Outputs from Control REACT Workstream 2 [Code]
Outputs from the Network Innovation Allowance project "Control REACT" (workstream 2), sponsored by National Grid Electricity System Operator (NGESO). This deposit comprises R code (in R markdown) and html renders of these workbooks produced by Control REACT that:
- implement benchmark and advanced methods for probabilistic wind, solar and electricity demand forecasting
- verify and evaluate the skill of these forecasts
A third output that demonstrate how these forecasts could be used in decision-making scenarios at NGESO may be added in a future realise but cannot be shared publicly at present.
Accompanying data is held in a separate repository linked below. In order to re-run the code, the data and code must be arranged in directories as given in "Directory Structure.pdf"
The methods implemented for regional and national wind, solar, and net-demand forecasting (day-ahead/daily update and 0-6h ahead 30 minute update) are implemented in R and annotated in detail in the Rmarkdown framework, which produces readable html renders of the descriptions and figures that can be read in a browser without the need to install or be familiar R. At the end of each document exact session information is provided listing R and package versions used.
Wind, solar and net-demand data are derived from raw data made available by Elexon and Solar Sheffield via public APIs. See respective websites for details, our processed (aggregated and cleaned) versions of this data are shared here under a CC-BY license. Weather forecast data are derived from historic operational forecasts from the ECMWF HRES model and are shared under a CC-BY licence. For details on how these were processed please see references.
Summary/background: The uncertainty that Control Room (CR) engineers must handle in their decision-making is growing rapidly due to increases in renewable and embedded generation. At the same time, the CR has seen a huge rise in the number of units involved in their balancing decisions (from 40 to over 1,000). It is inevitable then, that the costs of balancing the grid has also been rising and will continue to do so until an approach is adopted which allows CR engineers to effectively manage uncertainty. It is believed that if information about forecast uncertainty was presented in real-time to CR engineers, that this would provide opportunities for them to make more economic and secure balancing decisions.
Outcomes form Workstream 2:
- The production of skillful and statistically robust forecasts of BMU wind power generation and embedded solar power, using best-in-class data-driven forecasting algorithms.
- Skillful and statistically robust forecasts of demand and embedded solar.
- An example approach for using probabilistic forecasting to support rescheduling and redispatch.
- An example approach for using probabilistic forecasting to support day ahead reserves recommendations.
- An example approach for using probabilistic forecasting to support margins analysis.
Further infomation: https://smarter.energynetworks.org/projects/nia_ngso0032/
- J. Browell and M. Fasiolo, "Probabilistic Forecasting of regional net-load with conditional extremes and gridded NWP", IEEE Transactions on Smart Grid, vol. 12, no, 6, pp. 5011-5019, 2021