An Embedded Agent-Based Intelligent Industrial Wireless Sensor Network

Advances in cyber-physical systems and the introduction of Industry 4.0 have opened the door for interconnectivity in the industrial automation paradigm. One of the emerging technologies proven to be useful in factory automation is wireless sensor networks. In dynamic situations, wireless sensor networks need to be able to self-reconfigure while maintaining data integrity and efficiency. One solution popular with researchers is the use of multi-agent systems to manage wireless sensor networks. Typically, software agents are located on a server or cloud environment. Recent advances in microcomputers have made it feasible to embed these agents on the devices they control. This requires new reconfiguration and network management protocols. In this paper, an embedded agent architecture for wireless sensor network is proposed and an application specific example is given for an oil and gas refinery. An experiment is also conducted to investigate the effect of cluster sizes and signal frequency on the ratio of lost signals in a wireless sensor network cluster.