Short-term Load Forecasting with Distributed Long Short-Term Memory
This work solves the problem of accurate load forecasting for electricity retailers in a privacy-preserving manner, though it is incremental as it adapts existing distributed and consensus techniques to this domain.
The paper tackles short-term load forecasting for electricity retailers by addressing data privacy and heterogeneity challenges with a distributed LSTM framework, achieving comparable accuracy to centralized methods while improving training speed and privacy protection.
With the employment of smart meters, massive data on consumer behaviour can be collected by retailers. From the collected data, the retailers may obtain the household profile information and implement demand response. While retailers prefer to acquire a model as accurate as possible among different customers, there are two major challenges. First, different retailers in the retail market do not share their consumer's electricity consumption data as these data are regarded as their assets, which has led to the problem of data island. Second, the electricity load data are highly heterogeneous since different retailers may serve various consumers. To this end, a fully distributed short-term load forecasting framework based on a consensus algorithm and Long Short-Term Memory (LSTM) is proposed, which may protect the customer's privacy and satisfy the accurate load forecasting requirement. Specifically, a fully distributed learning framework is exploited for distributed training, and a consensus technique is applied to meet confidential privacy. Case studies show that the proposed method has comparable performance with centralised methods regarding the accuracy, but the proposed method shows advantages in training speed and data privacy.