Introduction
The present world is looking for feasible alternatives to conventional fossil fuels. Integrating renewable energy sources with the existing grid has proved to be a viable solution. As the renewable sources are inherently intermittent, energy storage systems are essential to provide reliable power to the consumers. The controllers play a vital role in providing the stable power output to the loads by reducing the variations between the expected and actual parameters. Smart grid is a promising and self-sufficient system which is based on digital automation technologies to monitor, control & provide effective solutions to the utilities and consumers. Now-a-days, to reduce the carbon dioxide gas emission from the motor vehicles and to save mother nature, the electric vehicles are becoming more practical. This book chapter is mainly aimed to focus on the areas of integration of renewable energy sources with existing grid, to introduce power exchange scenario in the prevailing power market, to control the voltage and frequency along with power management in hybrid micro grid, to expand the use of electric vehicle market for creating cleaner and transformative energy, to optimize the control variables with artificial intelligence techniques. The chapters will be discussed the algorithms involved, methodology used, solution techniques and its implementation, results with its discussion.
In the generation of climate-conscious people, traditional Internal Combustion (IC) engine based vehicles are rapidly replaced by eco-friendly Electric Vehicles (EV). Electric motor based transportation systems are employed in all forms of transport like land (e-Bikes, Cars, light good transport), air (Drones) and sea (Electric ferry boats). Due to the usage of high amount of electricity for charging of electric vehicles, conventional grid technologies may fail, which leads to catastrophic failures. Smart grid integrated with the renewable energy sources can effectively balance the load using integrated and intelligent monitoring and control systems. Vehicle-to-grid technology is used to balance the energy in the smart grid.
Battery Management System (BMS) monitors performance of the battery packs present in the electric vehicle. BMS evaluates the State of Charge (SoC) of the battery. It estimates SoC by measuring different parameters like current, voltage and temperature of the battery. It predicts the battery level, which the critical parameter in deciding remaining charge state, especially in electric vehicles. It helps in maximizing the efficiency of the battery and also improves the charging/discharging performance. BMS also estimate state of state of health and depth of discharge by measuring various parameters of the battery. It is integrated with vehicle management system. BMS system consists of both hardware and software components. BMS hardware components include automobile grade sensors and controllers. BMS performs additional functionalities like protection, diagnosis and data management.
Electric Vehicle Routing Problem is an optimization problem that deals with the framing of effective route plans for electric vehicle while fulfilling a set of batter power related constraints. This problem aims to find the optimized schedule for Electric Vehicles (EV) while considering the set of operational constraints like geography of charging stations, vicinity of charging station, number of charging points available in particular station, charging speed and time, power drawn from grid, and vehicle’s battery capacity and state of charge. Routing Problem in electric vehicles can be considered as a special case of traditional traveling salesman problem with different operational constraints. Operational constraints include recharging policy, charging technology used, and availability of battery swapping stations. EV’s characteristic parameters like travel distance, speed, vehicle tonnage, and gradient of road are also considered for optimized route plan. Routing problem is well utilized in EV based logistic delivery, public transportation system and EV based shuttle services.
Artificial Intelligence (AI) techniques like machine learning, deep learning and reinforcement learning algorithm plays a major role in forecasting of demand and supply of electrical energy in smart grid. In Electric Vehicles, AI techniques are used in self-driving autonomous cars, intelligent battery monitoring systems and prognostics of faults in EV prime movers.
This book provides a curated content in the applications of AI techniques in EV and smart grid. It delivers the peer reviewed and well tested results that can be directly used by researchers and industry professionals to develop new concepts and products. It deals with recent developments in the niche areas like energy forecasting from renewable energy sources, active load balancing in the smart grids integrated with solar and wind power and block chain based peer to peer energy transactions. It also deals with the topics in the developing fields like Vehicle-to-Grid (V2G), where there is bidirectional energy flow between vehicle and smart gird. V2G is gaining popularity, due to its ability to both charge and receive power from EV during peak loads.
Artificial intelligence techniques applied in power system sector makes the prediction of renewable power source generation and demand in an efficient and effective way. Moreover, these techniques are more powerful for solving the complexity of various energy sources having large size of data. By integrating clustering algorithms, the solar power generation can be estimated for effective analysis. The forecasting methods may be very-short, short, medium and long term depending on the characteristics of the systems developed. This book chapter contents are focusing on these artificial intelligence techniques for the evolving power system filed, electric vehicle market, energy storage elements and renewable energy source integration as distributed generators. The current trend of electric vehicle battery management system, vehicle routing problems will be elaborated in the proposed book chapters.