Oppositional teaching learning based optimization approach for combined heat and power dispatch

• This paper presents TLBO and OTLBO to solve combined heat and power dispatch problem.
• The proposed methods are implemented on three standard test systems.
• The effectiveness of the proposed methods are compared with other reported algorithms.
• Robustness of the proposed methods are checked through statistical analysis.

This paper presents a new optimization technique i.e. teaching learning based optimization (TLBO) to solve combined heat and power dispatch (CHPD) problem with bounded feasible operating region. To accelerate the convergence speed and improve the simulation results, opposition based learning (OBL) is incorporated in basic TLBO algorithm. The potential of the proposed TLBO and oppositional TLBO (OTLBO) algorithms are assessed by means of an extensive comparative study of the solutions obtained for three different standard combined heat and power dispatch problems of power systems. The results of the proposed methods are compared with other popular optimization techniques like evolutionary programming (EP), three variants of particle swarm optimization (PSO), real coded genetic algorithm (RCGA), differential evolution (DE) and bee colony optimization (BCO). Through the simulation of MATLAB programming it is seen that OTLBO provides better results than all other optimization techniques at less computational time.