Projects
Projects: Projects for Investigator |
||
| Reference Number | NIA_NGSO0001 | |
| Title | Optimisation of Energy Forecasting - analysis of datasets of metered embedded wind and PV generation | |
| Status | Completed | |
| Energy Categories | Renewable Energy Sources(Solar Energy) 50%; Renewable Energy Sources(Wind Energy) 50%; |
|
| Research Types | Applied Research and Development 100% | |
| Science and Technology Fields | PHYSICAL SCIENCES AND MATHEMATICS (Applied Mathematics) 75%; ENVIRONMENTAL SCIENCES (Earth Systems and Environmental Sciences) 25%; |
|
| UKERC Cross Cutting Characterisation | Not Cross-cutting 100% | |
| Principal Investigator |
Project Contact No email address given National Grid Electricity Transmission |
|
| Award Type | Network Innovation Allowance | |
| Funding Source | Ofgem | |
| Start Date | 01 June 2017 | |
| End Date | 01 February 2018 | |
| Duration | 8 months | |
| Total Grant Value | £34,150 | |
| Industrial Sectors | Power | |
| Region | London | |
| Programme | Network Innovation Allowance | |
| Investigators | Principal Investigator | Project Contact , National Grid Electricity Transmission (100.000%) |
| Web Site | http://www.smarternetworks.org/project/NIA_NGSO0001 |
|
| Objectives | The project plans to deliver:
Delivery of objectives listed above, leading to a reduction in mean demand forecast error in the three months following completion of the project compared to the previous three months of at least 20 MW. The benchmarking analysis will be based on the 365 day average error. It is expected that a 20 MW step change would show as a 5 MW reduction after 3 months on a rolling 365 day average. |
|
| Abstract | Forecasting renewable generation output is a key challenge for National Grid as GB System Operator; effective forecasting is vital to keeping the lights on and minimising the costs of operation that fall onto industry and consumers. Two new datasets of embedded generation output have recently been acquired by National Grid: Several years of historic output from around 20,000 domestic PV installations, at 30 minute or better resolution. To go with this data, we have hourly weather forecasts and outturns for around 60 weather stations for the last 18 months, and 80 for the last 6 months. Embedded wind generation output by Grid Supply Point by half hour for the last 4 years. To go with this, we have wind speed forecasts and outturns for 80 - 100 weather station locations, and metered output from directly connected wind generators - both 10 second spot data and 30 minute integrated data. We want to analyse this data to optimise the correlations used to convert forecast weather variables into power generation forecasts for both PV and embedded wind power generation. The proposed work will be supported by three PhD research students from The Alan Turing Institute (ATI), under the supervision of academics from the universities of Oxford, Warwick, Edinburgh and Sussex to work on the identified datasets for three months this summer. The ATI, as a leading UK institute for data science, specialises in dealing with Big Data, such as the data sets now available to us at National Grid, and have the analytical tools, expertise and access to resources necessary to analyse this data. The students will work with support from Senior Energy Forecasters from the Energy Forecasting Team at Electricity National Control Centre (ENCC) in order to analyse the large volume of data available and identify innovative ways of improving our demand forecasts. Key deliverables from the project would be new power correlations for wind and solar generation which could be implemented immediately into National Grid’s forecasting process (after suitable testing to ensure that there is no risk to system security) Note : Project Documents may be available via the ENA Smarter Networks Portal using the Website link above |
|
| Publications | (none) |
|
| Final Report | (none) |
|
| Added to Database | 14/09/18 | |
