Nov 2020
Electricity Distribution
Spatially Enabled Asset Management (SEAM)
WPD_NIA_054
Live
Nov 2020
Oct 2021
Western Power Distribution and Western Power Distribution South West
Jenny Woodruff
Click here to send a question to the contact.
Network Innovation Allowance
ED - New technologies and commercial evolution
Comms & IT
£426,298.00
Over time, various factors have adversely affected the quality of DNO’s Geospatial Information System (GIS) data. If datasets are shared with patterns of error, then different users will fill these error gaps in different ways leading to inconsistent results from analysis and how the data is exploited by applications. A Machine Learning (ML) tool is proposed to carry out data cleansing and data gap closure of WPD’s network GIS and relevant network data. The ML tool will be trained and populated with existing network asset data and run to identify data gaps. The model will initially be developed based on a set of business rules that will be updated based on the outcomes of the ML algorithms. Appropriate will be testing carried out to validate the results and assess the accuracy of the model.
In line with the overall objective of creating and testing a machine learning algorithm to identify and propose fixes for GIS data issues, the project objective are to;

  • Generate of potential hypotheses to test and use cases for the tool to be applied to
  • Understand the data available to support the machine learning proof of concept
  • Outline of the model design including selection of machine learning algorithms.
  • Create a final cleaned and prepared dataset that will be used to train and develop the model.
  • Provide an interim report that sets out early findings from the modelling and direction for the remainder of the project.
  • Develop the final version of the PoC model and front end.
  • Carry out statistical evaluation of the model and accuracy through comparison of the model outputs with baseline and training datasets.
  • Carry out data cleaning and loading of selected network area, including schematics if available in the format of a connectivity and impedance electrical model of EHV, HV and LV networks.
  • Provide a summary of key findings, assessment of outcomes against success criteria, recommendations and learnings to be shared.
The project will focus on errors that cannot currently be identified and fixed automatically. By highlighting potential errors and suggesting suitable fixes this will improve the usability of the GIS datasets by third parties, particularly where issues relate to missing data. Similarly, this is expected to reduce the time taken to manually identify and fix these GIS issues.