Prediction Techniques for Renewable Energy Generation and Load Demand Forecasting

Preface
Contents
Editors and Contributors
Introduction to Renewable Energy Prediction Methods
	1 Introduction
		1.1 Renewable Energy Status of the World
		1.2 Artificial Intelligence in Power System
		1.3 AI for Wind Energy Prediction
		1.4 Energy Prediction Models
		1.5 AI for Solar Prediction
	References
Solar Power Forecasting in Photovoltaic Modules Using Machine Learning
	1 Introduction
	2 Methodology
		2.1 Dataset
		2.2 Data Pre-processing
		2.3 Holt-Winters Method
		2.4 Auto-Regression Method
		2.5 ARIMA
		2.6 SARIMAX
	3 Results
	4 Conclusion
	References
Hybrid Techniques for Renewable Energy Prediction
	1 An Overview About Hybrid Techniques for Time Series Prediction
	2 Hybrid Techniques for Hydropower Prediction
		2.1 Model Ensemble
		2.2 Parameters Determination Based on Meta-Heuristic Methods
		2.3 Time Series Decomposition
		2.4 Other Hybrid Methods
	3 Hybrid Techniques for Wind Power Prediction
		3.1 Model Ensemble
		3.2 Parameters Determination Based on Meta-Heuristic Methods
		3.3 Time Series Decomposition
		3.4 Other Hybrid Methods
	4 Hybrid Techniques for Solar Power Prediction
		4.1 Model Ensemble
		4.2 Parameters Determination Based on Meta-Heuristic Methods
		4.3 Time Series Decomposition
		4.4 Other Hybrid Methods
	5 Conclusion and Future Perspectives
	References
A Deep Learning-Based Islanding Detection Approach by Considering the Load Demand of DGs Under Different Grid Conditions
	1 Introduction
	2 Data Generation and Test System
		2.1 Data Generation Using Mathematical Models and Simulation Models
		2.2 Islanding Test System
	3 Islanding Detection Techniques
		3.1 Conventional (Local and Remote) Techniques
		3.2 Signal Analysis-Based Methods
		3.3 Machine Learning-Based Techniques Using Signal Analysis, Feature Selection, and Classifier Methods
		3.4 Deep Learning-Based Techniques
	4 Proposed Hybrid Model Using CNN and LSTM
		4.1 Results
	5 Discussion and Conclusion
	References
Comparison of PV Power Production Estimation Methods Under Non-homogeneous Temperature Distribution for CPVT Systems
	1 Introduction
	2 System, Modeling, and Evaluation
		2.1 Definition of the CPVT System
		2.2 Mathematical Modeling of PV
	3 Results and Discussion
	4 Conclusions
	References
Renewable Energy Predictions: Worldwide Research Trends and Future Perspective
	1 Introduction
	2 Data
	3 Subjects from Worldwide Publications
	4 Countries, Affiliations, and Their Main Topics
	5 Keywords from Worldwide Publications
	6 Worldwide Research Trends: Cluster Analysis
	7 Evolution of the Research and Future Perspective
	References
Models of Load Forecasting
	1 Introduction
	2 Types of Load Forecasting
	3 Factors Affecting Load Forecasting
		3.1 Meteorological Factors: It is Further Divided into Two Sub Parts that are ‘Climate’ and ‘Weather’
		3.2 Temporal and Calendar Factors
		3.3 Economy Factors
		3.4 Random Factors
		3.5 Customer Factors
		3.6 Factors Based on Time Horizon
		3.7 Other Factors
	4 Comparative Review of Popular Load Forecasting Techniques
		4.1 Techniques Based on Machine Learning
		4.2 Techniques Based on Deep Learning (DL)
		4.3 Techniques Based on Artificial Intelligence
	5 Conclusion
	References
Load Forecasting Using Different Techniques
	1 Introduction
	2 Fuzzy Logic-Based Forecasting
		2.1 Architecture of Fuzzy Logic
		2.2 Fuzzy Logic Model
	3 Artificial Neural Network
		3.1 Architecture of Artificial Neural Network
		3.2 ANN Method for Load Forecasting
	4 Adaptive Neuro-Fuzzy Interference System
		4.1 Architecture of ANFIS
		4.2 ANFIS Model for Load Forecasting
	5 Conclusion
	References
Time Load Forecasting: A Smarter Expertise Through Modern Methods
	1 Introduction
	2 Types of Electrical Load Forecasting
		2.1 Long Term
		2.2 Medium Term
		2.3 Short Term
	3 Existing Models of Load Forecasting
	4 Controlling Method in Load Forecasting
		4.1 Classical Methods in Load Forecasting
		4.2 Modern Techniques in Load Forecasting
	5 Hybrid Method and a Classification System for Load Forecasting Models
	6 Case Study
		6.1 Problem Formulation
		6.2 Input Data
		6.3 Result
	7 Conclusion
	References
Deep Learning Techniques for Load Forecasting
	1 Introduction
		1.1 Motivation
		1.2 Compilation of Published Papers on Data-Driven Approaches for Load Forecasting
		1.3 The Aim of the Literature Review
		1.4 Objectives and Contributions
	2 Deep Learning Techniques
		2.1 History, Categorization, and a General Description
		2.2 Autoencoder
		2.3 Recurrent Neural Network
		2.4 Long Short-Term Memory (LSTM)
		2.5 Convolutional Neural Networks
		2.6 Deep Belief Networks
		2.7 Deep Feed-forward Neural Networks
	3 Trends in the Present
		3.1 Level of Building Application
		3.2 Qualities of Data
		3.3 Output Variables
		3.4 Input Styles
		3.5 Granularity of Time
	4 Feature Extraction Applications Using Deep Learning
	5 Application Summary at the Load Level
	6 Results and Discussion
		6.1 Challenges
		6.2 Data Collection and Results
		6.3 Future Research Prospects
	7 Conclusion
	References