This project will review the current methods of calculating system stability needs and implement automation and machine learning to calculate system stability needs for the GB network at a granular level. This project will:
- Review the current methods of calculating system stability needs and identify areas of improvement.
- Perform the analysis on a sufficiently granular representation of the active and passive network components in the GB system.
- Apply automation and other necessary methods (machine learning) to manage additional computational burden of using detailed network representation.
Benefits
The project will directly facilitate the energy transition as it will improve the calculation of system requirements in terms of stability; this an essential parameter to allow the integration of renewable generation onto the GB network. By understanding more accurately stability needs, it is possible to anticipate the technical solutions that will guarantee the system operates in a reliable and safe way, facilitating the transition to a zero carbon energy system while keeping the lights on.
Learnings
Outcomes
The project was delivered through five work packages, resulting in the delivery of five technical reports, two technical workshops, and two analysis tools developed under WP2 and WP3:
· WP1 delivered a completed WP1 report reviewing the current methodologies used by NESO for inertia, short-circuit strength, and voltage management assessment. The report also reviewed and qualitatively compared literature-based indices to support scenario-based, year-round analysis and informed the selection of indices for implementation in later work packages.
· WP2 delivered the WP2 report and a DIgSILENT PowerFactory-based analysis tool. The work included ingestion and interpretation of scenario data, use of the reduced ETYS model, data processing with feature engineering and clustering, system-needs calculation, and testing within DIgSILENT PowerFactory. A compromised data-mapping scheme was implemented to address misalignment between full BID3 datasets and the reduced ETYS model. A technical workshop was held at NESO Faraday House on 14 May 2025 to demonstrate the WP2 outcomes.
· WP3 delivered the WP3 report and a standalone system-needs calculation tool. The work completed outstanding elements from WP2, including the scoring methodology, and delivered comparison between existing and newly developed approaches, definition of output file formats and tool interfaces, and training and handover activities. A technical workshop was held at NESO Faraday House on 29 October 2025, and supporting user documentation and training materials were delivered alongside the tool.
· WP4 delivered a completed report covering secure server setup, access control, and data protection measures to meet NESO security requirements.
· WP5 delivered a completed report resolving data-mapping issues between full BID3 data and the reduced ETYS model, including a compromised mapping methodology to maximise mapping efficiency. A paper on the initial work on the machine learning algorithm for network convergence was accepted and presented in the poster session in CIGRE Paris 2024.
Lessons Learnt
The project highlighted the importance of planning data, model, and information sharing across the entire project lifecycle and agreeing early on a suitable approach and format for exchanging data and essential models between NESO and project partners, particularly where confidentiality and commercial sensitivity apply.
It demonstrated the need to allow sufficient time for security clearance procedures and data-sharing checks, as these can introduce significant delays.
The project also showed the importance of developing a mitigation or contingency plan to address potential human resource changes during the project, particularly within partner organisations.
