In recent years, with the advent of the era of large data and the leap of computer performance, the AI technology and its applications have developed qualitatively. The application of machine learning algorithms, represented by deep learning, has achieved great success in the fields of image recognition and speech recognition, which provides great opportunities and strong support for the development of smart grid. At present, the application of the third generation of AI technology, represented by deep learning, is advancing deeply in the power industry. The integration of artificial intelligence technology and power grid technology will accelerate the intelligent development process of the power grid.

Based on the traditional physical grid, the smart grid has improved the communication technology, control technology, equipment technology, measurement technology and decision-making ability of the power system by the aid of artificial intelligence technology, and makes the traditional power system form a "self healing power grid", which improves the reliability and security of the power grid. And high efficiency, so as to realize the intellectualization, automation and digitalization of the power grid.

At present, the national development and Reform Commission, the national energy administration and the Ministry of industry and information have integrated artificial intelligence into the development plan and strategy, emphasizing the integration and application of artificial intelligence and various industries. The "power development" 13th Five-Year "plan" clearly points out that the "Internet +" smart grid construction will be promoted.

In 2017, China Southern Power Grid Guangdong company signed a strategic cooperation agreement with Baidu, and actively introduced the AI capabilities of Baidu face recognition, image recognition, natural language understanding, large data and so on, and carried out deep research in the fields of customer service, information construction, energy service, production and operation, electric power scheduling, technology research and other fields in the power system. Enter cooperation. The cooperation between China Southern Power Grid and Baidu is a cross-border cooperation between the power industry and artificial intelligence technology. It is another milestone in the development of smart grid in China.

As the core part of the future smart grid, AI has a wide range of applications in the field of electric power: such as the output of clean energy (wind, tide, solar and so on), fault detection and positioning, power grid monitoring and management, power station patrol and management, power station patrol, forecast electricity price, real-time pricing, user electricity behavior, energy storage mode transformation, users Side response, electric vehicle charging and discharging, etc.

At present, it is playing an increasingly important role to use the real time data collection, transmission and storage of the panorama of the power grid, and the large data application based on the rapid analysis and processing of the mass and multi source data is playing a more and more important role. The application of AI in the smart grid monitoring system has not only monitored the circumstances surrounding the power equipment or the substation, but also penetrated into the power equipment to monitor, analyze and upload effective data to the operation of the power equipment in real time.

In addition, the intelligent control of the lighting and environment around the substation or the power equipment, the control of the entrance guard and the fire control system are the responsibilities of the smart grid monitoring system. When unexpected events are encountered, the smart grid monitoring system can send early warning signals and record the process of emergencies. This series of timely, efficient and complete monitoring is difficult to reach in the traditional monitoring system.

The smart grid management system is an important part of the construction and operation of the smart grid. Intelligent and reliable smart grid management system will provide an important guarantee for the continuous supply of urban industrial electricity and living electricity. Smart grid auxiliary decision-making system is mainly applied to the two major scenarios of smart grid failure self healing and unmanned substation.

The system relies on artificial intelligence technology and has the ability of "self diagnosis". It can analyze the operation situation in the power system and rationally use all kinds of parts in the power facilities. When a part of the fault is encountered, the system can separate the fault components from the preset program without manual intervention or less manual intervention, so that the power system can be returned to the normal operation state.

With the development of the smart grid to the energy Internet and the wide area interconnection of the high voltage and large power grid, the fusion of AI and the power grid application technology will effectively improve the ability to control the complex power grid and improve the security, efficiency and stability of the power grid operation. Smart grid is a continuous construction, development, and perfect process, and AI as a series of methods of the collection, AI and smart grid integration and development from a long way to go.