| CPC G06F 21/556 (2013.01) [G06F 18/2414 (2023.01); G06N 7/023 (2013.01); G06N 20/20 (2019.01)] | 5 Claims |

|
1. A leakage measurement error compensation method based on cloud-edge collaborative computing, implemented on a communication network formed by interconnection between a leakage current edge monitoring terminal and a power consumption management cloud platform, and comprising the following steps:
monitoring, by the leakage current edge monitoring terminal, load voltage, load current and leakage current data, and sending the data to the power consumption management cloud platform;
iteratively training, by the power consumption management cloud platform, a pseudo-leakage compensation model by using the received data, updating pseudo-leakage model parameters, and feeding the pseudo-leakage model parameters back to the leakage current edge monitoring terminal; and
processing, by the leakage current edge monitoring terminal, the leakage current data according to the pseudo-leakage compensation model parameters received from the power consumption management cloud platform and by using the same pseudo-leakage compensation model as the power consumption management cloud platform, so as to eliminate the influence of a pseudo-leakage phenomenon in the leakage current data in real time;
wherein the pseudo-leakage compensation model is constructed by a Multiple Instance Regression (MIR) algorithm based on Robust Fuzzy Clustering (RFC), and center points and covariances of fuzzy members are gradually optimized in a training process until probabilistic members complete the convergence;
wherein an optimization formula of the fuzzy members is:
![]() wherein
![]() C represents a number of clusters; m>1, and represents a fuzzy weight parameter; xj represents a sample; ci represents a center of a cluster i; eik represents a kth characteristic vector of a covariance matrix
![]() of the cluster i; and vik represents a weight coefficient of a characteristic root in the kth characteristic vector.
|