An effective hybrid-heuristic algorithm for urban traffic light scheduling
| Autor: | Chun-Wei Tsai, Tzu-Chi Teng, Ming-Chao Chiang, Jian-Ting Liao |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | Neural Computing and Applications. 33:17535-17549 |
| ISSN: | 1433-3058 0941-0643 |
| DOI: | 10.1007/s00521-021-06341-8 |
| Popis: | The traffic light cycle optimization problem (TLCOP) is certainly one of the most critical problems in a modern traffic management system because a “good solution” will be able to reduce the total waiting time of vehicles on roads of an entire city. In addition to heuristic algorithms, metaheuristic algorithms provide an alternative way for solving this optimization problem in the sense that they provide a better solution to adjust the traffic lights to mitigate the traffic congestion problem. However, there is still plenty of room for improvement. One of the open issues is that most metaheuristic algorithms will converge to a few regions at the later stage of the convergence process and thus are likely to fall into local optima. The proposed algorithm—a hybrid heuristic algorithm called grey wolf with grasshopper optimization (GWGO)—is developed to leverage the strength of grey wolf and grasshopper optimization algorithms. The underlying idea is to use the grey wolf optimization to avoid falling into local optimum too quickly while using the grasshopper optimization to dynamically adjust the convergence speed of the search algorithm. The experimental results show that the proposed algorithm is able to find out better results than all the other state-of-the-art search algorithms for the TLCOP evaluated in this study in terms of the quality of the end results. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|