학술논문

Monotonic Controller for Battery Energy Storage System Using Neural Network
Document Type
Conference
Source
2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies (GlobConHT) Renewable Energy and Hydrogen Technologies (GlobConHT), 2023 IEEE IAS Global Conference on. :1-7 Mar, 2023
Subject
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Power, Energy and Industry Applications
Robotics and Control Systems
Economics
Training
Renewable energy sources
Neural networks
Control systems
Batteries
Smart grids
Battery energy storage system
classical controller
monotonic controller
neural network
Language
Abstract
Demand-generation mismatch introduces extensive technical as well as economic challenges to the power system network. Furthermore, with the increasing global interest in integrating variable renewable generation systems, it becomes more challenging to eliminate demand-generation mismatch. Therefore, the elimination of demand-generation mismatch will define the efficacy and quantify the economics of future renewable integrated smart grid systems. Incorporating batteries to provide energy buffering is among the most feasible, but most expensive, solutions to deal with system discrepancies. The battery energy storage system (BESS) has a limited life cycle and inherently lacks economic significance due to frequent charging and discharge. Therefore, in this paper, a monotonic operation of BESS is coordinated and kept between maximum and minimum State-of-Charge (SoC). The classical controller has been designed and validated with sets of generation and load profiles with two batteries. Accordingly, a neural network system based on pattern recognition is trained to operate the BESS under monotonic operation.