No Detail Found!

Sensitivity Analysis of Reinforcement Learning to Schedule the Battery in Grid-tied Microgrid

Author(s)
Khawaja Haider Ali Department of Electrical Engineering, Sukkur IBA University, Sukkur, Pakistan
Hasnain Hyder Department of Electrical Engineering, Sukkur IBA University, Sukkur, Pakistan
Muhammad Asif Khan Department of Computer Science, Sukkur IBA University, Sukkur, Pakistan
Abstract
This research paper explores the application of offline reinforcement learning (RL) in controlling battery operation in a grid-connected microgrid. The study investigates the impact of different parameters on the performance of the RL algorithm, such as the number of discretization levels, gamma, and alpha values. The results show that the convergence time and optimality of the RL algorithm are affected by the choice of these parameters. The research concludes that carefully selecting the discretization levels of state-action spaces and RL hyperparameters is crucial for optimal RL algorithm performance. The benchmark offline sensitivity analysis can be compared in the future with other RL approaches, such as function approximation or DRL methods.
Publication Details
Page(s) 115-123
DOI DOI not available
Published Journal: University of Sindh Journal of Information and Communication Technology, Volume: 6, Issue: 3, Year: 2022

Request the full text from PASTIC

Keywords
convergence, Reinforcement Learning, Optimal solution, Sensitivity Analysis, Hyperparameters, gamma, Microgrid, Learning Rate, offline RL, discretisation, battery operation, cost savings, state action spaces
0

Citations

0

Downloads

37

Views