China’s First AI Data Analysis Platform for New Energy Storage Officially Launched

Recently, China’s first domestically developed artificial intelligence data analysis platform dedicated to the new energy storage sector was officially put into operation. Led by China Southern Power Grid, the platform is capable of connecting various types of energy storage equipment. Leveraging AI autonomous learning and massive data analysis capabilities, it can remotely identify potential equipment defects in real time and automatically generate operation and maintenance solutions for rapid handling. The launch of this platform marks a critical step forward in the intelligent operation and maintenance of new energy storage in China.

It is understood that the platform adopts a “cloud-edge-device” collaborative architecture, where the cloud handles AI model training and algorithm iteration, while the edge side is responsible for real-time inference and analysis. The platform has currently been deployed across eight new energy storage power stations in Guangdong, Yunnan, Hainan, and other regions, with over 2.3 million data collection points. By monitoring the operational status of energy storage equipment around the clock, the platform performs real-time analysis on key parameters such as temperature, voltage, and current. Once an anomaly is detected, the system can automatically identify the root cause and generate a resolution plan, significantly improving the operational efficiency and safety of energy storage power stations while reducing the intensity and error rate of manual inspections.

According to Liu Xuan, a technical expert from the Maintenance and Test Branch of China Southern Power Grid Energy Storage, the platform is already capable of intelligent analysis for more than 100 large-scale energy storage power stations. It has also established high-quality datasets for lithium batteries, sodium batteries, and other technologies. These datasets cover operational data from energy storage devices of different technical routes under various working conditions, providing a solid foundation for the continuous optimization of AI models. In the next phase, the platform will integrate new types of energy storage demonstration stations, such as all-vanadium redox flow batteries, to further expand application scenarios and support the development of emerging pillar industries.

After one year of trial operation, the eight power stations achieved a 34% reduction in equipment failure rates, a 30% increase in new energy consumption, and a significant enhancement in system regulation capabilities. Specifically, the drop in failure rate means a substantial reduction in unplanned equipment downtime and an effective improvement in the availability of energy storage systems. The increase in renewable energy consumption benefits from the platform’s precise optimization of charging and discharging strategies, enabling energy storage systems to better accommodate the intermittency of wind and solar power generation and achieve more efficient energy allocation.

Industry insiders believe that as the installed capacity of new energy storage expands rapidly, traditional operation and maintenance models are no longer sufficient to meet the demands of large-scale, high‑safety management. The deployment of this platform provides a replicable technical path for the intelligent transformation of the energy storage industry and lays a solid foundation for future large‑scale application.