The current lack of centralised clarity in dispatch reasoning makes it difficult to identify and evaluate possible process improvements to mitigate perceived skips. This project will explore the current state of dispatch transparency and define innovative new routes to increased dispatch transparency, including developing a new definition and methodology as well as a proof-of-concept tool. This will give engineers greater opportunity to mitigate potential future skips and enable NESO to understand the wider system conditions that contribute to the occurrence of perceived skips. This will be achieved by consulting with stakeholders and specialists, auditing external and internal data sources, and exploring statistical and AI methods that will prove useful in terms of increasing the range and scope of dispatch transparency tools available to NESO.
Benefits
This project will build upon on-going work to provide improved dispatch advice and facilitate convergence between Electricity National Control Centre (ENCC) engineers and their support tools. This project should provide improved situational awareness for ENCC, giving potential balancing costs savings through identification/implementation of more economically beneficial options to obtain balancing services. It will also aim to enhance the clarity and authority with which NESO communicates on the subject of skip rates and dispatch reasoning.
For external stakeholders, an improved dispatch transparency methodology will provide clearer lines of communication between the market and the control room, giving deeper business intelligence to zero carbon operators enabling them to improve their participation in the balancing mechanism.
Learnings
Outcomes
Two promising machine learning models have been identified in Gradient -Boosted Trees and foundation modelling. WP4 has defined a specification for a proof-of-concept tool using these approaches and this will be implemented in Phase 2.
Lessons Learnt
While Generative AI models such as LLMs may be of interest for ingesting and analysing text-based data such as ENCC reports, and trips and outages, they were deemed unsuitable at this stage for this purpose as they have not yet reached maturity using time series datasets. Machine learning approaches are more advanced, well understood and show more promise when attempting to predict dispatch patterns.
As part of the data review undertaken as part of this project, additional data sources were identified as helpful to this analysis and changes to data collection for NESO may occur as a result.
For the purposes of this project, a decision is defined as the issuance of a BOA.
The approach taken here will be to build models which can accurately predict the number and volume of BOAs issued, and when these models are accurate enough, use well-understood statistical methods to examine which factors present in the data are having the largest effect on the model predictions. This is an indirect method of examining decision making but given the number of BOAs issued over the course of a shift, more direct methods are impractical, time intensive and expensive.