The Implementation Path of the Auxiliary Technology of Data Fabric for Power Equipment Under the Background of the New Power System

Against the backdrop of the construction of a new power system to achieve the “dual carbon” goals, power equipment management is confronted with new challenges, and the traditional management mode is difficult to meet its requirements for reliability, safety, and high efficiency. This study focuses on the auxiliary technology of data fabric for power equipment, deeply analyzes the core requirements of the new power system, and clarifies its requirements for data services in terms of flexibility, reliability, and low carbonization. It elaborately discusses the application of the auxiliary technology of data fabric in typical scenarios such as equipment condition monitoring, fault diagnosis, load forecasting, and operation and maintenance decision-making. By modeling the data service problems of power equipment as a Markov decision process, a deep reinforcement learning model is designed using the Actor-Critic framework, and optimized with multi-objective constraint optimization and transfer learning initialization strategies. Simulation verification shows that, based on data fabric, this model can accurately monitor the equipment condition and explore the potential relationships within the data, providing strong support for related services, effectively improving the operation performance of the power system, and promoting the intelligent development of the data services of power equipment.