Abstract: Existing traffic light controls are ineffective and causes a handful of problems such as congestion and pollution. The purpose of this study is to investigate the application of deep reinforcement learning on traffic control systems to minimize congestion at a targeted traffic intersection. The traffic data was extracted, analyzed and simulated based on the Poisson Distribution, using a simulator, Simulation of Urban Mobility (SUMO). In this research, we proposed a deep reinforcement learning model, which combines the capabilities of convolutional neural networks and reinforcement learning to control the traffic lights to increase the effectiveness of the traffic control system. The paper explains the method we used to quantify the traffic scenario into different matrices which fed to the model as states which reduces the load of computing as compared to images. After 2000 iterations of training, our deep reinforcement learning model was able to reduce the cumulative waiting time of al

• Publication Date: 08-Dec-2019
• DOI: 10.15224/978-1-63248-181-8-09
• Views: 0
• Downloads: 0

Abstract: ollision free dynamic slot scheduling in ad-hoc networks is NP complete problem. In most of the distributed networks, scheduling is performed by cluster heads or relay nodes. A sophisticated method is needed for nodes to perform dynamic schedule on their own and update the state of resources. Recently, neural network and few heuristic approaches are used to solve the problem. In this paper, we propose a heuristic based method on the idea of generating optimal solutions. The arithmetic crossover and cyclic permutation use random generated slot vectors of neighbors, broadcast during the scheduling period to create an initial population. The technique uses elitism to highlight one-hop and two-hop collisions and makes the information usable in finding valid solutions. The operations provide optimal scheduling solutions which are used in next generation. The method increases collision av

• Publication Date: 08-Dec-2019
• DOI: 10.15224/978-1-63248-181-8-10
• Views: 0
• Downloads: 0