Reducing Network Traffic in Blockchain Transactions using Reinforcement Learning

In this paper, we identify the network traffic in blockchains using reinforcement learning (RL). The RL mechanism identifies the action to be provided at each states i.e., either rewarding or penalising. In other words, the network traffic is mitigated based on the reward or penalising function such that the network traffic is eliminated. The simulation is conducted to test whether the model is efficient in reducing the traffic than other methods. The results show a better rate of accuracy in eliminating the traffic than other methods.