Projects
Projects: Projects for Investigator |
||
| Reference Number | NIA2_NGESO057 | |
| Title | Alternative Metering (Baselines) | |
| Status | Completed | |
| Energy Categories | Other Power and Storage Technologies(Electricity transmission and distribution) 100%; | |
| Research Types | Applied Research and Development 100% | |
| Science and Technology Fields | ENGINEERING AND TECHNOLOGY (Electrical and Electronic Engineering) 100% | |
| 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 September 2023 | |
| End Date | 31 March 2024 | |
| Duration | ENA months | |
| Total Grant Value | £400,000 | |
| 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_NGESO057 |
|
| Objectives | "This project will consist of three Work Packages (WPs) starting with a review of theoretical analysis methods through to the development and delivery of a monitoring algorithm: WP1: determining available data sources such as historical records of real-time and post-delivery metering of Frequency Response delivery as potential algorithm inputs and agreeing the format of data outputs to ensure it will be deliverable in to the existing ESO performance monitoring system. WP2: research of analysis techniques and how they can be combined in an efficient and accurate algorithmic model. WP3: writing the code for a Proof-of-Concept (PoC) model to allow the operation of the algorithm on ESO systems to validate test data from industry participants in their development of data derived metering solutions. This project will develop methodology to detect manipulation in response data profiles submitted under a new proposed provision of flexibility service. As the new provision is not yet live, available response profile data is not directly applicable. Instead, it will form the basis for crafting a synthetic data generation algorithm. Of importance will be to synthesise data that reflects expected day-to-day variability and errors in measurement and reporting. That is, our solution must be robust to anticipated data quality when productionised and deployed. We will be guided in this by quantifying variability in current available data. A schema for generated data will be defined as part of scoping the synthetic data generator itself. It is expected that data used as the basis for qualitatively or quantitatively building a synthetic data generator will comprise response profiles originating from the ESO. Thus data quality will be assured by its unified and single-source nature. Any missing data will be filled by an appropriate imputation scheme as part of pre-processing. Finally, in developing the manipulation detection algorithm, we will be mindful of the potential for error in its conclusion. To mitigate this, it will not conclude a binary yes/no; rather, a level of risk will be reported, allowing for natural variability in the data and resultant grey areas where expert judgement can then be applied. In line with the ENAs ENIP document, the risk rating is scored Low. TRL Steps = 2 (5 TRL steps) Cost = 1 (£400k) Suppliers = 1 (1 supplier) Data Assumptions = 2 (Assumptions known but will be defined within project) Total = 6 (Low) " "This project will focus on reviewing the theoretical options and developing suitable ones into a usable PoC algorithm which can be implemented as a Minimum Viable Product (MVP) to begin trials for provider generated operational delivery data. The final deliverable will be the development and coding of the chosen algorithmic model in a suitable format and language for delivery in to the existing ESO performance monitoring systems to allow external submission trials to begin. The algorithm should use metered data, possibly combined with historical delivery data to output a score indicating the probability of manipulation. The algorithm must also be calibrated to set an appropriate threshold for the score to suggest if further investigation should be conducted WP1: Scoping Workshops will be undertaken to generate a process map indicating: the data sources available; any short- and long-term outputs likely generated by the analysis algorithm that will require presentation or storage; and interoperation of data streams with the algorithm itself. WP2: Solution identification There are several possible algorithmic avenues to quantify baseline legitimacy. With scope and data availability known, one or more suitable approaches will be designed based on mathematical analysis and machine learning. Solutions could include: Direct correlation analysis between submitted baseline and responseUnit capability and service attributionTime series analysisHybrid methodology WP3: Implementation and evaluation Following design agreement, the chosen solution will be delivered as end-to-end demonstration scripts. These will clearly show both pre-training on historic data, if applicable to the selected methodology, and the regular assessment process. This will initially be deployed as a proof of concept but could be expanded to a full production solution. If a successful solution is developed, the ESO IT teams will undertake the delivery and testing required for implementation on the IT systems, upon completion of the project. If there is a successful solution developed, found then, following the conclusion of this Innovation project, internal If appropriate, this will be progressed through to the live data analytics platform system to complement the existing data analysis tools. " "Validate metering data from service providers to ensure that submitted data has not been falsified Develop a PoC algorithm which can be implemented as an MVP to start accepting trials for provider generated operational delivery dataDevelop the chosen algorithmic model in a suitable format and language for delivery into the existing performance monitoring systems to allow external submission trials to begin." | |
| Abstract | Currently there are a significant number of assets which are not able to participate in Frequency Response services due to challenges in clearly demonstrating frequency response delivery separate from the delivery of other services. This means there is less competition in the markets and as a result the cost paid for response services is higher than it could be if these assets were able to participate. This project will investigate analysis techniques and develop an algorithm to validate Response delivery from a large number of these assets which are unable to use conventional metering solutions. This should enable service providers to participate in Dynamic Response markets with assets using forms of data processing to separate out dynamic response service delivery from other energy recorded by the meter. | |
| Publications | (none) |
|
| Final Report | (none) |
|
| Added to Database | 01/11/23 | |
