Real-Time Pricing-Enabled Demand Response Using Long Short-Time Memory Deep Learning

Sustainable energy development requires environment-friendly energy-generating methods. Pricing system constraints influence the efficient use of resources. Real-Time (RTP) is theoretically superior to previous pricing systems for allowing demand response (DR) activities. The DR approach has been useful correcting supply–demand imbalances as technology evolved. There are several determining and controlling DR. However, most these solutions unable control rising or forecast prices future time slots. This research provides a model management based on deep learning, where learning framework trained real-time pricing. study data in this article were taken from Australian Energy Market Operator (AEMO), was over 17 years real price demand. To investigate suggested learning-based dynamic strategy, two prediction instances addressed: actual–predicted price. We estimated outcomes using long short-term memory (LSTM), which then greatly improved by architectural changes model. findings showed that suitable terms prediction.