Temporal Data Pooling With Meta-Initialization for Individual Short-Term Load Forecasting

The growth of advanced metering infrastructure (AMI) deployment has enabled intelligent power control and management at the customer level; Highly accurate individual short-term load forecasting is crucial for this precise control per customer. Recently, deep learning has been widely adopted to improve forecasting accuracy. However, training an individual deep network (local training) has overfitting issues due to data paucity per customer. Thus, a pooling scheme has been introduced to augment a training dataset by batching several customers’ data. Nevertheless, there is room for existing pooling approaches to further improve accuracy by considering distribution heterogeneity within a customer dataset. In addition, their static pool assignment only with a customer’s training dataset may cause accuracy degradation under concept drift in serving time. To overcome these, we propose a Temporal Data Pooling (TDP) that constructs data pools at the data sample level with a novel distribution inference method and theoretical analysis. It allows the most probable forecasting model to serve predictions while resolving data shortage issues in local training. The TDP outperforms the other six competing methods for point and probabilistic forecasting; it shows robust accuracy under concept drift. Moreover, it demonstrates superior accuracy for unseen customers without additional training, proving its scalability.