go to top scroll for more

Projects: Custom Search
Reference Number	NIA2_NGESO061
Title	VoltaVisor
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	PHYSICAL SCIENCES AND MATHEMATICS (Computer Science and Informatics) 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 March 2024
Duration	ENA months
Total Grant Value	£450,000
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_NGESO061
Objectives	The Project will be delivered through 3 work packages (WPs):Work Package 1: User research and design - Engage with ESO users to define the project problem statement and scope of the AI software solution, in particular, how the outcome of this project can support in providing voltage advice.Work Package 2: Data Science ingestion and analysis of relevant datasets (for example, regarding outages, prior voltage advice and system outcomes) to determine an appropriate solution design to be tested with ESO. The project will continue to build a proof-of-concept (PoC) solution, which represents the core output of this phase.Work Package 3: Backend engineering actively identify and test potential deployment pipelines, such that models described above can be successfully integrated into ESO infrastructure within subsequent phases.Using a combination of National demand forecasts at day to week ahead, historical outages, network voltage data, generator availability and previous voltage advice, Faculty will develop a PoC model that identifies the amount of voltage support (in MVars) required in each region (for the time corresponding to minimum demand, overnight on weekends), and possible combinations of plants and reactive equipment (e.g. Static VAR compensator, Voltage Controllers, Voltage Control Centres, Static Reactors) to deliver it, based on relationships identified from historical data.Due to the nature of the data utilised in the project it will restrict how the data can be handled and shared; we have put mitigations in place with our security teams to ensure that the data used for the project follows a strict governance process with our supplier, and information that is deemed confidential will be redacted from the final reports and outputs to ensure we comply with our obligations.  At the end of this project, we expect to have the following:A PoC solution for delivering fast voltage advice that can adapt to last minute changes and unscheduled outages, benchmarked against key metricsAn agreed plan for how the tool will be deployed for regular use by end users, developed in close collaboration with ESO"s IT team. While we expect the format of the advice to not change from current practice, deployment will require ongoing access to the data needed by the model.Established infrastructure for tool deployment as tested with a skeleton solution.However, we would not expect tools to be fully deployed and this would need to follow in a next iteration phase. In the next phase, we would anticipate the following activities to be undertaken, with estimated cost/effort to be developed towards the end of the project:Building of the full solution architecture and deployment of models within ESO infrastructureIf required, further refinement of the POC models based on findings from earlier phase to improve performance.Development of monitoring systems to ensure alerting in the case of unexpected issues. Monitoring for model performance and data drift will also be developed. Further user testing during live deployment to adjust usability or utility of tool.The project will deliver a solution that provides voltage advice in the same format as currently used by the Network Access Planning (NAP) team but to an agreed acceptable standard on far shorter timescales. Upon completion we will test out the tool further within NAP and the wider business and if successful we will aim to embed the tool into the NAP process with the help of the ESO IT teamsIn line with the ENA"s ENIP document, the risk rating is scored Low.TRL Steps = 1 (2 TRL steps)Cost = 1 (£450k)Suppliers = 1 (1 supplier)Data Assumptions = 2Total = 5 (Low) Currently, voltage advice for the week ahead is generated using simulations from PowerFactory software (a power systems model of the electricity transmission network), a process that takes approximately a week for Voltage Engineers to produce. In particular, Voltage Engineers spend considerable time manually inputting and adjusting different scenarios and contingencies, a process which is inflexible in adapting for last minute changes (e.g. plant outages).By examining the relationship between voltage, forecasted national demand, planned outages, and commonly seen patterns of advised voltage support, this project aims to deliver rapid voltage advice under most circumstances utilising AI techniques. The end solution will be used by voltage engineers to rapidly understand the total amount of support required and assess potential combinations of plants and other reactive equipment to mitigate high overnight voltages.This solution has scope to deliver significant time savings for voltage engineers, providing initial recommendations within minutes, as opposed to hours and days using existing methods. In turn, this can enable the ESO to test a wider set of scenarios than would have been possible before. This not only has benefits for time saved but also acts as an extension of existing capability, further improving system resilience and the quality of advice provided. This project aims to deliver a PoC AI solution to provide rapid voltage advice, namely, a solution that has been trained and tested on historical data but is not yet deployed on ESO infrastructure. The specific objectives of the project are to develop:A PoC model that identifies the amount of voltage support (in MVars) required in each region (for the time corresponding to minimum demand, overnight on weekends), and possible combinations of plants and reactive equipment (e.g. SVCs, VCCs, SRs) to deliver it, based on relationships identified from historical data. This will include initial designs of a front-end user interface to represent how the bespoke software would be integrated into decision-makingA plan for full deployment during a prospective phase based on engineering discovery activities combined with user research (deployment out of scope of this phase).
Abstract	Low demand on the network has the potential to push network voltages beyond safe operating levels. Network voltages are maintained within these safe operating levels by controlling which voltage support equipment: generators, circuits and reactive equipment are in use in each UK network region. Currently, determining which voltage support equipment should be in use is done using complex simulations, which can be time-consuming and take up to one week to plan which combination should be switched in or out for any one week.As part of this project, the relationship between national demand forecasts, outage patterns and voltage advice given in the Integrated Energy Management System (IEMS) data will be analysed and the most common pattern of assets switched in/out will be extracted. This will result in the development of predictive techniques that allow high confidence assignment of one of the common switching combinations or a suggestion to return to simulation in unusual circumstances, achieving huge reductions in time spent on simulation.
Data	No related datasets
Projects	No related projects
Publications	No related publications
Added to Database	02/10/24