Simulation and Machine Learning Models for Energy Policy Design.

Format:

Book

Author/Creator:

Adedoyin BSc, M. S. c.

Language:

English

Physical Description:

1 online resource (392 pages)

Edition:

1st ed.

Place of Publication:

Chantilly : Elsevier, 2025.

Summary:

Simulation and Machine Learning Models for Energy Policy Design explores how policy design can reduce emissions in support of climate action by emphasizing the integration of cutting-edge simulation and machine learning techniques and bridging the gap between theoretical frameworks and practical implementation, therefore offering a hands-on guide.

Contents:

Front Cover

Simulation and Machine Learning Models for Energy Policy Design

Copyright

Dedication

Contents

Contributors

About the editor

Preface

Acknowledgments

Introduction

One - Introduction: Rethinking energy policy in the digital age

Theoretical framework

Literature review

Research gap

Discussion

Conclusion

References

Further reading

Two - Ethical and regulatory dimensions of energy policy models

Three - Data-driven decision making: Harnessing energy data for policy

Combining policy design, targeted interventions, and operational optimization

UK power system participants and data roles

Case studies

Challenges

The role of data in energy policy design, targeted interventions, and operational optimization

UK power system participants and data in UK power system

Case study: UK Green Homes Grant (GHG)

Case study: Optimal sizing and operations of batteries for managing network constraints

Expected outcomes

Challenges and considerations

Data quality and reliability

Data privacy and security

Interoperability and standardization

Scalability and complexity

Organizational and cultural challenges

Cost and resource allocation

Acknowledgement

Four - Simulating energy systems: Case studies of food waste management and environmental degradation in the USA

Environmental impact assessment theory

Food waste management and environmental degradation

Research gap/novelty

Data, models and methods

Data and variables.

Description of variables

Model and methods

Policy simulations and an application of the novel dynamic ARDL model

Dynamic ARDL simulation exercise: Methodological approach

Stationarity test

ARDL estimation, diagnostic, and postestimation diagnostic measures

Novel dynamic ARDL simulations

Results and discussion

ARDL model estimation

ARDL model diagnostic

ARDL regression: Postestimation diagnostics

Food waste management policy simulations

Kernel-based regularized least squares (KRLS)

Discussion: Simulated shocks to food waste management policies in the USA

Conclusion and policy directions

Five - Machine learning algorithms for policy optimization. Application to energy consumption in manufacturing

Challenges in applying machine learning to energy consumption optimization

Data quality and availability

Model interpretability and transparency

Scalability and computational efficiency

Case study and practical application: Predicting and optimizing milling parameters for energy efficiency in end-milling

Experiment procedure

Methodology

Predictive results

Multi-objective optimization using NSGA-II

Future directions and emerging trends

Integration of renewable energy sources

Advances in algorithm development

Policy implications and sustainability

Conclusion and outlook

Funding

Conflicts of interest

Six - Efficiency policies and beyond: Leveraging machine learning

Review of literature

The theoretical framework

Ecological footprint and environmental tax theory

Environmental tax and policy experiment to test the impact of policy options on achieving 2050 Net Zero targets

Model and methods

Dynamic ARDL model

ARDL regression: post-estimation diagnostics

Environmental tax policy simulations

Dynamic ARDL simulations

Seven - Efficiency of simulation and machine learning algorithms for modeling and forecasting greenhouse gas emissi ...

Overview of background, dilemma, and necessity of a green transition for the Central American power system

Overview of the development of machine learning techniques

Overview of greenhouse gases and energy crisis

Energy crisis in Europe

The need for forecasting

Classification of models based on age

The old age (1990-99)

The mid age (2000-09)

The new age (2010-till present)

Tabular data on related work analysis

Author contributions

Eight - Sustainable renewable energy transitions: Data-driven strategies for the East African Community (EAC)

Descriptive analysis and correlation matrix

Diagnostic tests

Nine - A machine learning-based simulation experiment on the impact of transportation energy consumption on carbon ...

Research objectives

Chapter structure

Transportation energy consumption and carbon emissions nexus using ML

Nonrenewable energy consumption and carbon emission nexus using ML

Ten - Plastic wastes and sustainability targets in Germany: A policy simulation experiment using machine learning.

Introduction

Problem definition

Aim

Objectives

Overview of plastic waste and factors on carbon emissions

Policy simulations using machine learning

Plastic wastes and sustainability

Factors influencing carbon emissions

Integrated modeling approaches

Policy simulation studies

Eleven - Energy use modeling and tracking in a university environment using machine learning algorithms

Overview of climate change

Behavior toward climate change

Analyzing behavior change

Behaviors toward the environment

Proenvironmental behavior

Environmental concern

Environmental concern and positive environmental behavior

Factors of energy consumption and climate change mitigation behavior

Policies for solving climate change

Behavioral models

The Attitude-Behavior-Context model

Triandis' Theory of Interpersonal Behavior

Energy intervention measures

Information to feedback

Smart metering

Use of dashboards

Energy meters

Dashboard preparation

Data ingestion

Data preparation

Forecasting

Data pipeline

Data visualization

Dashboard feedback

Results

Poole Gateway Building

Data output

Missing data and outliers

Electricity consumption over the years

Consumption in 2020

Electricity consumption in 2021

Consumption behavior in 2022

Electricity consumption in 2023

Carbon emissions

Renewable energy

Forecast

Feedback from questionnaire

Occupants influence on energy consumption

Renewable energy in Bournemouth University

Education of the community in BU

Appendices

Appendix A: Power automate flow

Appendix B: Logic apps flow

Index

A

B

C

D

E

F

G

I

J

K

L

M.

N

O

P

Q

R

S

T

U

Back Cover.

Notes:

Description based on publisher supplied metadata and other sources.

ISBN:

0-443-33972-4

9780443339721

OCLC:

1547927351