Q-learning optical network-on-chip adaptive routing planning method based on Dijkstra algorithm

Abstract

The invention relates to a Q-learning optical network-on-chip adaptive routing planning method based on a Dijkstra algorithm, and the method comprises the steps: S1, constructing a network model, anddefining the parameters of the network model; S2, constructing a shortest path tree from each node to other nodes according to a Dijkstra algorithm and a network model, storing a plurality of shortestpaths from the node to a target node vd in each node according to a preset value, and obtaining a routing hop count h (vs, vd) of the shortest path from a source node vs to the target node vd; S3, according to a Q-learning algorithm, performing path planning by adopting a link selection mechanism based on an epsilon-greedy strategy to obtain a plurality of planned paths from the source node vs tothe target node vd, and obtaining reward values of the planned paths, the routing hop count of the planned paths not exceeding the routing hop count h (vs, vd) of the shortest path; and S4, obtainingan optimal path according to the reward value of the planned path. According to the method, the defect that each target point of the Dijkstra algorithm can only generate one shortest path is overcome.

Description

technical field [0001] The invention belongs to the technical field of dynamic routing planning, and in particular relates to a Q-learning optical chip network self-adaptive routing planning method based on Dijkstra algorithm. Background technique [0002] With the exponential growth of data traffic and the rapid development of smart devices, networks are becoming more and more complex and diverse, and more factors need to be considered, including stability, security, bandwidth, delay, load, etc. Now that the multi-processor capability of the chip is constantly increasing, the efficiency of on-chip communication is critical to the overall performance. During the entire information transmission process, the intermediate router needs to select the next-hop router according to the current state. However, in the overall and long-term perspective, the lack of global information makes the selected next-hop forwarding node often not necessarily the best, so people pay more attenti...

AI Technical Summary

Problems solved by technology

Dijkstra's algorithm is a well-known algorithm for finding the shortest path. It can quickly give the shortest path, but it can only provide one shortest path for each target point, and cannot provide other alternative shortest paths, and it is only applicable to non-negative weight planning

Compared with the Dijkstra algorithm, the Bellman-Ford algorithm supports the presence of negative weights, and the code implementation is relatively simple, but the Bellman-Ford algorithm has a high time complexity, the convergence speed is lower than the Dijkstra algorithm, and the Bellman-Ford algorithm requires a lot of information Passing, especially when negative weights are encountered, requires multiple iterations

Images