Edge Intelligent Perception Agents for Smart City Field Application

Artificial intelligence has been increasingly applied to smart city development and field practice. As a result, the problem about the exponential growth of city data and the cost of computing power has become increasingly prominent. Edge computing and multi-agent collaboration tend to be an emerging technology paradigm that enables the balance of the above contradiction. Based on the edge computing and multi-agent theory, we put forward the concept of EIPA (Edge Intelligent Perception Agent) and its system architecture. The hardware design methodologies of mobile EIPA and stationary EIPA were expounded in detail, and then the algorithm model of intelligent monitoring in the urban park was introduced. The whole system is being tested and verified in the urban industry park and residential quarter. The utility results of EIPA for pollutant diffusion center location are discussed, which confirmed the system's effectiveness. The limitations of current work and recommendations for future work are proposed at last.