Название: Applications of Big Data and Artificial Intelligence in Smart Energy Systems: Volume 1
Автор: Neelu Nagpal, Hassan Haes Alhelou, Pierluigi Siano, Sanjeevikumar Padmanaban
Издательство: River Publishers
Серия: River Publishers Series in Computing and Information Science and Technology
Год: 2023
Страниц: 318
Язык: английский
Формат: pdf (true)
Размер: 10.9 MB

This book covers smart grid applications of various big data analytics, Artificial Intelligence, and Machine Learning technologies for demand prediction, decision-making processes, policy, and energy management. The book delves into new technologies such as the Internet of Things, BlockChain for smart home solutions, and smart city solutions in depth in the context of modern power systems.

In the era of propelling traditional energy systems to evolve towards smart energy systems, systems, including power generation energy storage systems, and electricity consumption have become more dynamic. The quality and reliability of power supply are impacted by the sporadic and rising use of electric vehicles, and domestic and industrial loads. Similarly, with the integration of solid state devices, renewable sources, and distributed generation, power generation processes are evolving in a variety of ways. Several cutting-edge technologies are necessary for the safe and secure operation of power systems in such a dynamic setting, including load distribution automation, energy regulation and control, and energy trading.

Implementing Big Data science for better and safer operation is possible in the context of future smart energy system’s digitization and automation. Smart plugs, switches, devices, smart grids, smart appliances, phase measurement, field measurement, RTUs, sensors mounted on grid-level equipment (e.g., transformers and network switches), asset inventory, SCADA system, geographic information system (GIS), weather data, traffic data, and social media are all expected to become massive data sources. This book covers real-time monitoring, control, and automation utilizing AI to access and extract data features. It will therefore include the approaches used to detect voltage instability, margin prediction, real-time fault threshold computation, nonstationary faults, line outage detection, and expedite control and planning for energy restoration and protection.

Big Data analytics is an area that has shown promising results in handling complex problems such as electricity demand forecasting. This book chapter explores the advancements in forecasting techniques of electrical demand. These advancements are explored via survey of existing literature, demonstration of techniques, and a comparative analysis of performance of Machine Learning techniques. Machine Learning techniques, viz. linear regression (LR), polynomial regression (PR), ridge regression (RR), least absolute shrinkage and selection operator (LASSO) regression, decision tree regression (DTR), random forest regression (RFR), and K nearest neighbor regression (KNNR) are demonstrated and discussed.

Technical topics discussed in the book include:

Hybrid smart energy system technologies
Smart meters
Energy demand forecasting
Use of different protocols and communication in smart energy systems
Power quality and allied issues and mitigation using AI
Intelligent transportation
Virtual power plants
AI based smart energy business models
Smart home solutions
Blockchain solutions for smart grids