Empowering data-driven load forecasting by leveraging long short-term memory recurrent neural networks
Waqar Waheed, Qingshan Xu, Muhammad Aurangzeb, Sheeraz Iqbal, Saadat Hanif Dar, Z.M.S. Elbarbary · 2024
Read Empowering data-driven load forecasting by leveraging long short-term memory recurrent neural networks by Waqar Waheed, Qingshan Xu, Muhammad Aurangzeb, Sheeraz Iqbal, Saadat Hanif Dar, Z.M.S. Elbarbary (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11696747.txt.
Description
Waqar Waheed and co-authors forecast power demand with a memory-based neural network in a 2024 paper. Renewable energy makes power systems harder to run, and good load forecasts keep them stable. Weather and social factors bend demand in tangled ways that older statistical tools and plain machine learning often miss.
The team applies a long short-term memory recurrent network, a model built to read sequences and remember patterns over time. Their forecasts, both hourly and yearly, landed with very low error, and the hourly model beat the yearly one. The authors argue this accuracy supports demand response programs and smooth blending of scattered renewable sources into smart grids, where knowing tomorrow's load is half the battle.
Catalog record
| CREATOR | Waqar Waheed, Qingshan Xu, Muhammad Aurangzeb, Sheeraz Iqbal, Saadat Hanif Dar, Z.M.S. Elbarbary |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 58 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |