Predict4Resilience - Discovery Continuity will inform the development of a “Weather Fault” tool which can:
- Forecast severe and extreme weather events;
- Improve the accuracy within the current forecasting window;
- Double the current forecasting window (up to 14 days ahead) and;
- Predict specific network faults and risks.
This project is in place to safeguard the delivery and continuity of the associated SIF project.
Benefits
Increasing resilience and reliability therefore having more visibility of the grid (increased forecasting) and a clear awareness of the impact (fault prediction), will realise a reduction in Customer Minutes Losses and Customer Interruptions. By reducing 5% of the customer interruption, it would realise £250k benefits to customers; and £2.5m for the sector, as noted in the SPD Executive Summary 2018/19. Furthermore, we would optimise the cost of maintaining the grid as the alternative to conventional reactive maintenance and repair.
Any reduction in outages has benefit to rural communities and vulnerable customers, who are at higher risk of severe impact from a power outage. This proposal would see improvements to their social return (primarily through reduced outages).
We will reduce CO2 by:
- Protecting assets from extreme weather and extending asset lifespan: thereby reduce carbon footprint from purchasing new equipment.
- A reduction in non-utilisation of staff on standby to reduce carbon footprint.
- Reducing the need for back-up diesel generators in energy network activities.
We will quantify the benefits via platform operation, as when it determines a forecasted fault, we are able to determine its impact via a reduction in:
- Outages, which would be measured by the CI/CML avoided (GBP) from the appropriate mitigation is put in place which avoids the outage, determined by the cost multiplied by the number of customers who would have seen an outage.
- Cost for associated maintenance (GBP), which can be determined from the avoided cost for labour and parts which would have had to respond to the avoided fault (minus the cost for the proactive repair).
- Associated CO2 impact (kt CO2) , as identified above, quantified through the avoidance of new equipment, reduced stand-by rotas and avoidance of diesel generators.
Additional benefits include:
- Supporting a topic which is a Government priority demonstrated by the development of a National Resilience Strategy.
- Learning embedded to the continuous development of our Control Room and Resource Dispatch which will be transferrable to T&D Asset Owners, and the Oil and Gas industry.
- Our partners will have the opportunity to provide the similar services other utilities with an estimated income of £500k per annum.
- Potential reduction of H&S incidents and unnecessary staff exposure to extreme weather hazards.
- More resilient operations: digitalisation and the use of data ensures that information is available to relevant stakeholders and preserved independently of changes in personnel.
Learnings
Outcomes
The project was successful in securing Beta funding following the successful demonstration of the prototype’s efficacy. Beta will evolve the prototype into a commercial solution that can be rolled out across GB DNOs and beyond, improving resilience with data-driven fault forecasting and decision-support.the benefits will be monitored as part of the Beta scope.
Lessons Learnt
The Discovery Phase demonstrated the potential benefits of the solution. In Alpha, the project utilised data science capabilities and experience in design and software development to further refine the prototype, resulting in a Fault Forecast Engine which uses cutting-edge statistical methods and an Interface that closely meets the user needs.
In Alpha, a prototype fault forecasting model and accompanying data infrastructure was implemented which verified the feasibility of the P4R’s innovations. These statistical models have shown forecasts are highly accurate in days 1-7, a key timescale for operational planning for the Control Room. It was also found that the model successfully predicted severe weather events resulting in large numbers of faults.
There was also a strong focus on engagement with users and User Experience (UX) experts to co-design the solution’s UX to ensure that it meets user requirements, such as the display of the entire fault probability distribution instead of the RAG status to aid decision-making.