Application of Social Spider Algorithm to Optimize Train Energy

Abstract

This study incorporated the social spider algorithm (SSA), which simulates the preying behaviors of a group of spiders, to explore energy-efficient train operations. In this SSA, the magnitude of the vibration signal transmitted by the prey on a simulated spider web was used to determine the location with the most abundant food, which was equivalent to the optimal solution for train acceleration. In addition, a random movement model was implemented in the SSA to facilitate its capability for both local and global search and thereby increase its probability in identifying the optimal solution. A railroad route in Taiwan was simulated to verify the feasibility of this approach; the simulated data were then compared with the measured data from the actual test. According to the measured data, the SSA can formulate feasible railroad energy conservation plans and can assist locomotive engineers in planning their train operations. The results of the SSA were also compared to those of the teaching–learning-based optimization, to validate the superiority of the SSA.