Grid Optimizer and DTU Compute (Danish Technical University – Department of Applied Mathematics and Computer Science) will collaborate on a project with the objective of using DTU’s world-class research in providing machine learning based picture and video recognition for optimizing some of the most costly technical work processes in planning and designing grids (fiber, electricity, water, etc).
The project will develop an application that will be integrated into the Grid Optimizer machine learning engine. The application will analyze detailed pictures and videos taken by drones in order to automate the validation of grid design quality and costs. Significant cost savings for infrastructure establishment can be expected for utilities by providing real-life, detailed update of business cases through the application. Currently these design validations are done manually, or not done at all. The application will use machine learning to obtain the grid specific competences required and standard drones with standard camera technology to capture the required picture and video data input.
Please contact Lars Struwe Christensen at Grid Optimizer for more information and details.
Machine learning techniques look set to transform the way that utilities companies predict customer usage and production capacity in the years ahead. Utilities take note: when it comes to analyzing data, machine learning could be your best bet for achieving new insights, far outstripping other methods in terms of effectiveness, according to a new report published by analyst company Navigant Research, Machine Learning for the Digital Utility.
While machine learning has existed in parts of the ‘utility value chain’ for years, various drivers are expected to increase its use in other parts of the business, the report says. In particular, it has several advantages over other approaches when it comes to customer segmentation, pricing forecasts, anomaly decision, fraud detection and predictive maintenance. Basically, it’s about jobs that use the analytic processes of clustering, regression and classification.
“The utilities industry is already using self-learning algorithms, particularly in the field of asset monitoring and predictive maintenance, and several reasons suggest the use of machine learning will expand to many more use cases and its adoption will accelerate,” says Stuart Ravens, principal research analyst at Navigant.
Innovation Fund Denmark will invest in a 4.8 million DKK development project at breakoutimage, a commitment from the Fund´s “InnoBooster” programme. The project will develop advanced artificial intelligence to optimise complex technical workflows at utility companies (for example, electricity and fibre networks). The project is based on Grid Optimizer – a cloud-based platform which develops advanced machine learning by collecting data from across utility companies’ various IT systems, and then aggregating the data with publicly available data sources. The InnoBooster project will collaborate closely with DTU Compute to develop the most advanced algorithms and technologies in artificial intelligence, which will be used for technical workflows for implementation and operation of infrastructure at utility companies.