Energy and spinning reserve scheduling for a wind-thermal power system using CMA-ES with mean learning technique

The goal of the paper is to solve economic dispatch problem and to find optimal scheduling/allocation of energy and spinning reserves among the thermal and wind generators available to serve the demand. There is a considerable need for the alternative energy sources in the economic dispatch problem, hence wind energy generators are used. The stochastic behavior of wind speed and wind power is represented by Weibull probability density function. The total cost minimization objective considered in this paper includes cost of energy provided by conventional thermal generators and wind generators, cost of reserves provided by conventional thermal generators. It also includes costs due to over-estimation and under-estimation of available wind power. Covariant Matrix Adaptation with Evolution Strategy (CMA-ES) with mean learning technique (MLT) is used to solve the proposed economic dispatch problem for both conventional power system, and wind-thermal power system considering the provision for spinning reserves. In order to show the effectiveness and feasibility of the proposed frame work, various case studies are presented for two different test systems.