IEEE Trans Cybern. 2016 Aug;46(8):1771-83. doi: 10.1109/TCYB.2016.2522471. Epub 2016 Feb 15.
The growing ubiquity of vehicles has led to increased concerns about environmental issues. These concerns can be mitigated by implementing an effective carpool service. In an intelligent carpool system, an automated service process assists carpool participants in determining routes and matches. It is a discrete optimization problem that involves a system-wide condition as well as participants' expectations. In this paper, we solve the carpool service problem (CSP) to provide satisfactory ride matches. To this end, we developed a particle swarm carpool algorithm based on stochastic set-based particle swarm optimization (PSO). Our method introduces stochastic coding to augment traditional particles, and uses three terminologies to represent a particle: 1) particle position; 2) particle view; and 3) particle velocity. In this way, the set-based PSO (S-PSO) can be realized by local exploration. In the simulation and experiments, two kind of discrete PSOs-S-PSO and binary PSO (BPSO)-and a genetic algorithm (GA) are compared and examined using tested benchmarks that simulate a real-world metropolis. We observed that the S-PSO outperformed the BPSO and the GA thoroughly. Moreover, our method yielded the best result in a statistical test and successfully obtained numerical results for meeting the optimization objectives of the CSP.
车辆的普及导致人们对环境问题的担忧日益增加。通过实施有效的拼车服务可以减轻这些担忧。在智能拼车系统中，自动化服务流程可以帮助拼车参与者确定路线和匹配。这是一个涉及系统全局条件和参与者期望的离散优化问题。在本文中，我们解决了拼车服务问题 (CSP) 以提供满意的乘车匹配。为此，我们开发了一种基于随机集粒子群优化 (SPSO) 的粒子群拼车算法。我们的方法通过引入随机编码来增强传统粒子，并使用三个术语来表示粒子：1）粒子位置；2）粒子视角；3）粒子速度。通过这种方式，可以通过局部探索来实现基于集的粒子群优化 (S-PSO)。在模拟和实验中，我们比较和检验了两种离散粒子群算法-S-PSO 和二进制粒子群算法 (BPSO) 以及遗传算法 (GA)，并使用模拟现实大都市的测试基准进行了测试。我们观察到 S-PSO 彻底优于 BPSO 和 GA。此外，我们的方法在统计测试中取得了最佳结果，并成功获得了满足 CSP 优化目标的数值结果。
