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.
Benefits
This project presents significant advantages by revolutionising the voltage advice process. Adapting the approach to generate accurate and responsive voltage advice ensures adaptability to evolving outage scenarios. This flexibility allows timely advice updates in planned and unplanned situations, leading to cost savings through proactive decision-making.
Additionally, it enables the early identification of issues, facilitating efficient contracts with generators and ultimately reducing consumer expenses. Solutions delivered through this project support coordination of the system to navigate voltage constraints and ensure security of supply, helping the ESO to accommodate greater renewable generation and reduce the carbon intensity of the grid.
Overall, the initiative promises more robust and precise voltage management guidance for the control room, streamlining operations and fostering greater efficiency.
Learnings
Outcomes
Despite encountering several challenges, the VoltaVisor project yielded outcomes that provide a solid foundation for future advancements in voltage management. The primary achievement was the development of an Alpha proof-of-concept (PoC) prototype designed to deliver rapid voltage advice using AI techniques. This prototype, created in Python with a web-based GUI, enabled Voltage Engineers to input assumptions and receive immediate voltage management advice. Although the tool's functionality was limited to outages affecting reactive equipment and generators, it represented a notable step towards automating the traditionally manual and time-consuming process.
Additionally, the project successfully demonstrated the feasibility of using alternative data sources, such as the ENCC's daily Voltage Management reports, when initial data extraction proved problematic. This adaptation highlighted the project's flexibility and the team's problem-solving capabilities. The user interface of the prototype received positive feedback for its usability and visual appeal, indicating strong potential for user engagement in future iterations. Furthermore, the project underscored the importance of rigorous data quality assessment and iterative refinement based on user feedback, providing crucial insights for subsequent phases. Overall, the VoltaVisor project established a critical understanding of the challenges and potential in developing AI-driven voltage management solutions, paving the way for more advanced and accurate tools in the future.
Lessons Learnt
The VoltaVisor project provided valuable insights that will inform the planning and execution of future initiatives. One of the foremost lessons learned is the critical importance of data quality and accessibility. Initial difficulties in extracting historical electricity transmission status data led to significant project modifications. Future projects should prioritise a comprehensive data assessment phase to ensure the availability and consistency of required data sources. This proactive approach will mitigate risks associated with data integration and enhance the reliability of outcomes.
Another key lesson is the necessity of flexibility and adaptability in project management. The ability to pivot to alternative data sources and adjust project scope based on available information proved essential in maintaining progress. Additionally, iterative testing and incorporating user feedback were crucial for refining the prototype and aligning it with operational needs. Emphasising user engagement from the outset ensures that the developed tools are both functional and user-friendly. Finally, close collaboration with IT and network planning teams is vital for successful data integration and tool deployment, highlighting the need for interdisciplinary cooperation in complex projects. These lessons will guide future efforts in developing innovative and effective solutions.
