Optimizing Block Propagation in Bitcoin Network with Region-based Neighbor Selection Using Reinforcement Learning

Bitcoin proved the potential of blockchain technology through decentralized, transparent, and immutable transactions. However, there are still challenges for fast and stable transitions. Optimizing block propagation times within the network is one of them. Prolonged propagation times can restrict efficiency, scalability, and security. This paper presents a novel approach to reducing block propagation time through leveraging reinforce-ment learning (RL) for the node’s neighbor selection strategies. We implemented a Deep Q-Network (DQN) model in minimizing block receive times at each node, thereby impacting overall block propagation time. We used a model that defines node states based on latencies of outbound connections, which present the node’s region. By evaluating this model through simulations using SimBlock, a robust Bitcoin network simulator, we observed a significant reduction in block propagation time—approximately 30% for smaller networks and 20% for larger ones. Our analysis extended to node connections generated by our model and comparative evaluation against existing methodologies.