Blog: Immediate Grid Forecasting: An Imminent Revolution In How Utilities Prevent Disasters
Wildfires and the utility sector have a dangerous relationship. Not only do wildfires pose a threat to reliable electricity service, but as climate change paves the way for high winds, storm surges, hurricanes, droughts, and flooding, utility companies need reliable solutions to protect their infrastructure from causing wildfires.
We don’t have to look far to see how disasters like wildfires can wreak havoc on our lives. Just this fall, we’ve seen smoke from California wildfires turn the sky orange, over 4 million acres of land affected and 8,400 buildings destroyed. It’s truly devastating.
While not all disasters like wildfires begin the same way, failed utility infrastructure has increasingly become a major culprit. Failed utility equipment was the cause of 17 major California fires in 2017 alone and led to the Camp Fire of 2018 that killed 85 and destroyed nearly 20,000 structures.
But we can’t place all the blame on utility companies for this. With thousands of miles of power lines, being able to locate compromised equipment is key to preventing these fires.
One main issue here of course is wind, which jostles and loosens electric lines, sending sparking electrical current down onto dry and drought-ridden plant life below. Understanding the health of our electrical grid can play a crucial role in preventing disasters—if we can catch issues and perform necessary repairs predictively.
Grid forecasting and preventative maintenance centers around one idea: That companies can more effectively deploy their maintenance services and prevent potential disasters by proactively identifying and resolving issues with aging infrastructure before it leads to a larger problem.
Faults and failures are predicted based on years of structured data regarding the make, model, and warranty details of the utility company’s products, as well as unstructured data like maintenance history and repair logs.
Additionally, information gathered using on-site sensors can provide actionable insights that can help pinpoint exact areas that need maintenance. These crucial data points can enable utilities to forecast when functional equipment may fail and perform maintenance before these failures occur and cause a disaster.
Using artificial intelligence (AI) at the edge and on the cloud, grid forecasting algorithms can take data from hundreds of thousands of miles of deteriorating equipment, to help locate where maintenance needs to be done. Why does this matter?
According to T&D World, U.S. utilities typically have one component every 7.2 miles of overhead electricity lines that is deteriorated and needs repair. This may not seem like that big of a deal, but when you factor in that there are typically around 140-150 poles per 7.2 miles, each with 6 to 10 components, that means there is one point of risk for approximately every 1000 components. Locating that without the aid of a predictive maintenance solution is like trying to find a needle in a haystack—before the haystack catches fire!
Predictive maintenance can potentially narrow those 140 to 150 utility poles to 1 or 2, and then narrow it down even further to the components that need repair. This can not only prevent outages but catastrophic disasters like the wildfires in the west.
What makes grid forecasting a viable solution to mitigating potential disasters is predictive analytics and AI at the edge—all reporting back to an easy-to-manage SaaS solution.
As Rock Health said in a report, “The goal of predictive analytics in any field is to reliably predict the unknown.” Across industries, predictive analytics is using the power of big data analytics to deliver more accurate forecasts for all kinds of things. This is true in the medical field, as well as other industries like freight-forwarding and supply chain management, retail, manufacturing, education, transportation, agriculture, and oil, and in the financial realm as well, and has major implications for the utility sector, where predicting an outage can mean preventing a disaster.
Predictive maintenance and analytics are one of the leading use cases for the Internet of Things (IoT) industry at the edge. Using edge-AI, data from sensors is analyzed and processed on-site in milliseconds. It’s much faster than centralized IoT models, and offers greater security as well, as there is less risk of hacked or tampered data during transit.
For grid forecasting, this means that with edge-AI algorithms, data is generated on the device to produce real-time insights about which components need maintenance. This empowers utility companies to do a few things:
Wildfires and the utility sector have a dangerous relationship. Not only do wildfires pose a threat to reliable electricity service, but as climate change paves the way for high winds, storm surges, hurricanes, droughts, and flooding, utility companies need reliable solutions to protect their infrastructure from causing wildfires.
Our world entirely depends on the reliability of utilities. Outages and failed components can lead to major disasters that have consequences on our environment, our economy, and our communities. Through features that include failure prediction, fault diagnosis, failure-type classification, and maintenance recommendations, Gridware can not only streamline and simplify your maintenance procedures but also reduce the risk of raging fires like those we’ve seen throughout 2020. You’ll also see:
Grid forecasting is the future of disaster prevention for the utilities industry. Want to get in on the ground floor? We’re currently accepting partners for our beta program, and we’d love to chat. Schedule a meeting to join our beta test group today.
