Smart community electricity consumption real-time prediction method and device based on depth learning

Abstract

The invention relates to a smart community electricity consumption real-time prediction method and device based on depth learning. The method comprises the steps of (1) obtaining the historical electricity consumption data of a community to be predicted, (2) constructing an electricity consumption database comprising the historical electricity consumption data in step (1) in a distributed real-time processing frame Storm, (3) using the electricity consumption database in the step (2) to train a convolutional neural network, and obtaining a convolutional neural network model, and (4) inputting the electricity consumption data of a community to be predicted of a current certain time period and obtaining a result of predicted electricity consumption amount. The method and the device have the advantages that the optimal weight of a community electricity consumption database is extracted through an artificial neural network, the accuracy of detection is effectively improved, on the basis of the Storm, the parallel community electricity consumption prediction is implemented, and a purpose of real-time prediction is achieved.

Description

technical field

[0001] The invention relates to artificial intelligence technology, in particular to a method and device for real-time prediction of electricity consumption in a smart community based on deep learning. Background technique

[0002] Deep learning is currently the highest level of machine learning development. As a method of deep learning, artificial neural network has a high effect in the fields of object recognition and image processing. For time series forecasting, artificial neural networks have the advantage of being able to automatically learn time series features, reduce manual intervention, and extract high-quality features. Since deep learning methods may consume a large amount of GPU resources, excessive calculations may not reach the actual Real-time effects in application scenarios. In order to solve the problem of real-time processing of big data, the distributed real-time processing framework Storm came into being. Storm has many application field...

Images