieve significant reductions in operational costs and improved power scheduling [34,35]

Several studies have also addressed the optimization of renewable energy microgrids for rural areas, considering variables such as load size, energy sources, and objective functions [36] Techniques like differential evolution, mixed integer linear programming, and Markov decision processes and other methods have been employed to optimize microgrid designs and power scheduling, aiming to minimize costs, emissions, and reliability issues [37-45] Moreover, the multi-verse optimization algorithm has shown promising results in optimizing microgrid parameters and has been applied to various optimization problems in microgrids [46-47]

However, despite the existing research efforts, there is still a need for more efficient optimization algorithms to address power scheduling and generation cost minimization in microgrids The proposed modified multi-verse optimization algorithm aims to fill this research gap by optimizing power scheduling among different generation units, considering the intermittent nature of renewable sources The algorithm stores the best outcome of each iteration and uses it as input for subsequent iterations, enhancing its solution searching capability

The proposed approach contributes to the field of microgrid optimization and provides an effective solution to optimize power scheduling and minimize generation costs However, the number of minimizing costs of construction project are insufficient as well as not many studies exploit more of MVO capability in minimizing cost by hybrid it with other algorithms Here is the list of studies related

to construction energy and resource management using machine-learning or Artificial Intelligence in solving those issues

No Year Title Result

Energy Sustainability in Smart

Cities: Artificial Intelligence, Smart

Monitoring, and Optimization of

Energy Consumption

This paper offers an insight into pilot systems and prototypes that showcase in which ways artificial intelligence can offer critical support in the process

of obtaining energy sustainability in smart citie

Exploiting Multi-Verse Optimization

and Sine-Cosine Algorithms for

Energy Management in Smart Cities

The proposed schemes are implemented on a university campus load, which is divided into two portions, morning session and evening session Both sessions contain different shiftable and non-shiftable appliances

Energy-Efficient Multi-Constraint

Routing Algorithm with Load

Balancing for Smart City

Applications

This paper is to minimize the network's bit energy consumption parameter, and then we propose the Energy-Efficient Minimum Criticality Routing Algorithm (EEMCRA), which includes energy efficiency routing and load balancing To further improve network energy efficiency, this paper proposes an Energy-Efficient Multiconstraint ReRouting (E2MR2) algorithm

Contributions and Risks of Artificial

Intelligence (AI) in Building Smarter

Cities: Insights from a Systematic

Review of the Literature

This paper generates insights into how AI can contribute to the development of smarter cities A systematic review of the literature is selected as the methodologic approach Results are categorized under the main smart city development dimensions, i.e., economy, society, environment, and governance.

IoT assisted Hierarchical

Computation Strategic Making

(HCSM) and Dynamic Stochastic

Optimization Technique (DSOT) for

energy optimization in wireless

sensor networks for smart city

monitoring

This paper proposed the IoT assisted Hierarchical Computation Strategic Making (HCSM) and Dynamic Stochastic Optimization Technique (DSOT) Approaches for energy optimization in a Wireless Sensor Network for tracking a smart city

The Cluster head selection node and K-means algorithm have been utilized to increase the network lifetime and energy efficiency.

It is recommended that penetration is maximized while reducing energy The performance measurements can be regarded as dependingon the loading and resource profiles, storage systems’

capacity, and the dispatch algorithm

7 Intelligent system for lighting control

in smart cities

2016

To carry out this management, the architecture merges various techniques of artificial intelligence (AI) and statistics such as artificial neural networks (ANN), multi-agent systems (MAS), EM algorithm, methods based on ANOVA, and a Service Oriented Approach (SOA).

Uncertainty and risk analysis are other factors that play a crucial role in the optimization of energy resources within construction projects As construction activities are influenced by various uncertainties, such as material availability, workforce productivity, and equipment reliability, it is essential to develop optimization models that account for these uncertainties By incorporating risk analysis into the models, construction stakeholders can make more robust decisions, mitigating potential risks and uncertainties that may arise during project execution Addressing this research gap will lead to more resilient and efficient energy optimization strategies, ensuring better project outcomes

In the context of energy efficiency in construction, uncertainty and risk analysis offer opportunities to enhance decision-making processes However, current research lacks comprehensive models that fully consider the impact of uncertainties

on energy resource optimization There is a need for advanced algorithms that can effectively handle uncertainties and develop risk-aware strategies By addressing this gap, construction managers and decision-makers can gain better insights into potential risks, allowing them to devise strategies that optimize energy consumption and enhance project performance while minimizing the adverse effects of uncertainties

Despite the significance of Life Cycle Assessment (LCA) in optimizing energy resources in construction projects, there are notable research gaps that need to

be addressed One major gap is the limited integration of LCA methodologies into existing energy optimization models Many energy optimization models primarily

focus on the operational phase of buildings, neglecting the embodied energy of materials used in construction and their impacts on the environment throughout the building's entire life cycle Bridging this gap requires the development of comprehensive LCA-based energy optimization models that consider the full life cycle of construction projects, enabling a more accurate evaluation of their environmental sustainability

Another research gap lies in the practical implementation of LCA in construction projects While LCA is a valuable tool for assessing environmental impacts, its application in real construction settings remains challenging due to data availability and computational complexities More research is needed to develop user-friendly tools and methodologies that construction practitioners can readily employ to conduct LCA during the design and planning stages By addressing these research gaps, the construction industry can better harness the potential of LCA to guide energy-efficient decision-making, leading to more sustainable and environmentally responsible construction practices in smart cities

The integration of renewable energy sources presents promising opportunities for energy-efficient construction projects in smart cities However, there are significant research gaps that need to be addressed to realize the full potential of renewable energy integration One major challenge is the intermittency of renewable energy generation, which can lead to fluctuations in power supply Addressing this gap requires the development of innovative energy storage and management solutions that can effectively balance the intermittent nature of renewable sources and ensure a stable and reliable energy supply throughout construction projects

Moreover, the impact of renewable energy integration on the overall performance of construction microgrids and smart city infrastructure is not yet fully understood Further research is needed to assess the technical and economic feasibility of incorporating renewable energy sources into construction projects on a larger scale This includes evaluating the potential cost savings and environmental benefits associated with renewable energy adoption and identifying potential barriers and opportunities for successful implementation By addressing these research gaps, construction project managers and city planners can make informed decisions about

integrating renewable energy sources, paving the way for more sustainable and energy-efficient smart cities

The utilization of high-quality data is essential for accurate energy optimization in construction projects within smart cities However, data accessibility and privacy concerns pose significant research gaps that need to be addressed Construction projects often involve multiple stakeholders and data sources, leading to challenges in data collection, sharing, and integration Researchers must explore ways to ensure seamless data access and interoperability among various construction-related systems to enhance the effectiveness of energy optimization models

In addition to data accessibility, privacy concerns also arise when collecting and sharing construction-related energy data As energy optimization models rely on

a vast amount of sensitive information, ensuring data privacy and security is crucial Researchers need to focus on developing robust data protection measures and privacy frameworks that comply with regulations and standards while allowing for the efficient exchange of data Addressing these research gaps will foster a collaborative environment and enable construction stakeholders to confidently contribute and utilize energy-related data to drive better decision-making and energy-efficient outcomes in smart city construction projects

Moreover, research is needed to develop smart grid optimization algorithms tailored to the unique requirements of construction projects These algorithms should consider construction-specific variables, such as project timelines, resource availability, and workforce activities, to deliver real-time energy management solutions that adapt to dynamic project conditions By addressing these research gaps, smart grid technologies can be effectively harnessed to optimize energy consumption, promote sustainability, and enhance the overall performance of construction projects within smart cities

Real-time energy management in construction projects is a crucial aspect that can significantly impact energy optimization and resource allocation However, there are notable research gaps in this area that need to be addressed to enhance the effectiveness of real-time energy management strategies One of the key challenges is the development of dynamic energy optimization models that can adapt to fluctuating