LSTM networks using temporal autocorrelation in consumption achieve R² of 0.883 and 0.865 versus -0.055 and 0.410 for weather-driven MLPs at 5-minute resolution, showing temporal features dominate.
State of the Energy Market 2023,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Weather Correlation: A Comparative Study of Static and Temporal Neural Architectures for Fine-Grained Residential Energy Consumption Forecasting in Melbourne, Australia
LSTM networks using temporal autocorrelation in consumption achieve R² of 0.883 and 0.865 versus -0.055 and 0.410 for weather-driven MLPs at 5-minute resolution, showing temporal features dominate.