Introduction: The study shall include all SPD primary substations across the central belt of Scotland covering both the west and east coast. The wide geographical area is to provide a broad range of input conditions for the machine learning algorithms to ensure applicability across the GB area.

The project shall be a desktop exercise using historic SCADA, generation and discretised weather data. Where available, the project shall use 10 years of hourly data. Each primary substation will be allocated a geographic polygon which represents the service area for the substation.

This data will be used to build and evaluate models which disaggregate electrical demand into load driven by weather conditions and load driven by other customer behaviour. Analysis of the underlying trends will be undertaken.

The output from the project will then be used in network planning and the completion of regulatory reports.

Objectives:

• Analyse historical demand data and create normalisation models
• Evaluation of the weather normalised demand model
• Completion of uncertainty analysis against historical data.
• Analysis of demand trends – weather related vs customer behaviour.
• Creation of summary report and data files.
• Delivery of final presentation or paper at industry event/conference.

Expected Benefits: The project will be considered successful if the aforementioned objectives are realised and the outputs become a useful part of SP Energy Network’s suite of planning tools.