Projects
Projects: Custom Search |
||
| Reference Number | NIA2_NGESO048 | |
| Title | GB Inertia Forecasting with Regional Extrapolation | |
| Status | Completed | |
| Energy Categories | Other Cross-Cutting Technologies or Research (Energy system analysis) 50%; Other Power and Storage Technologies (Electricity transmission and distribution) 50%; |
|
| Research Types | Applied Research and Development 100% | |
| Science and Technology Fields | PHYSICAL SCIENCES AND MATHEMATICS (Computer Science and Informatics) 20%; ENGINEERING AND TECHNOLOGY (Electrical and Electronic Engineering) 30%; ENVIRONMENTAL SCIENCES (Earth Systems and Environmental Sciences) 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 December 2023 | |
| End Date | 31 May 2024 | |
| Duration | ENA months | |
| Total Grant Value | £158,000 | |
| 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_NGESO048 |
|
| Objectives | The existing inertia metering & forecast solution in question applies machine learning to build a forecast model for each inertia region that relates metered inertia (derived from real-time PMU data) to "inertia predictors" variables such as regional demand, connected synchronous generator inertia, and levels of solar and wind generation. Such models can then be executed with forecasts of the same predictor values to generate a corresponding inertia forecast.This project will explore the relationship between measured and forecast inertia in Scotland to investigate the possibility of applying this relationship to forecast the inertia for England and Wales. It will aim to use a machine learning model built solely from Scotland inertia metering data, to be fed with England & Wales and GB-wide predictor values to provide an inertia forecast for the whole of GB. In this way, inertia could be forecast for other network regions without the need for measured data from PMUs. Various approaches will be explored, for example the normalisation of inputs and outputs to the machine learning model to account for regional differences.The project will be completed in a single work package and will utilise the following input data to explore potential solutions:England and Wales predictors ideally for a period of 3-12 months, including rotating inertia, solar and wind generation, and demandValidation events of known Megawatt Dispatch (MW) disconnections outside of England & Wales, either occurring in Scotland or on an external High Voltage Direct Current (HVDC) trip. Ideally these events should overlap with the predictor dataset in (1). The associated PMU frequency measurements from 45 minutes prior to, and 5 minutes after these events from across the GB grid will also be utilised so a GB Rate of Change of Frequency (RoCoF) value can be determined. Scotland-only PMU measurements will be suitable if it is not possible to get accurate information from other locations.Estimates of GB inertia from the present GB-wide inertia estimation method (distinct from the PMU-based inertia metering & forecast solution), the 30-minute inertia estimate provided on the ESO data portal are expected to be sufficient for this.Validation of the forecasts will be carried out by the ESO team against data from a number of methods and tools used within the ESO, looking at both continuous inertia calculations and trip events. Deliverables include a report describing potential solutions explored and assessment of their suitability to achieve the project objective, followed by a workshop with the ESO to discuss findings within the report. If an identified method is demonstrated to give good results, the project will provide a proposal for implementing the chosen enhancement into the existing inertia forecasting solution.In line with the ENA"s ENIP document, the risk rating is scored LowTRL steps = 1 (2 TRL steps)Cost = 1 (<£500k)Suppliers = 1 (1 supplier)Data assumptions = 2 (Assumptions known but will be defined within project)Total = 5 (Low) This project will focus on two potential solution areas:Explore enhancements that can be applied outside the existing machine learning algorithms, including normalisation of data in and out of the machine learning model.Evaluate alternative approaches and enhancements to the existing machine learning algorithm.If these solutions are successful, the project will also consider an implementation plan for the chosen enhancements into operationalinertia tools. Implementation of any recommendations to the existing solution will be made through a separate investment. To establish if it is possible to use a model based on Scottish inertia metering data to forecast the inertia of England and Wales, and therefore the whole GB inertia.If successful, provide a proposal for implementing the enhancements into the relevant operational inertia tools. | |
| Abstract | One of the primary inertia tools used by the ESO, forecasts inertia 24 hours ahead, but only for regions where Phasor Measurement Units (PMUs) enable inertia measurement This project will investigate potential solutions for an inertia forecast model for England and Wales ahead of installations of PMUs in these regions, by using the inertia metering data from installed measurement units in Scotland to tune and verify models. These models built on Scottish PMU data would be fed with inertia predictor data (such as demand, synchronous and inverter-based generation levels) for the remaining regions of GB in order to provide inertia forecasts for the whole GB system. | |
| Data | No related datasets |
|
| Projects | No related projects |
|
| Publications | No related publications |
|
| Added to Database | 02/10/24 | |
