Multi-Horizon Short-Term Residential Load Forecasting Using Decomposition-Based Linear Neural Network

View Full Paper

Ask AI

Bookmark

DLinear achieves the lowest MSE of 41.58 and MAE of 5.11 at a 24-hour prediction length, confirming its accuracy.
The DLinear model effectively decomposes time series data into trend and seasonal components, enhancing predictions.
This analysis utilized a linear neural network architecture for multi-horizon forecasting of electricity demand.
Results indicate DLinear's robustness in capturing dynamic patterns of residential electricity consumption.

Discussion

No takes yet. Share an insight, caveat, or question.

Forecasting framework predicts electricity demand in residential settings, highlighting improved accuracy in multi-horizon forecasting.

Tantyoko et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark