Energy Demand Forecasting
[TODO -- redo intro] Since variable generation and electricity demand both fluctuate, they must be forecast ahead of time to inform real-time electricity scheduling and longer-term system planning. Better short-term forecasts can allow system operators to reduce their reliance on polluting standby plants and to proactively manage increasing amounts of variable sources. Better long-term forecasts can help system operators (and investors) determine where and when power plants should be built. While many system operators today use basic forecasting techniques, forecasts will need to become increasingly accurate, span multiple horizons in time and space, and better quantify uncertainty to support these use cases. Machine learning has commonly been used on all these fronts.
Background Readings
Electricity demand forecasting
- "Electrical load forecasting models: A critical systematic review" (2017)[1]: A review and taxonomy of electricity load forecasting models.
- "Probabilistic electric load forecasting: A tutorial review" (2016)[2]: A tutorial and review of methods of probabilistic electricity load forecasting.
Community
Journals
- International Journal of Forecasting: The official journal of the International Institute of Forecasters. Journal website here.
Libraries and Tools
Data
General
- See the Electricity Systems page for general electricity systems datasets.
Future Directions
- Decision-integration: As supply and demand forecasts ultimately need to inform power system optimization decisions, a fruitful direction may be to integrate knowledge of how these decisions are made into ML models. For instance, deep neural networks have been used to forecast electricity demand in a way that optimizes for electricity scheduling costs rather than forecast accuracy,[3] and this notion could be extended to optimizing for greenhouse gas emissions.
- Interpretable/explainable ML and uncertainty quantification: Techniques that explain or quantify the uncertainty of forecasts could help power system operators better integrate these forecasts into their operations, and facilitate applications such as robust optimization.
- ↑ Kuster, Corentin; Rezgui, Yacine; Mourshed, Monjur (2017-11). "Electrical load forecasting models: A critical systematic review". Sustainable Cities and Society. 35: 257–270. doi:10.1016/j.scs.2017.08.009. ISSN 2210-6707. Check date values in:
|date=(help) - ↑ Hong, Tao; Fan, Shu (2016-07). "Probabilistic electric load forecasting: A tutorial review". International Journal of Forecasting. 32 (3): 914–938. doi:10.1016/j.ijforecast.2015.11.011. ISSN 0169-2070. Check date values in:
|date=(help) - ↑ Donti, Priya, Brandon Amos, and J. Zico Kolter. "Task-based end-to-end model learning in stochastic optimization." In Advances in Neural Information Processing Systems, pp. 5484-5494. 2017.