Analyzing the Impacts of a Deep-Learning Based Day-Ahead Residential Demand Response Model on The Jordanian Power Sector in Winter Season

Abstract

In this paper, a detailed analysis of the impact of a day-ahead residential demand response model on the winter season of Jordan’s power sector is presented and discussed. The model used is based on a deep neural network that was trained on four years of Jordan’s electrical demand data and a profit-based day-ahead demand response optimization. The day-ahead demand response model was established based on the predicted day-ahead demand and a demand response model conducted by Jordan’s Grid operator (GO) being NEPCO to reduce its energy costs from the power Generator (PGs) by applying a day-ahead peak period pricing scheme on the service providers (SPs). The results of applying the DR model on the winter season showed that a potential peak reduction of 4.49% to 8.19% could be achieved as well as a cost reduction of 64,263$ to 265,411$ per day.