If an equipment failure occurs in the low-voltage distribution network of the area, the peripheral computers immediately start the self-healing function.
China’s state-owned power grid company on Tuesday launched the country’s most powerful artificial intelligence to support power distribution, Science and Technology Daily reports. After a major power outage, it usually takes six to ten hours to fix the problem and restore power, but artificial intelligence reduces that to three seconds. With a one-month test operation, they confirmed the effectiveness of the system in Qitailu, a residential community of more than 200 families, and in Urumqi in the Xinjiang region. Qitailu’s community power grid has more sensors than anywhere else in the country, and each sensor is controlled by its own “brain” that can decide on power routes without human intervention. If an equipment failure occurs in the area’s low-voltage distribution network, the edge computers “immediately initiate a self-healing function, including automatic fault location, fault isolation and power restoration,” the report said. “Now the outage is almost nothing. The power comes on as soon as it stops and does not affect life and work in any way,” the state newspaper quoted an unnamed resident as saying. According to local authorities, the application of artificial intelligence-controlled power grid technology would soon spread from Qitailu to other settlements. China produces a third of the world’s electricity, more than the United States, India, Russia and Japan combined. China’s electricity grid has been using artificial intelligence in its daily operations for years, especially after the massive construction of wind and solar power plants, which had unstable power generation. However, these applications have mostly been limited to backbone networks or preventing outages for industrial users, said a senior engineer who works at the State Grid Corporation of China’s Beijing headquarters.”In a residential community, the network connects to a large number of end users. The environment is quite complex. There are many kinds of problems. Most of the problems have to be localized and identified manually,” said the engineer, who asked not to be named because he was not authorized to speak to the media. . Power outages are rare in China, especially in cities. “And China’s power grid workers are probably the most efficient in the world. But if it does happen, it still takes hours to fix the problem,” he said. According to the engineer, artificial intelligence works differently than existing automated systems in the electrical grid. Conventional power grid management computers generate a large number of error codes when a power outage occurs. The human operator must make an assessment based on the information and develop a solution, such as a rerouting plan, based on their experience. The artificial intelligence uses natural language processing to “understand” the textual explanation behind each error code, the engineer said. It then learns from a large number of previous power outages to figure out hidden patterns that help you find and fix the problem. However, according to the engineer, to improve accuracy, artificial intelligence needs a huge amount of data collected by a wide variety of sensors. “In the past, these sensors and related data transmission technologies were only available for high-voltage transmission lines. Now they are making their way into urban areas,” he said, according to the South China Morning Post .Hardware, software, tests, interesting and colorful news from the world of IT by clicking here!