Abstract: The Gamer’s Non-public Community (GPN) is a shopper/server expertise created by WTFast for making the network performance of on-line games sooner and extra dependable. GPN s use center-mile servers and proprietary algorithms to better join on-line video-recreation players to their recreation’s servers throughout a wide-area community. Top-minecraft-servers Online games are a large entertainment market and network latency is a key aspect of a player’s aggressive edge. This market means many different approaches to network structure are carried out by completely different competing companies and that those architectures are continually evolving. Guaranteeing the optimal connection between a client of WTFast and the web recreation they want to play is thus an incredibly troublesome drawback to automate. Using machine studying, we analyzed historical network knowledge from GPN connections to discover the feasibility of network latency prediction which is a key part of optimization. Our next step shall be to gather reside knowledge (together with shopper/server load, packet and port info and particular game state data) from GPN Minecraft servers and bots. We are going to use this information in a Reinforcement Learning model together with predictions about latency to change the clients’ and servers’ configurations for optimal community performance. These investigations and experiments will improve the quality of service and reliability of GPN techniques.