Multi-swarm PSO algorithm for the Quadratic Assignment Problem: a massive parallel implementation on the OpenCL platform
This work addresses optimization efficiency for combinatorial problems like QAP, but it is incremental as it extends existing PSO methods with parallel implementation.
The paper tackles the Quadratic Assignment Problem by developing a multi-swarm PSO algorithm implemented on OpenCL for parallel execution, showing that large populations enable full exploitation of parallelism and demonstrating that particle behavior appears chaotic individually but collectively increases the probability of near-optimal solutions.
This paper presents a multi-swarm PSO algorithm for the Quadratic Assignment Problem (QAP) implemented on OpenCL platform. Our work was motivated by results of time efficiency tests performed for single-swarm algorithm implementation that showed clearly that the benefits of a parallel execution platform can be fully exploited, if the processed population is large. The described algorithm can be executed in two modes: with independent swarms or with migration. We discuss the algorithm construction, as well as we report results of tests performed on several problem instances from the QAPLIB library. During the experiments the algorithm was configured to process large populations. This allowed us to collect statistical data related to values of goal function reached by individual particles. We use them to demonstrate on two test cases that although single particles seem to behave chaotically during the optimization process, when the whole population is analyzed, the probability that a particle will select a near-optimal solution grows.