Applying Data Analytics to Vegetation Management for Grid Reliability
- February 8, 2019
- 554 views
Vegetation management is a major expense for utilities. Falling tree limbs regularly disrupt electric supply, particularly during storms. Wildfires also can burn vegetation close to transmission and distribution lines and sometimes cause widespread outages.
Texas-based Oncor and IBM are using data analytics to help identify vegetation management priorities and deploy resources for efficiently to better ensure grid reliability.
The approach is called “Weather Company Vegetation Management – Predict” and is designed to process large amounts of geospatial and time-based datasets collected by satellites, drones, aerial flights, sensors and weather models.
The resulting insights are intended to help utilities like Oncor monitor vegetation growth across their service territory, allowing them to better identify and predict potential conflict points with power lines.
Vegetation management can be a time-consuming process, said Peter Stoltman, Oncor’s vegetation management program manager, in a statement. Analytics better enable the utility to prioritize high-risk areas. In turn, this helps the utility adapt maintenance operations to improve public safety and service reliability.
Oncor is not the first Texas utility to use data analytics for vegetation management.
Texas A&M University researchers in 2017 unveiled a model that can predict potential vulnerabilities to utility assets and map where and when a possible outage may occur. In practice, the predictive feature allows trees in areas with the highest risk to be trimmed first.
Researchers used data provided by CenterPoint Energy, which operates the wires, poles, and electric infrastructure in a 5,000-square-mile electric service territory in the Houston metropolitan area.
By analyzing potential weather impacts on power systems, the university researchers can predict where and when outages may occur. Data such as a utility company’s operational records, weather forecasts, altitude, and vegetation around the power systems all can be used to customize the model. The model can predict weather hazards, vulnerability of electric grids and the economic impact of the potential damage.