MECOMS is an IT solution provider specialised in the utility sector and focused on Microsoft and Azure technologies. We’re investigating how artificial intelligence can help the different players in the utility market run their business processes in a more efficient way, using different techniques like machine learning and advanced chatbots.
We’ve run several different proof of concepts, including building a specific chatbot for a customer service area or using blockchain capabilities for managing smart contracts.
For distribution grid operators, we see interesting opportunities in the area of machine learning. We came up with the idea of using machine learning to help run the process of validation of meter readings that arrive as raw data at the IT system. Machine learning could be used to observe whether there is a consistent pattern in the reasons why meter readings run into validation errors. If the ‘machine’ can spot these patterns and take on the validation step, we can avoid a user needing to manually check all exceptional validation errors.
Key to these models is having access to a large amount of data. When smart meters are fully rolled out, the amount of received data is multiplied and available at a much earlier stage, meaning that abnormal usage patterns, disruption and device malfunctions could be identified and used for forecasting and predictions, maintenance and much more.
Knowledge, the availability of applications and AI business cases aren’t directly the greatest obstacle for our industry. Access to sufficient amounts of good data, together with the slow roll-out of smart devices, is the bigger challenge.
Mar Jorba is product manager for MECOMS
This article was originally published in the Winter 2020 issue of The Record. To get future issues delivered directly to your inbox, sign up for a free subscription.