Artificial intelligence-enabled probabilistic load demand scheduling with dynamic pricing involving renewable resource

Residential demand response is one of the key enabling technologies which plays an important role in managing load prosumers. However, scheduling problem becomes quite challenging due to involvement dynamic parameters and renewable energy resources. This work has proposed a bi-level mechanism with electricity pricing integrated storage system overcome this problem. The first level involves formulation optimization problems as optimal stopping objective consumption delay cost minimization. involved real-time signal, customers priority, machine learning (ML) based forecasted demand, & unit profiles, solved using mathematical programming branch-and-cut branch-and-bound algorithms. Since first-level formulated problem, time slots are obtained one-step lookahead rule schedule ability handle uncertainties. second used further model through signal. minimization function then genetic algorithm (GA), where input from solution. Furthermore, impact prioritization terms factor price also modeled allow end-users control their load. Analytical simulation results conducted solar-home data, Ausgrid, AUS validate model. Results show that can uncertainties process along cost-effective solution discomfort reduction. ensures end-user satisfaction regarding