Optimal control of mobile monitoring agents in immune-inspired wireless monitoring networks

This paper studies optimal control of mobile monitoring agents in artificial-immune-system-based (AIS-based) monitoring networks. In AIS-based structural health monitoring (SHM) networks, the active structural health monitoring is performed by a group of mobile monitoring agents equipped with damage pattern recognition algorithms. The mobile monitoring agents mimic immune cells in the natural immune system and patrol a structure to detect damage patterns using their receptors (feature vectors), damage pattern recognition algorithms, and the dynamic response data of the structure. The optimal control of mobile monitoring agents includes agent generation and distribution. The generation of mobile monitoring agents is optimized to minimize the response time for the mobile monitoring agents to diagnose structural damage in a sub-network and maximize the average affinity of monitoring agents′ receptors to the damaged sensor data feature vector. The objective functions for distributing mobile monitoring agents are to increase the detection probability and extend network life by balancing energy consumption of sensor nodes in the network. The presented optimization algorithms are developed using multi-objective genetic algorithms. The impact of the algorithm parameters on the performance of the algorithm is also investigated.