A Hybrid ALNS-Based Approach for the Electric Vehicle Routing Problem with Time Windows

Chiamaka Anicho-Okoro, Mariem Belhor, Omar Alam
Proceedings of the The 39th Canadian Conference on Artificial Intelligence, PMLR 318:212-223, 2026.

Abstract

Facing the need for low-carbon vehicle routing solutions, this paper addresses the Electric Vehicle Routing Problem with Time Windows (EVRPTW), which involves battery limitations and recharging constraints. In particular, we propose a hybrid metaheuristic approach that combines Adaptive Large Neighborhood Search (ALNS), a Greedy Time-Oriented Nearest Neighborhood Heuristic (GTONNH), and Tabu Search (TS). Experiments on standard benchmark instances show that the proposed GTONNH-ALNS-TS variant outperforms baseline approaches, achieving the best solutions on more than 60% of large-scale instances and reaching the minimum fleet size in nearly 95% of the cases. On average, the proposed approach reduces the required number of vehicles by more than one compared to classical ALNS, while maintaining competitive travel distances. High-quality solutions are obtained within a few seconds on small and medium-sized instances, highlighting the efficiency of the proposed framework.

Cite this Paper

BibTeX
@InProceedings{pmlr-v318-anicho-okoro26a, title = {A Hybrid ALNS-Based Approach for the Electric Vehicle Routing Problem with Time Windows}, author = {Anicho-Okoro, Chiamaka and Belhor, Mariem and Alam, Omar}, booktitle = {Proceedings of the The 39th Canadian Conference on Artificial Intelligence}, pages = {212--223}, year = {2026}, editor = {Bouzar-Benlabiod, Lydia and Leung, Carson}, volume = {318}, series = {Proceedings of Machine Learning Research}, month = {25--29 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v318/main/assets/anicho-okoro26a/anicho-okoro26a.pdf}, url = {https://proceedings.mlr.press/v318/anicho-okoro26a.html}, abstract = {Facing the need for low-carbon vehicle routing solutions, this paper addresses the Electric Vehicle Routing Problem with Time Windows (EVRPTW), which involves battery limitations and recharging constraints. In particular, we propose a hybrid metaheuristic approach that combines Adaptive Large Neighborhood Search (ALNS), a Greedy Time-Oriented Nearest Neighborhood Heuristic (GTONNH), and Tabu Search (TS). Experiments on standard benchmark instances show that the proposed GTONNH-ALNS-TS variant outperforms baseline approaches, achieving the best solutions on more than 60% of large-scale instances and reaching the minimum fleet size in nearly 95% of the cases. On average, the proposed approach reduces the required number of vehicles by more than one compared to classical ALNS, while maintaining competitive travel distances. High-quality solutions are obtained within a few seconds on small and medium-sized instances, highlighting the efficiency of the proposed framework.} }
Endnote
%0 Conference Paper %T A Hybrid ALNS-Based Approach for the Electric Vehicle Routing Problem with Time Windows %A Chiamaka Anicho-Okoro %A Mariem Belhor %A Omar Alam %B Proceedings of the The 39th Canadian Conference on Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Lydia Bouzar-Benlabiod %E Carson Leung %F pmlr-v318-anicho-okoro26a %I PMLR %P 212--223 %U https://proceedings.mlr.press/v318/anicho-okoro26a.html %V 318 %X Facing the need for low-carbon vehicle routing solutions, this paper addresses the Electric Vehicle Routing Problem with Time Windows (EVRPTW), which involves battery limitations and recharging constraints. In particular, we propose a hybrid metaheuristic approach that combines Adaptive Large Neighborhood Search (ALNS), a Greedy Time-Oriented Nearest Neighborhood Heuristic (GTONNH), and Tabu Search (TS). Experiments on standard benchmark instances show that the proposed GTONNH-ALNS-TS variant outperforms baseline approaches, achieving the best solutions on more than 60% of large-scale instances and reaching the minimum fleet size in nearly 95% of the cases. On average, the proposed approach reduces the required number of vehicles by more than one compared to classical ALNS, while maintaining competitive travel distances. High-quality solutions are obtained within a few seconds on small and medium-sized instances, highlighting the efficiency of the proposed framework.
APA
Anicho-Okoro, C., Belhor, M. & Alam, O.. (2026). A Hybrid ALNS-Based Approach for the Electric Vehicle Routing Problem with Time Windows. Proceedings of the The 39th Canadian Conference on Artificial Intelligence, in Proceedings of Machine Learning Research 318:212-223 Available from https://proceedings.mlr.press/v318/anicho-okoro26a.html.

Related Material