go to top scroll for more

Projects: Projects for Investigator
Reference Number	NIA2_NGESO025
Title	3MD (Market Monitoring Model Development)
Status	Completed
Energy Categories	Other Power and Storage Technologies(Electricity transmission and distribution) 80%; Other Cross-Cutting Technologies or Research(Energy Economics) 20%;
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) 80%;
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 November 2022
End Date	31 October 2023
Duration	ENA months
Total Grant Value	£250,000
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_NGESO025
Objectives	"This project will investigate whether ML will allow for the consideration of uncertain variables that cannot currently be factored into analytical techniques. It will investigate the development of statistical models which identify anomalous pricing and positioning strategies in relation to constraint data. 5 work packages have been defined. These will cover: WP1: Exploratory data analysis of National Economic Database (NED) data filesWP2: Detect securing of artificial priceWP3: Detect false physical notificationsWP4: Detect constraint-related manipulationWP5: (Dependant on Successful Outcomes) Prototype integration In line with the ENAs ENIP document, the risk rating is scored Low.  TRL Steps = 1 (2 TRL steps)  Cost = 1 (£250k)  Suppliers = 1 (1 supplier)  Data Assumptions = 2  Total = 5 (Low) " "Whilst ML and hidden variable models are used across multiple innovation projects for different purposes and also in other industries and organisations outside of the ESO, they have not been applied in a utility for a similar purpose. Learnings will be shared within the ESO where applicable, however this will be a non-default innovation project and, as such, detailed findings and models will not be shared externally. Ultimately, knowledge of enhanced monitoring capabilities being used, may encourage market participants to better consider REMIT and Grid Code requirements as they develop new trading strategies and support the market monitoring team in working with trading parties to reduce instances of potential breaches. This may reduce costs to consumers through a reduction in incidents of prices that do not directly result from normal market supply and demand interactions. It will also enable detection of changes in pricing or positioning in response to the management of system conditions, reducing the risk for exploitation of dominant market positions where they arise because of geographic or technological monopolies. " "Develop methods for out-of-characteristic market prices, physical positions in response to system operability issues such as constraints by applying statistical techniques to identify potential market abuse.Develop methods for detecting and characterising anomalies. Enhance current manual investigative techniques by using multiple new data sources to generate alerts. This will enable detection of cross market events and ensure alerts better consider market externalities, reducing false positives compared with current monitoring systems.Enable models of pricing and positioning to be developed that are individual to Balancing Mechanism Units (BMUs) which each have different economic drivers and therefore will behave differently given the same set of system and external conditions. "
Abstract	National Grid ESO are required by our License and by the REMIT regulation (EU Regulation on wholesale Energy Market Integrity and Transparency) to monitor the market for suspicious activity relating to manipulation, insider trading, breach of Grid Code etc. Our current, manual, processes are not infinitely scalable or transferable as the market grows so greater automation and sophistication is required. The development of a more sophisticated, Machine Learning (ML) based solution will be investigated to increase the efficiency of team activities and be scalable to new products and increasing market participant numbers.
Publications	(none)
Final Report	(none)
Added to Database	01/11/23