Delta-Based Target Reformulation for Short-Term Electricity Load Forecasting Using LSTM and Transformer Models
arXiv:2606.17692v1 Announce Type: new Abstract: Accurate short-term electricity load forecasting is critical for the reliable and economic operation of modern power systems, under non-stationarity arising from weather variability, calendar effects, and evolving consumption patterns. While deep learning models such as LSTMs and Transformers show promising performance, most existing studies focus on direct absolute load prediction without explicitly addressing target non-stationarity. Motivated by classical time-series differencing techniques in ARIMA models, this paper investigates a delta-base
The increasing complexity and non-stationarity of modern power grids, driven by renewable energy integration and evolving consumption patterns, necessitate more sophisticated forecasting tools.
Accurate electricity load forecasting is crucial for grid stability, cost optimization, and preventing outages, directly impacting economic activity and public safety.
This research introduces a refined deep learning approach that could lead to more robust and accurate short-term electricity load predictions, improving grid management capabilities.
- · Grid operators
- · Energy producers
- · Deep learning researchers
- · AI model developers
- · Traditional forecasting methods
- · Inefficient power utilities
Improved grid stability and reduced operational costs for electricity providers.
More efficient integration of intermittent renewable energy sources into the grid.
Reduced likelihood of blackouts and brownouts, supporting the reliable operation of compute-intensive industries and AI infrastructure.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG