Hybrid weighted probabilistic neural network and biogeography based optimization for dynamic economic dispatch of integrated multiple-fuel and wind power plants

• Integration of wind into thermal system and its impact on the DEDP are explored here.
• WPNN is proposed to forecast a one-hour ahead wind power for reliable power supply.
• BBO algorithm is integrated with SQP to obtain the better solution for DEDP.
• DEDP considering valve-point effects and multiple-fuel options has been solved.
• The proposed WPNN–BBO method is applied for a test bench DEDP and a practical DEDP.

Generally, a major power system problem is a dynamic economic dispatch problem (DEDP) which is a nonlinear and non-smooth optimization problem when multi fuel effects and valve-point effects are considered. In this research study, minimization of the overall cost of operation of wind–thermal system is carried out by employing hybridized version of weighted probabilistic neural network and biogeography based optimization. The weighted probabilistic neural network (WPNN) is proposed to forecast a one-hour ahead wind power for ensuring reliable power supply. The biogeography based optimization (BBO) algorithm is integrated with sequential quadratic programming (SQP) to obtain the better solution. The proposed hybrid WPNN–BBO method is 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 validated by comparing the results of the present method with that of the existing methodologies available in the literature.