Sürdürülebilir Kalkınma Amaçları
Yayınlar
- ArticleAçık Erişim2026Double Deep Q-Network-Based Solution for the Dynamic Electric Vehicle Routing Problem
Taş, Mehmet Bilge Han; Özkan, Kemal; Sarıçiçek, İnci; Yazıcı, Ahmet
The Dynamic Electric Vehicle Routing Problem (D-EVRP) presents a framework that requires electric vehicles to meet demand with limited energy capacity. When dynamic demand flows and charging requirements are considered together, traditional methods cannot provide sufficient adaptation for real-time decision-making. Therefore, a learning-based approach was chosen to ensure that decision-making processes respond quickly to changing conditions. The solution utilizes a model with a Double Deep Q-Network (DDQN) architecture and a discrete valuation structure. Prioritized Experience Replay (PER) was implemented to increase model stability, allowing infrequent but effective experiments to contribute more to the learning process. The state representation is constructed using the vehicle’s location, battery level, load status, and current customer demands. Scalability is ensured by dividing customer locations into clusters using the K-means method, with each cluster handled by an independent representative. The approach was tested with real-world road data obtained from the Meşelik Campus of Osmangazi University in Eskişehir. Experiments conducted under different demand levels and data sizes have shown that the PER-assisted DDQN structure produces more stable and shorter route lengths in dynamic scenarios, but random selection, greedy method and genetic algorithm experience significant performance losses as dynamicity increases.
RDL Kalıcı Kaydıİncele - ArticleAçık Erişim2025Transportation Mode Selection Using Reinforcement Learning in Simulation of Urban Mobility
Taş, Mehmet Bilge Han; Özkan, Kemal; Sarıçiçek, İnci; Yazici, Ahmet
Transportation mode selection is pivotal for navigating through cities plagued by heavy traffic congestion. This plays a crucial role in ensuring the efficient utilization of time and resources to achieve the desired objectives. Given the complex dynamics of urban mobility, strategically selecting a transportation mode can significantly mitigate delays and enhance overall productivity in densely populated areas. The objective of this study is to find the most efficient result among various transportation modes to make deliveries from different points on a university campus. To solve this problem, reinforcement learning was used and tested on the simulation environment SUMO. Traffic density was increased by using an equal number of different transportation modes, such as driving, cycling, motorbiking, and walking. Various traffic densities were generated, and different reward models were applied to select the best means of transportation. Various probability distributions were used as reward models to avoid the unfair distribution caused by how near or how far the road is when moving from random points to the destination region. As a result of the models created using the applied reward–penalty functions, it was determined that the best means of transportation in areas with a low traffic density is cycling, and in areas with high traffic density, the optimal mode of transportation is motorbiking.
RDL Kalıcı Kaydıİncele - Conference ObjectYalnız künye2024Traffic Light Control with Policy Gradient-Based Reinforcement Learning
Tas, Mehmet Bilge Han; Özkan, Kemal; Sariçiçek, Inci; Yazici, Ahmet
With the increase in population and transportation vehicles, increasing transportation times due to traffic density and carbon dioxide emitted by vehicles is one of the most important problems today. In this study, it is aimed to reduce these times and reduce traffic density by controlling traffic lights within the scope of smart cities. By using Policy Gradient-based reinforcement learning, a realistic city traffic sample is created with various vehicle elements such as cars, motorcycles and bicycles, and traffic lights are controlled to provide a smoother traffic with lower transportation times. Thanks to the application, a one-third improvement was achieved in the 180-hour period presented as an example.
RDL Kalıcı Kaydıİncele - Conference ObjectYalnız künye2024Routing with Pickup and Delivery via Deep Reinforcement Learning; [Derin Pekiştirmeli Öğrenme ile Al-Bırak Rotalama]
Aslan Yildiz, Özge; Sariçi̇Çek, İnci; Özkan, Kemal; Yazici, Ahmet
Intelligent transportation systems are an important issue within the scope of smart cities. Vehicle routing problems, which are a combinatorial problem, need to be solved in the design of the relevant systems. In this regard, the use of artificial intelligence optimization algorithms such as meta-heuristics has increased significantly in recent years. To the best of our knowledge, there are no papers that address the Dial and Ride problem by using reinforcement learning, one of the learning-based models. In this study, the Dial and Ride problem is solved for a single service vehicle using the transformer-based deep reinforcement learning method. The proposed method is tested on a problem generated in an environment in Eskişehir Büyükdere Neighborhood. As a result of the test problem, it is shown that the proposed method produced a solution to the problem in a reasonable time. The study showed that the Dial and Ride Problems can be solved with reinforcement learning.
RDL Kalıcı Kaydıİncele