Guaranteeing continuous and reliable power to end customers
The monitoring of the grid assets health and vegetation surrounding can help to enhance predictive and prescriptive maintenance while detecting vegetation hazards and asset anomalies. Thanks to the latest innovations in the imagery data this process is becoming faster and less expensive. Unluckily, this kind of data is often underused by the key responsible of the power grids.
DSOs, need to quickly identify possible future problems in the system to assure the reliability of the grids. To achieve this important target, they can take advantage of technological tools used to centralize, analyze and process this load of data. If this process is made in advance, it reduces costly emergency repairs and the risk of blackouts.
A virtual 3D replica of the grid to increase safety and detect anomalies
Based on the Network Digital Twin®, the Digital Asset and Vegetation Intelligence (DAVI) recreates a virtual 3D replica of the electricity grid and its surroundings, by acquiring and processing structured dataset provided not only by images, but by laserscanner, photography and video.
Doing this, it enables the identification of critical distances and the classification of the point cloud, consequently, vegetation inspection and predictive maintenance are brought up by asset recognition and anomaly detection thanks to AI.
Benefits
The global repository is among the advantages of the Digital Asset and Vegetation Intelligence: thanks to this platform it is easier to manage large volumes of images uploaded from drones, helicopters, pedestrian inspections and terrestrial laser scans.
All of this data is quickly processed, and then updates automatically the DSO’s GIS data to provide accurate location of assets within the grid. This technology, moreover, enables aerial audit that helps creating a model of the grid. Thanks to this, causes of possible incidents can be easily tracked down and, subsequently, solved.
The DAVI, furthermore, performs vegetation mapping and possibility to measure vegetation height even classifying it into small, medium and large thanks to its algorithm processing. Through machine learning it is easier to automatically and visually identify anomalies.
The Lidar technology when compared to satellite data acquisition performs even more accurate due to the centimeter precision (compared to meters precision from satellite technology) of the images, what can lead in more detailed recognition of the assets, detection of anomalies and vegetation distances.
These functionalities allow savings on patrol inspections, increase the safety for field workers, detect anomalies, and help predicting future outages or reparations. They also aid from an engineering point of view: using the Digital Asset and Vegetation Intelligence, in fact, visits on site become virtual and this tool can be used to design or actualize the electricity grid.
Enhancing efficiency and reducing maintenance and trimming plan expenses
DSOs reduce up to 26% of vegetation management costs, 15% of maintenance expenses and save up to 50% of engineering costs. We have collected this data in various pilot experiments conducted in Spain, Italy, Brazil, and Colombia.