A Multi-agent Based Flexible IoT Edge Computing Architecture and Application to ITS

—On a large-scale IoT system based on cloud computing, problems such as increase of network load, delay in response, invasion of privacy, are concerned in recent years. As a solution to this problem, edge computing has introduced to the IoT systems. However, if you migrate the cloud function to the edge too much, the collected data cannot be shared between IoT systems and this decreases the usefulness of the IoT system. In this paper, a multi-agent based flexible IoT edge computing architecture is proposed to balance global optimization by a cloud and local optimization by edges and to optimize the role of the cloud server and the edge servers dynamically. Also, as its application example, a parking search system example based on the proposed edge computing system architecture is shown to show the effectiveness.