The cloud system structure is limited by sensor data processing to handle real-time constancy and mobility. To solve such a problem, this paper proposes a system structure based on edge cloud computing and human perception of data in the ring and explores its application in big data analysis. Specifically, a three-layer data flow computing structure composed of a wireless network, edge cloud system, and central cloud system is constructed. In terms of data flow structure, a mobile service structure supporting real-time operation and mobility is proposed. Based on such a structure, an edge cloud data awareness structure is further proposed. Moreover, a flexible storage structure that can be used to support different types of applications is designed to optimize the sensor system and improve the reliability of data storage. The experimental results show that the system structure based on edge cloud terms reduces the server failure rate and total utilization due to the capacity of VMs. Besides, its performance is much better than the existing structure in terms of maintenance and data processing time. Finally, the result of the edge of the cloud computing solution can save 19% on time than the original scheme.

Edge computing gateway automation system is integrated in edge computing gateway. One of the main functions of edge computing system is to connect industrial instruments and communication equipment in the process of industrial production. It provides real-time data monitoring and analysis, and initiates responses to predetermined logical events. The operation process includes separating and designing different processes in a certain order. The production and processing process is susceptible to problems such as long production and processing cycles, multiple types of monitoring data, large amounts of processing data, and data vulnerability to external interference, which leads to inaccurate and unsynchronized data. Based on this, this article investigated the analysis of data processing systems based on cloud computing, focusing on analyzing the system architecture and processing, and elaborating the design of data collectors. Then, this article analyzed the efficiency of AI (artificial intelligence) automatic control system and data processing unit. This article discussed the application of AI in collecting and processing data, the composition of the data management module of AI automatic control system, and the data processing in the data module of AI automatic control system. This paper also described the construction method and process of the automatic control system of edge computing gateway, and discussed from the following aspects: data preprocessing module, data classification processing module, data accumulation analysis module, automatic control algorithm logic module, and instruction execution control module. Experiments and investigations showed that the accuracy of data analysis by using the new AI automatic control system and data processing system was 0.11 higher than that of traditional automatic control systems and data processing systems. The data processing effectiveness of the new AI automatic control system and data processing system was 0.10 higher than that of the traditional automatic control system and data processing system. By using AI technology and edge computing technology to structure the automatic control system and data processing system, a new AI automatic control system and data processing system were constructed, which were 9 % more satisfied than the traditional automatic control system and data processing system.

In this study, we are concerned with the optimization of fuzzy clustering (Fuzzy C-Means) on the basis of a collection of distributed datasets without violating data confidentiality and security. The optimization of fuzzy clusters is realized using the differential evolution algorithm in a federated learning environment. Fuzzy clustering plays an important role in revealing the underlying structure of a given dataset. However, traditional iterative method is easy to get stuck at local optimum. With the growing concerning on data confidentiality and security, how to reveal the underlying structure of the data that are stored locally across different sites is becoming an urgent problem. In order to overcome these two obstacles, we propose a federated differential evolution algorithm to realize fuzzy clustering. We augment the well-known differential evolution algorithm such that it can work in a federated learning environment to ensure local data privacy. The design practice of the federated differential evolution is elaborated on by highlighting its effectiveness in finding the optimal fuzzy clusters on the basis of distributed datasets. The performance of the proposed method is compared with traditional fuzzy clustering algorithm. Experimental studies completed on a series of real-world datasets coming from machine learning repository are reported to demonstrate the superiority of the proposed algorithm.