Dynamic Monitoring of Voltage Difference Fault in Energy Storage System Based on Adaptive Threshold Algorithm

For the problem that the fixed threshold setting method cannot realize dynamic monitoring of voltage difference fault, a data-driven method is adopted in this paper to establish an adaptive threshold algorithm for voltage difference of the energy storage system by combining the threshold setting for battery voltage difference of the energy storage system with the exponentially weighted moving-average (EWMA) method. Compared with other methods, the alarm threshold obtained by the algorithm can realize dynamic monitoring of the voltage difference in the whole charging and discharging process and improve the accuracy of early warning. The actual operation data of a power grid-side energy storage power station in China show that the false alarm rate and omissive alarm rate of the algorithm are lower than 1%, which can greatly alleviate the workload of operation and maintenance personnel while ensuring the safe and reliable operation of the system, with good application and promotion value.