State-aware-based power communication backbone network fault recovery method and device
A fault recovery and power communication technology, applied to electrical components, transmission systems, etc., can solve the problems of inability to achieve fast isolation and high cost of fault recovery, and achieve the effects of reducing human intervention, fast isolation, and good performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0063] A power communication backbone network fault recovery method based on artificial intelligence and state awareness, comprising steps:
[0064] Step 1. Obtain the number of nodes in the power communication backbone network at the current moment t that the actual unsaturated nodes are turned into saturated nodes;
[0065] The occupancy degree of node cache is a direct indicator reflecting the state of network communication. However, for the power communication backbone network, a single node status is not enough to reflect the congestion information of all surrounding nodes. If only a certain link is blocked, reasonable forwarding modification can effectively relieve the blocking. Nodes in the network can be divided into saturated nodes and unsaturated nodes according to their cache occupancy status. While judging its own state, the node can also judge the corresponding blocking state according to the return information of other nodes within the communication range. Ide...
Embodiment 2
[0096] A power communication backbone network fault recovery device based on artificial intelligence and state perception, comprising:
[0097] The actual flipped node acquisition module is used to obtain the number of nodes that are flipped from actual unsaturated nodes to saturated nodes in the power communication backbone network at the current moment;
[0098] The node flip prediction module at the next moment is used to correct and predict the number of nodes that are actually unsaturated nodes flipped to saturated nodes by weighting parameters to obtain the number of nodes that are flipped from unsaturated nodes to saturated nodes at the next moment;
[0099] The failure recovery module takes the number of unsaturated nodes turned into saturated nodes at the next moment as the input of the reinforcement learning algorithm. When a link e fails, the reinforcement learning algorithm proposes a new network topology as a recovery strategy, and establishes A new and more effec...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


