Comparative Study of Effective Wind Power Prediction Methods with Optimization Algorithms for Optimal Economic Dispatch of Multiple Fuel Power Plants

Generally, a major power system problem is dynamic economic dispatch problem (DEDP) for multiple fuel power plants. This problem is a nonlinear and nonsmooth optimization problem when multi fuel effects and valve-point effects are considered. In this contribution, Improved Radial Basis Function Network (IRBFN) and Weighted Probabilistic Neural Network (WPNN) are compared and employed to forecast a one-hour ahead wind power for ensuring reliable power supply. Also Teaching Learning Based Optimization (TLBO) and biogeography based optimization is utilized to minimize the overall cost of operation of wind – thermal power system. The above algorithms are integrated with Sequential Quadratic Programming (SQP) for fine tuning the better solutions to reach the optimized minimal level. The proposed hybrid neural network model with the considered algorithms are applied for a test bench DEDP and a practical DEDP wind power forecasted based on real time data from Wind Power Plant. The effectiveness of the approach is also validated with the comparison of the existing methodologies available in the literature.