Minimum cascade repair method for mobile network nodes failure under time–frequency feature fusion

Abstract

Aiming at the connectivity failure caused by the failure of mobile network nodes in complex application scenarios, a minimum cascade repair method for the failure of mobile network nodes under time–frequency feature fusion is proposed. The short-time energy and zero-crossing rate of time-domain features of mobile network nodes were extracted.The frequency domain features of network nodes are extracted by fully connected long and short time memory network. In the form of weighting and series, the time domain and frequency domain features are fused to obtain the time–frequency fusion features. The failure node is detected by using the adaptive mechanism of node clustering feature combined with time–frequency fusion feature. Judging whether the failed node is a cut point according to the rule; If the failed node is a cut point, the network needs to be repaired. Considering the impact of faulty nodes on network communication and connectivity in the real world, an innovative minimum cascade repair algorithm is introduced to establish communication links to repair the network topology without moving nodes, achieving optimization of repair rules. Calculate the energy consumption of the repair moving distance of the failed node, based on the optimized repair rules. If the energy consumption is less than or equal to the energy consumption of the communication radius of the neighboring node, the mobile network can be repaired statically by directly establishing a communication link between the neighboring nodes. Otherwise, the best candidate node is selected and its location to be moved is calculated to complete the mobile network mobile repair. Experimental results show that this method can effectively repair the network after node failure. This method reduces the energy loss of the repair node and improves the status indicator value of the mobile network.