Quick summary: To optimize vegetation management, we recommend these eight best practices to help utilities manage risk, reduce costs, and improve the customer experience.
Recent weather extremes and new legislation have made vegetation management a growing priority for utilities across the United States. Since 2010, utility operating expenses have increased year over year, so public and private utilities are eager to optimize costs while maintaining their focus on customer safety.
Defining vegetation management
The definition of vegetation management is the intentional monitoring and removal of natural plant matter to reduce risk and maintain the integrity and safety of equipment, structures, and/or human life.
Why vegetation management is important
Vegetation management is important for utilities because it reduces risk, increases safety for customers and employees, and lowers costs.
One area of rising important for vegetation management is wildfire response. 2021’s US wildfire statistics are staggering:
- 58,985 wildfires total, with at least one every state except Delaware.
- 18 states had over 1,000 fires each.
- 13 states had over 100,000 acres burned (equivalent to 500 times the size of Disneyland)
Other reasons to invest in vegetation management
- Increased customer awareness
- New regulations and federal investments
- Modernizing legacy systems
- Dynamic data infrastructure
How utilities can optimize vegetation management with best practices
1. Analyze legacy systems with a current state assessment and data quality audit
Utilities often use legacy systems. While functional in most cases, these tools are usually disconnected from the cloud, last updated “a few years ago,” and not geared toward the speed or connectivity of the future. To get a comprehensive, holistic understanding of how information moves within the company, utilities can analyze their systems from a technical perspective using a current state assessment and data quality audit. These reveal what data is captured, why, where it goes, what’s missing, and more. Another element of this analysis is process mapping, which provides a clear understanding of where and how to improve processes and tools.
2. Prepare inspectors and field technicians for change
It’s important for all team members to be aware of a change before it happens; including everyone with timely announcements, opportunities to provide input, and long lead times will reduce frustration and improve adoption. Utilities inspectors and field technicians work closely with the technologies involved in vegetation management, so they should absolutely be given priority during the modernization of tools and processes. Any change managers involved should be familiar with modern frameworks like the Prosci ADKAR® Model.
3. Expand Internet of Things (IoT) data sources
The utilities IoT market is expected to reach nearly $33 billion by 2025. IoT data sources include meters, drone footage, satellite imagery, LIDAR, and more. To optimize vegetation management, utilities should invest in connecting—and properly analyzing—as many data sources as possible.
4. Move to the cloud
Moving to the cloud enables utilities to handle new data sets and conduct large-scale analyses on them. With a strong engineering foundation, cloud-based tools support rapid decision making and advanced applications, both of which help utilities reduce wildfire risk faster. See how we helped a major California utility move to the cloud.
5. Create standard data science practices
To analyze IoT data efficiently and purposefully, utilities should standardize their data science practices and processes. A data science Center of Excellence (COE) could be used, but this would likely require partnership with a team outside of the vegetation management department. Questions to consider include:
- How do you conduct development? (We recommend Agile data science.)
- What tools do you use to technically produce models?
- What are your development processes?
- Which validation strategies do you use for your data and analyses?
6. Augment human effort with machine learning
Machine learning has increased the speed at which we can process and analyze data, run impact analyses and simulations, predict behavior, and more. It augments human effort to analyze millions of data points, efficiently identifying risks and predicting issues. Utilities can use diverse machine learning technologies to improve processes, including:
- enabling field technicians with computer vision products
- using risk management dashboards and forecasting for grid management
- managing satellites and remote radar
- reducing strain on utilities infrastructure for both machines and people
- prioritizing maintenance of high-risk assets
One striking example of machine learning and data science in utilities is that of vegetation management area (VMA) calendar planning. When planning how these territories are managed, utilities often create a year-long plan with standardized maintenance schedules based on location. For our clients, we’ve used machine learning tools to provide optimized maintenance schedules—refreshed monthly—that factor in real-time information to prioritize high-risk assets. Data analytics can influence utilities’ strategies, even without heavy investment into dashboards or more complicated machine learning.
7. Document tools and processes to stay ahead of regulatory changes
To avoid running afoul of new legislation and incurring costly fines, utilities should maintain thorough documentation of tools and processes. For WMP compliance, utilities are required to use data-driven methods—and report on their success throughout the year and during emergencies. Documentation ensures that all decisions are auditable, analyses are justifiable, and progress is clear. See how we helped one utility document their WMP compliance.
8. Work with experts
Change management, cloud migration, and data science implementation can be achieved alone, but the most cost-effective, long-term solution is to work with experts. For over 20 years, we’ve worked with utilities nationwide to improve safety, customer satisfaction, and financial performance. If you’re interested in optimizing your vegetation management, contact us.
Digital transformation done right
We create powerful custom tools, optimize packaged software, and provide trusted guidance to enable your teams and deliver business value that lasts.
Adam Cornille is Director of Advanced Analytics at Logic20/20. He is a data science manager and practitioner with over a decade of field experience, and has trained in development, statistics, and management practices. Adam currently heads the development of data science solutions and strategies for improving business maturity in the application of data.