A multi-objective neural network trained with differential evolution for dynamic economic emission dispatch

Multi-objective optimisation has received considerable attention in recent years as many real world problems have multiple conflicting objectives. There is an additional layer of complexity when considering multi-objective problems in dynamic environments due to the changing nature of the problem. A novel Multi-Objective Neural Network trained with Differential Evolution (MONNDE) is presented in this research. MONNDE utilizes Neural Network function approximators to address dynamic multi-objective optimisation problems. Differential Evolution (DE) is a state of the art single objective global optimisation problems and will be used to evolve neural networks capable of generating Pareto fronts. The proposed MONNDE algorithm has the added advantage of developing an approximation of the problem that can produce further Pareto fronts as the environment changes with no further optimisation needed. The MONNDE framework is applied to the Dynamic Economic Emission Dispatch (DEED) problem and performs equally optimal when compared to other state of the art algorithms in terms of the 24 h cost and emissions. This research also compares the performance of fully and partially connected networks and discovers that dynamically optimising the topology of the neural networks performs better in an online learning environment than simply optimising the network weights.