Electrical and Computer Engineering ETDs

Publication Date

Summer 7-30-2021


The stochastic fluctuations from Renewable Energy Resources (RER) have a great influence on power quality and off-grid communities. A combination of the different storage systems is accessible for RER generation intermittency and to bring about finest smoothing operating cycle compared to sole Energy Storage System (ESS). Additionally, energy management in Hybrid Energy Storage System (HESS) creates an uncertainty during power smoothing operation. This research materializes, an intelligent mechanism for power smoothing and dispatch with the introduction of hybridized storage that can accommodate the unpredictable behavior of RER under dynamic load. A feed-forward neural network is proposed as a power smoothing model for a RER with supercapacitors (SC) and battery energy storage (BES). The novelty of the research is adopted from the Reinforcement Learning (RL) based Deep Deterministic Policy Gradient (DDPG) approach to control the charge/discharge of HESS by removing severely fluctuating current exchange. The proposed distributed control architecture is developed using the Matlab/Simulink model for analyzing its efficiency in achieving power dispatch, smoothing, and compares to other strategies in the literature in terms of SC coordination with RER and BESS.


Hybrid Energy Storage Systems, Neural Network, Power Balancing, Power Dispatch, Power Management, Power Smoothing, Reinforcement Learning

Document Type




Degree Name

Electrical Engineering

Level of Degree


Department Name

Electrical and Computer Engineering

First Committee Member (Chair)

Dr. Ali Bidram

Second Committee Member

Dr. Marios Pattichis

Third Committee Member

Dr. Ramiro Jordan