Abstract: The disclosure discloses a method for detecting an intrusion in parallel based on an unbalanced data Deep Belief Network, which reads an unbalanced data set DS; under-samples the unbalanced data set using the improved NCR algorithm to reduce the ratio of the majority type samples and make the data distribution of the data set balanced; the improved differential evolution algorithm is used on the distributed memory computing platform Spark to optimize the parameters of the deep belief network model to obtain the optimal model parameters; extract the feature of data of the data set, and then classify the intrusion detection by the weighted nuclear extreme learning machine, and finally train multiple weighted nuclear extreme learning machines of different structures in parallel by multithreading as the base classifier, and establish a multi-classifier intrusion detection model based on adaptive weighted voting for detecting the intrusion in parallel.

Abstract: A lightning strike probability-based coordinated power control method for an energy storage system and a load adjusts output power of an energy storage system and a regulatable load based on a real-time predicted lightning strike probability. This reduces a correlation between a power grid in a lightning region and an external power grid, minimizes impact of a lightning strike if any on the external power grid, and decreases an economic loss due to the lightning strike in the lightning region. The present disclosure establishes a relationship between the output power of the energy storage system, the regulated power of the regulatable load, and a lightning strike probability in a same region, and then regulates the power of the energy storage system and the regulatable load in real time based on the lightning strike probability.

Abstract: A lightning prewarning-based method for active protection against a lightning strike on an important transmission channel includes collecting meteorological element data, and establishing a transmission line-specific lightning strike probability prewarning model; using a maximum probability of a lightning strike prewarning level as a lightning strike prewarning level; performing equivalence calculation on a large-scale regional power system, using a minimum sum of a power loss risk cost and a regulation cost as an optimized objective function, and establishing a power flow transfer optimization model; and comparing a sum of a regulation cost and load power loss risk cost caused after the tie line is disconnected if regulation is performed before a lightning strike, and a load power loss risk cost caused if regulation is not performed, and when the regulation cost is not greater than the load power loss risk cost, performing regulation before the lightning strike.