Research on Edge Intelligence-based Security Analysis Method for Power Operation System

The development and rise of edge computing

As early as the 1990s, [8] proposed the design principle of “local simple, remote complex” agent control system, that is, the local controller should adopt simple algorithms as much as possible. However, these simple algorithms are isomorphic in function and structure through the network and remote complex algorithms to use remote complex computing and storage capabilities to learn and improve performance, and then improve and modify the simple local algorithms through the network, in order to achieve low-cost, high-performance, high-intelligence intelligent control. In the follow-up work [9], [10], this principle has been further improved in structure and algorithm. From the perspective of today’s edge computing technology, this architecture is an advanced and effective ideological method and technical architecture to achieve dis­tributed control edge intelligence under the conditions of communication computing at the time. The current rise of the Internet of Things, computing technology, artificial in­telligence technology, mainly distributed artificial intelligence technology, has given edge computing new capabilities and connotations [11].
The Internet of Things (IoT) realizes the ubiquitous connec­tion between things and people, between people and things through various information sensors, intelligent recognition, pattern perception and other devices and technologies. Intel­ligent perception, recognition and management of objects or
processes in the system [12], [13]. Compared with the tradi­tional Internet framework, there are a large number of terminal devices in the IoE, Cloud computing models cannot effectively transmit, calculate, and store massive data generated by smart terminals in real-time. Therefore, some of the original cloud services can be distributed to the edge of the network for processing, to meet the real-time requirements of various tasks while ensuring the overall performance of the system [14].
Edge computing, a new computing model, proposed under the rapid development of the Internet of Things, artificial intelligence, big data and cloud computing, can deploy a smart platform with computing, storage, application and other capabilities on the network side close to the data source [15], [16]. Also, it can provide intelligent services in the edge sense, to get faster network service response, and meet the basic needs of the industry in real-time business, application intelligence, security and privacy protection, etc [17], [18]. The development of edge computing in the industry has also received much attention, and its potential has been widely recognized worldwide. [19] described the reference frame of edge computing and proposes the sinking of computing resources and task allocation under this framework. Edge computing plays an essential role in the application of in­telligent networked devices and can significantly promote the deployment of artificial intelligence solutions [20]. With the development of 5G communication technology and distributed artificial intelligence technology, the use of edge computing technology in conjunction with 5G network and artificial intelligence to realize the edge of intelligent Internet of Things applications has gradually emerged [21], [22].

2.