Improving the Performance of OLSR in Wireless Networks using Reinforcement Learning Algorithms

The Optimized Link State Routing Protocol is a popular proactive routing protocol used in wireless mesh networks. However, like many protocols, OLSR can suffer from inefficiencies and suboptimal performance certain network conditions. To address these issues, researchers have proposed using reinforcement learning algorithms to improve the decisions made by OLSR. This paper explores use of three RL - Q-Learning, SARSA, DQN Each algorithm described detail, their application explained. In particular, represented as Markov decision process, where each node state, link between nodes an action. reward for taking action determined quality link, goal maximize cumulative over sequence actions. Q-Learning simple effective that estimates value possible given state. SARSA similar takes into account current policy when estimating uses neural approximate Q-values providing more accurate complex environments. Overall, all be provides comprehensive overview highlights potential benefits