IP-optical network communication service joint distribution method and device

Abstract

The embodiment of the invention provides an IP-optical network communication service joint distribution method and device. The method comprises the following steps: obtaining service information; inputting the service information into a preset route distribution model, and analyzing the preset route distribution model by using a preset deep reinforcement learning model to obtain service route distribution information; wherein the preset route distribution model is obtained by performing normalization weighting on IP-optical network risk balance degree information, main and standby route similarity information and network time delay information. Routing distribution indexes are constructed by considering two aspects of communication network efficiency and risk balance of a intelligent powergrid; according to the method, the specific evaluation method of the service balance degree and the transmission time delay in the power communication network is analyzed, then weighted analysis calculation is performed on the service balance degree and the transmission time delay, a reasonable preset routing allocation model is finally designed, a preset deep reinforcement learning model is selected, and an optimal path is solved, so that efficient and reasonable operation of the IP-optical network is guaranteed.

Description

technical field [0001] The invention relates to the technical field of information processing, in particular to a method and device for jointly distributing IP-optical network communication services. Background technique [0002] With the development and popularization of smart grid, information construction, and energy Internet, various data communication network IP services are rapidly emerging, such as broadband video services, data centers, and cloud computing and other bandwidth services. This explosive increase in data and bandwidth requirements has brought great challenges to traditional power communication networks. The increasing complexity of the network and the increase in the number of nodes make it increasingly difficult to adapt to the traditional extensive network management and scheduling. [0003] In the traditional power communication network, a top-down network system design method is adopted. Both the IP network and the optical network have unique manage...

AI Technical Summary

Problems solved by technology

This relatively closed network layer design makes the overall network operation efficiency low, and the operation and maintenance, protection, and traffic coordination capabilities are insufficient. For IP services with strong randomness, large traffic, and various types, it is often impossible to allocate reasonable efficient routing

Images