Deep Q-Learning Based Optimal Query Routing Approach for Unstructured P2P Network

Deep Reinforcement Learning(DRL)is a class of Machine Learning(ML)that combines Deep Learning with Reinforcement Learning and provides a framework by which a system can learn from its previous actions in an environment to select its efforts in the future efficiently.DRL has been used in many application fields,including games,robots,networks,etc.for creating autonomous systems that improve themselves with experience.It is well acknowledged that DRL is well suited to solve optimization problems in distributed systems in general and network routing especially.Therefore,a novel query routing approach called Deep Reinforcement Learning based Route Selection(DRLRS)is proposed for unstructured P2P networks based on a Deep Q-Learning algorithm.The main objective of this approach is to achieve better retrieval effectiveness with reduced searching cost by less number of connected peers,exchangedmessages,and reduced time.The simulation results shows a significantly improve searching a resource with compression to k-Random Walker and Directed BFS.Here,retrieval effectiveness,search cost in terms of connected peers,and average overhead are 1.28,106,149,respectively.

Query routing mismatch alleviation architecture for P2P file lookup in MANETs

A cross-layer optimized query routing mismatch alleviation （QRMA） architecture is proposed to mitigate the problem of query routing mismatch （QRM） phenomenon between the structured peer to peer （P2P） overlay and the routing layer in mobile Ad-hoc networks （MANETs）, which is an important issue that results in the inefficiency of lookup process in the system. Explicated with the representative Chord protocol, the proposal exploits the information of topologic neighbors in the routing layer of MANETs to find if there is any optimized alternative next hop in P2P overlay during conventional lookup progress. Once an alternative next hop is detected, it will take the shortcut to accelerate the query procedure and therefore alleviate the QRM problem in scalable MANETs without any assistance of affiliation equipments such as GPS device. The probability of finding out such an alternative node is formulated and the factors that could increase the chance are discussed. The simulation results show that the proposed architecture can effectively alleviate the QRM problem and significantly improve the system performance compared with the conventional mechanism.