Cyber-Resilient Trading for Sustainable Energy Management: A Three-Phase Demand-Side Management Solution with Integrated Deep Learning-Based Renewable Energy Forecasting

Rising technological advancement has resulted in increased demand for power. As a result of this tendency, conventional fuel stocks have been severely exhausted. Energy suppliers are concerned about the sustainability of their grid's electricity dependability as fuel sources dwindle. Also, to reduce carbon footprints, governments throughout the world are exerting pressure on the energy sector to convert to cleaner energy sources. In order to lower the system's dependence on traditional fuel reserves during peak demand hours and progress towards introducing greener energy into the network with no discernible generation intermittency, an efficient scheduling model has been developed in this article to regulate end-user load as well as solar generation. The scheduling model is built with a long-short term memory (LSTM) network-based solar energy prediction approach integrated with a load and solar energy scheduling model based on Teaching-Learning Optimization (TLBO). In addition to effective scheduling, a secure trade platform based on blockchain technology is being developed for utility and prosumer interaction in a cyber-secured environment. The suggested technique is intended for three-phased distribution networks, and its effectiveness is demonstrated using a 906-bus low voltage European distribution network. The proposed methodology is developed using MATLAB and Remix IDE interface. The effectiveness of the considered optimization in the proposed scheduling model is tested against another population-based optimization based identical scheduling model.