A Power Prediction Method for Edge Devices Based on Sparse Anomaly Perception

Abstract

The invention discloses a method for predicting power consumption of edge devices based on sparse anomaly perception, which includes the following steps: S1: the edge device collects power data for K target buildings; Perform sparse anomaly labeling; S3: Calculate the sparse anomaly discard probability and obtain the total training set; S4: Use the machine learning regression algorithm and 5-fold cross-validation to train the model, use the sparse anomaly discard probability to randomly discard abnormal data during each fold cross-validation, and do not participate Training; S5: Use the machine learning model to predict the power of the data to be predicted, and multiply the model prediction output by the probability of sparse exception discarding to obtain the final prediction. The invention alleviates the problem that the machine learning regression model based on mean square error loss is more sensitive to abnormal data; at the same time, it reduces the amount of training data, improves the speed of model training, introduces randomness, and improves the prediction accuracy and generality of the model. ability.

Description

technical field [0001] The present invention relates to power forecasting in the energy field, in particular to a power forecasting method under edge devices based on sparse anomaly perception. Background technique [0002] Energy issues are closely related to human development. With the development of the times and the advancement of science and technology, electric energy has become one of the indispensable energy sources in human social life, and is the most important part of the energy field in modern society. demand is increasing day by day. As the basis of power system operation, optimization and control, electricity consumption forecasting is facing new challenges in today's environment of rapid development of energy systems. [0003] In recent years, with the rapid development of machine learning technology and deep learning technology, a large number of machine learning technology and deep learning technology have been applied to power forecasting, and good result...

AI Technical Summary

Problems solved by technology

And its biggest shortcoming is that it is easily affected by outliers. In response to this shortcoming, domestic and foreign scholars have made many improvements, most of which are aimed at the loss function itself, directly using the Huber loss function, etc.

Images