The Dimensions call for speakers is open through April 17
Vegetation risk to overhead power lines is a perennial issue for electric utility networks. A sudden electric flashover can ignite encroaching vegetation or a tree-fall can result in electrical faults, sustained outages and wildfires. These issues cause expensive damage and repairs, decrease network reliability and impact a provider’s ability to ensure a sustainable energy source.
Standard approaches for vegetation management use LiDAR data to identify which trees are close to the network and provide a static snapshot of the state of vegetation threats. While this technique provides some value, it doesn’t identify growth patterns or prioritize tree-fall risk—two factors that are paramount for maintaining consistent distribution networks.
As an electricity provider to 2.4 million people, Australia’s Endeavor Energy has been challenged to cost-effectively assess and predict vegetation risks to its distribution assets and deliver reliable energy to its customers across New South Wales (NSW). The company wanted to implement a smart and efficient vegetation management solution that would help them foresee vulnerabilities, prioritize identified risks and develop a targeted, risk-based management approach. Most importantly, it needed a system that would lower vegetation maintenance costs without reducing their exposure to risk.
Those needs led Endeavor to test the Vegetation Analytics solution from Trimble’s NM Group, which specializes in providing technology solutions for the energy industry.
A wide-scale trial, the project focused on 12,000 kilometers of the company’s NSW network based in a high bushfire-risk area. For the most effective historical analysis, Endeavour and NM Group collated and prepared three years’ worth of geospatial data, including cutting records, hazard tree records and modeling Endeavor’s unique calculation of risk criteria. Teams also mapped more than 3,500 fallen trees to build the statistical models needed to predict the likelihood of tree-fall risk.
Field teams also surveyed more than 43 sites and measured and inspected 400 trees to calculate biological and structural variables for use in the modeling.
Using Vegetation Analytics’ data integration and diagnostic tools, the NM Group’s team were able to inventory trees, model growth patterns per span and risk-rank trees based on their match to local fall patterns. Quantitative testing of this tree-fall model on historical tree failure indicated an 80 percent success rate in the model’s prediction ability.
With the comprehensive data analysis, Endeavour could also clearly identify which spans should be pruned versus cut. Being better informed enables them to reduce contractor costs through more targeted work assignments.
The foresight also enables Endeavour to be proactive, prioritize vegetation management programs, and optimize costs.
“Having well-organized and high-quality data is a key input to this type of project which uses powerful data analytics, cloud processing and machine learning techniques to optimize our vegetation maintenance program,” said Vegetation Control Manager, Endeavor Energy.
Based on the project’s success, Endeavour is branching out to a more cost-effective, risk-based approach to vegetation management. Firmly rooted in using Vegetation Analytics, the company is driving toward its goal of reducing its management operating costs by 40 percent.