Back to search

ENERGIX-Stort program energi

Machine Learning Models for the Surveillance of Physical Power Markets

Alternative title: Maskinlæringsmodeller for overvåkning av fysiske kraftmarkedene

Awarded: NOK 4.7 mill.

Project Number:

282395

Project Period:

2018 - 2021

Funding received from:

Location:

A critical but often overlooked requirement for power markets is transparency. A market that is not transparent may be subject to manipulation. This reduces market efficiency, public confidence, and ultimately entails a socio-economic cost. In our project, project HAWK, we develop machine learning models for the daily monitoring of physical power markets. The developed models and software will be designed to run automatically and are used by power market regulators such as NVE, market operators, brokers and TSOs in their daily monitoring activities, and by market participants trading in physical markets to monitor and regulate their own trading activities. In addition and as part of the project, several of the monitoring ML methods developed will be tested by NVE as part of their monitoring activities. Based on interviews with regulators and market participants, as well as assessments of market surveillance practices and the literature, we have identified several promising research areas. The first of these is automation - to develop ML methods to replicate monitoring analysis performed manually today, to increase accuracy and speed. The second is ML methods to identify anomalous behaviour in the market bidding of individual actors. The third is ML methods for predicting the ability of individual players to influence or manipulate the market at any given time. The research work started in the first quarter of 2019 and will continue until 2021. Our focus in 2020 has been on identifying discrepancies in the players' bids and market results. It has given very promising results and is now being implemented at NVE for testing. In the rest of the project, we will focus on identifying periods in which individual actors have the greatest impact on the market and generating alerts based on this.

The goal of our project is the development and implementation in software of machine learning models for the operative surveillance of physical power markets. The developed models and software will be designed to run automatically and be used by power market regulators such as NVE, market operators, brokers and TSOs in their daily surveillance activities in physical power markets, and by market actors trading in physical markets to monitor and regulate their own trading activities. Power markets often exhibit low elasticity of demand. In combination with large and flexible power storages (e.g. hydro power and, increasingly, batteries in combination with renewables) this results in market places that are particularly vulnerable to abuse. Surveillance of markets with high renewable and storage penetration is especially complex and difficult. Auction markets where all participants face the same price may be particularly exposed, especially in periods with congestion. Currently, most models and tools used for market surveillance in the power market based on sets of rules used to define market abuse scenarios. Rule-based approaches have several weaknesses, such as a tendency to produce large volumes of alerts, an inability to assess and priories the alerts produced, and difficulty in catching new behaviours. Machine learning is well suited for such monitoring, and can execute much more effectively than rules alone. The monitoring will be more automated, produce more relevant alerts (and fewer false positives) and enable users to detect market behavior that would otherwise be obscured. Such tools will also be more robust, since they will be less dependent on specific persons. This will in turn enable more effective and efficient mitigating actions to be planned and and taken, increasing the transparency and efficiency of the power system, especially given increased use of storage and renewable generation.

Activity:

ENERGIX-Stort program energi