A self-adaptive differential evolution algorithm for transmission network expansion planning with system losses consideration

In this paper, a self-adaptive differential evolution algorithm (SaDEA) is applied directly to the DC power flow based model in order to efficiently solve transmission network expansion planning (TNEP) problem. The purpose of TNEP is to minimize the transmission investment cost associated with the technical operation and economical constraints. The TNEP problem is a large-scale, complex and nonlinear combinatorial problem of mixed integer nature where the number of candidate solutions to be evaluated increases exponentially with system size. In addition, the TNEP problem with system losses consideration is also investigated in this paper. The efficiency of the proposed method is initially demonstrated via the analysis of low and medium complexity transmission network test cases. A detailed comparative study among conventional genetic algorithm (CGA), tabu search (TS), artificial neural networks (ANNs), hybrid artificial intelligent techniques and the proposed method is presented. From the obtained experimental results, the proposed technique provides the accurate solution, the feature of robust computation, the simple implementation and the satisfactory computational time.