Projects
Projects: Custom Search |
||
| Reference Number | NIA2_NGESO058 | |
| Title | InterCast | |
| Status | Completed | |
| Energy Categories | Other Power and Storage Technologies (Electricity transmission and distribution) 10%; Other Cross-Cutting Technologies or Research (Energy Economics) 90%; |
|
| Research Types | Applied Research and Development 100% | |
| Science and Technology Fields | SOCIAL SCIENCES (Economics and Econometrics) 50%; ENGINEERING AND TECHNOLOGY (Electrical and Electronic Engineering) 50%; |
|
| UKERC Cross Cutting Characterisation | Not Cross-cutting 100% | |
| Principal Investigator |
Project Contact No email address given National Grid plc |
|
| Award Type | Network Innovation Allowance | |
| Funding Source | Ofgem | |
| Start Date | 01 October 2023 | |
| End Date | 31 December 2023 | |
| Duration | ENA months | |
| Total Grant Value | £50,000 | |
| Industrial Sectors | Power | |
| Region | London | |
| Programme | Network Innovation Allowance | |
| Investigators | Principal Investigator | Project Contact , National Grid plc (100.000%) |
| Industrial Collaborator | Project Contact , National Grid plc (0.000%) |
|
| Web Site | https://smarter.energynetworks.org/projects/NIA2_NGESO058 |
|
| Objectives | At present, future market price data for Norway and Great Britain is transformed to an hourly time series of future prices using a technique based on similar historical days. This project will focus on:1. Examine current methodologies and data including:How does the ESO currently predict price at an hourly level and where are the biggest challenges with the approach. How accurate are predicted prices? Determine what, if any, relationships exist between previous and future hourly prices.2. Assess alternative techniques with two possible options:Compare different similarity scoring techniques to isolate previous hourly price/forecasted price combinations that are most predictive of future hourly price spread. Examine using other methods such as time series forecasting with historical hourly price data and potentially other factors. In each case, examine whether such predictions can be improved by including other data such as weather or calendar data or national demand forecast. 3. Build out Proof of Concept (PoC):Create a PoC model to assign forecasted peak price to hourly intervals based on most promising strategy identified in previous phase. The PoC will be for one country in the first instance but with a stretch goal to examine other countries. Validate model performance compared to baseline models and currently used approaches. Assess model performance under different conditions (e.g., summer vs winter, peak vs trough demand).4. Ensure full handover of PoC and related documentation:Fully document all work in data processing and exploration as well as model training and validation. In line with the ENA"s ENIP document, the risk rating is scored Low. TRL Steps = 1 (2 TRL steps) Cost = 1 (£50k) Suppliers = 1 (1 supplier) Data Assumptions = 2 Total = 5 (Low) This project will focus on forecasting the North Sea Link interconnector (NSL), however the learnings and methods generated can be applied to models for the other interconnectors. NSL has been selected as the focus of this project as the ESO currently does not have a model to forecast the hourly Norwegian electricity prices. The project will focus on 3 main work packages and a final deliverable. An examination of current methodologies and dataAn assessment of alternative techniques comparing 2 scoring techniquesBuild a PoC modelDeliver a PoC and related documentation Improve understanding of the relationship between future market price data and in-day prices.Develop a PoC model in notebook form for predicting price at hourly level based on the future market price data.Develop a report on model validation, performance against current methodology and potential next steps, including applying the learning to the other interconnectors. | |
| Abstract | Currently, the ESO produce a forecast of hourly interconnector flow at a lead time of day ahead to 1 week ahead. This forecast is based on the expected difference between electricity prices of the two interconnected countries.To forecast the hourly electricity price in each country, the ESO have acquired future market price data for the peak and baseload periods from external data sources. This is transformed to hourly prices using a technique based on similar historical days. However, this method does not produce the level of accuracy required for a key input into the ESO interconnector flow model, published externally. This project therefore seeks to produce an improved method of converting future market prices data into a forecast of hourly electricity prices. | |
| Data | No related datasets |
|
| Projects | No related projects |
|
| Publications | No related publications |
|
| Added to Database | 02/10/24 | |
