Digital Infrastructure

AI for Visibility and Forecasting of Renewable Generation

The AI for Visibility and Forecasting of Renewable Generation project aims to enhance UK Power Networks' ability to forecast unmetered solar energy generation. By developing a machine learning (ML) algorithm, the project will infer the capacity of unmetered solar generation behind substations. This capacity estimate will feed into a solar forecast algorithm, producing forecasts at primary substations. Improved visibility and forecasting will help UK Power Networks better anticipate network power flows, reduce procurement costs, minimize renewable curtailment, and inform long-term planning. This project aims to lower costs for end users and support a sustainable energy system.

Key deliverables

  • Develop machine learning algorithm for renewable generation forecasting
  • Improve capacity estimation for unmonitored generation

Target outcomes

  • Achieve meaningful improvement in forecast accuracy
  • Enhance energy accounting for behind-the-meter generation

Measures of success

  • Forecast accuracy improvement (quantile exceedances, pinball loss
  • Capacity estimation accuracy and uncertainty reporting
  • Evidence of cost efficiencies achieved

Stakeholder Engagement

Stakeholder engagement plan is in development.

Timeline

Planned start:
02.04.2025
Target completion:
31.07.2026

Status

Extended

Milestones

  • Discovery Phase Kick-Off (Apr 25)
  • M1 - Completion of WP1 (Jul 25)
  • M2 Completion of WP2 (Nov 25)
  • M3 - Completion of WP3 (Jul 26)

Change Log

Featured Projects

Customers

AImee

The project aims to develop a digital customer experience that uses cutting edge technology such as AI and machine learning to offer tailored advice and support at scale to vulnerable consumers at risk of being left behind in the energy transition. It will be designed with input from service delivery partners through workshops and interviews. The project includes designing, building & testing the tool, and a service trial with consumers to gather feedback and assess the tool's success.

Status: ExtendedTarget end: 30.09.2027

See project
Assets and Operations

SummarAIze

SummarAIze is an initiative to improve how power outages are managed by automatically generating clear incident summaries and more accurate restoration time estimates. It uses data from our outage management system (ADMS) to help teams respond faster and keep customers better informed during power cuts.

Status: In ProgressTarget end: 31.07.2026

See project
Smart Networks

Short-Term Forecasting Platform

Develop and evolve short-term forecasting tools/models to predict load, generation, network constraint and load related network intervention requirements across different voltage levels and operational timescales.

Status: CompletedTarget end: 12.03.2025

See project
Digital Initiatives Page