Intelligent learning aproaches for renewable and sustainable energy [electronic resource] / edited by Josep M. Guerrero, Pankaj Gupta, Ritu Kandari, Alexander Micallef.

Saved in:
Bibliographic Details
Online Access: Full Text (via ScienceDirect)
Format: Electronic eBook
Language:English
Published: Amsterdam : Elsevier, 2024.
Subjects:
Table of Contents:
  • Front Cover
  • Intelligent Learning Approaches for Renewable and Sustainable Energy
  • Copyright Page
  • Contents
  • List of contributors
  • Preface
  • Section I: Introduction to intelligent learning approaches for renewable and sustainable energy
  • Section II: Applications of intelligence learning approaches for renewable and sustainable energy
  • Section III: Intelligent learning methods for optimizing integrated energy systems
  • I. Introduction to intelligent learning approaches for renewable and sustainable energy
  • 1 Transforming the grid: AI, ML, renewable, storage, EVs, and prosumers
  • 1.1 Introduction
  • 1.2 Artificial intelligence and machine learning in the modern grid
  • 1.2.1 AI-based load forecasting
  • 1.2.2 AI-based renewable energy forecasting
  • 1.2.3 EVs operation, AI, and modern grid integration
  • 1.2.4 AI in modern grid fault diagnostics
  • 1.3 Status of RES and storage systems in the modern grid
  • 1.3.1 Status of RES in the modern grid
  • 1.3.1.1 Solar energy
  • 1.3.1.2 Wind energy
  • 1.3.1.3 Other renewable energy sources
  • 1.3.2 Status of storage systems in the modern grid
  • 1.4 Case study: application of AI in power electronics driven RES
  • 1.4.1 Problem formulation
  • 1.4.2 System under investigation
  • 1.4.3 Genetic algorithm for data generation
  • 1.4.3.1 Objective function
  • 1.4.4 ANN-based controller
  • 1.4.5 Results
  • References
  • 2 A new artificial intelligence-based demand side management method for EV charging stations
  • 2.1 Introduction
  • 2.1.1 Direct load control
  • 2.2 Problem description
  • 2.3 Proposed method
  • 2.3.1 RUS Boost tree ensemble classifiers
  • 2.4 Conclusion
  • References
  • 3 Modeling stochastic renewable energy processes by combining the Monte Carlo method and mixture density networks
  • 3.1 Introduction to stochastic phenomena in renewable energies
  • 3.2 Monte Carlo method (MCM)
  • 3.2.1 Foundations
  • 3.2.2 Algorithms
  • 3.2.3 Advantages and shortcomings
  • 3.2.4 Applications to renewable energies
  • 3.3 Mixture density networks
  • 3.3.1 Foundations of machine learning
  • 3.3.2 Gaussian distribution and Gaussian mixture
  • 3.3.3 MDN architecture
  • 3.3.4 MDN training
  • 3.3.5 Applications to the renewable energies
  • 3.4 Case study
  • 3.4.1 Formulation
  • 3.4.2 MDN-based modeling
  • 3.4.3 Monte Carlo simulation
  • 3.4.4 Analysis of the results
  • 3.5 Concluding remarks
  • Acknowledgments
  • References
  • 4 Profitability and performance improvement of smart photovoltaic/energy storage microgrid by integration of solar produ...
  • 4.1 Introduction
  • 4.2 Forecasting of solar radiation and PV production
  • 4.2.1 Brief overview of the forecasting methods for solar radiation
  • 4.2.2 Time series based forecasting methods
  • 4.2.2.1 Cleaning the data (making it stationary)
  • 4.2.2.2 Persistence and smart (or scaled) persistence
  • 4.2.2.3 ARMA model