A Primal Dynamic Neural Network for Solving a Multi-objective Environmental/Economic Dispatch

This paper explores the performance of Gradian-based Dynamic Neural Networks (G-DNN), to solve one of the most important energy problems called the “Environmental-Economic Dispatch (EED)”. The idea behind the Combined Economic Emission Dispatch (CEED) formulation is to reduce costs, save energy, and reduce environmental pollution. By adopting the maximum / maximum price penalty factor, the multi-objective CEED optimization problem is transformed into a single- objective optimization problem. The proposed approach has a good performance in finding a diverse set of solutions and in converging near the desired optimal generated powers. To highlight the performance of the proposed technique, it is tested on the test system with three units. The numerical results of several case studies are compared with other published methods in the literature and confirm the effectiveness of G-DNN against other existing methods.