In the first half of the CleanTech Talk podcast with Buzz Solutions co-founders Kaitlyn Albertoi and Vik Chaudhry, they shared their backstories in California and New Delhi, talked about the pivots in their startup, and how their transmission and distribution imaging platform is saving utilities 50% of time and effort for analysis.
In the second half of the podcast, we pivoted to the growing data volumes, types of data, and increases in continual monitoring, and the challenges that’s creating. We spend a bit of time on the machine learnings aspects, a bit of time on a recent project in Newfoundland, and end with Chaudhry and Albertoli’s perspective on what has made them successful and their advice to others.
Moving the data is a critical aspect of the solution, and it’s critical infrastructure data, so it is sensitive, requiring security and audit trails. Continuous monitoring of the grid is being mandated, with additional sensor sets including multi-spectral imaging and 3D Lidar data sets. Utilities can warehouse their data locally and use a Buzz Solutions API to process the data. Alternatively, utilities can use Buzz Solutions’ platform-as-a-service secure and encrypted storage, and manage it directly or have Buzz Solutions manage it for them.
Identification of an issue in a component is challenging. The solution has to be able to identify the asset and what’s wrong with it. In machine learning, reinforcement learning makes image recognition better. Buzz Solutions trains its neural net with base data from utilities and provides that basic model to their customers. But then customers have a human-in-the-loop model to improve their instantiation of the model. If an insulator is marked by the AI as damaged, a human can override that. The feedback is used in retraining the model to make it better over time. The models become more personalized to each utility.
The baseline model is a trunk model, with branch models supporting customers. The branch models are trained regularly, and the trunk model is less frequently updated. But differences between utilities meant that there is significant value in the branches. All improvements that are general get to all customers over time.
One of the challenges of expert-systems has traditionally been that experts don’t want to be put out of jobs. However, with the massive increase in demand, this is just dealing with massive growth of analysis. They still have to deal with concerns about automation putting people out of work. Buzz Solutions helps their customers’ employees realize it’s just another tool in the toolbox, not a replacement for a lines person or engineer.
What Buzz Solutions is seeing in the utility sector is that linespeople and engineers, once they’ve trained the model, are able to do their primary job, repairing lines and components or doing resiliency engineering. The models and algorithms just help them find the things to fix.
This actually enhances job satisfaction. The people who become linespeople self-selected for that kind of work, and they want to be out in the field. Buzz Solutions gets them out from behind the computer and working directly with the power technology. The doubling or tripling of images every year has been chaining these workers to their computers clicking through images, something that they don’t like nearly as much.
One customer had 200 linespeople and engineers doing image assessments for 8-10 hours every day, and they weren’t able to fix the identified problems quickly enough. As one example of the lag, PG&E had 3,500 outstanding maintenance tasks before the fires. Now the workers can be drawing down on the backlog of maintenance and enhancement fixes instead of looking at their computers.
Buzz Solutions assists utilities with grid resilience, reduces increases in labor costs, increases speed of identification of critical issues, and enhances employee satisfaction. Making workers happier is a counter-example for a lot of automation solutions. Buzz Solutions surveys workers at the end of the first week, first month and a few months down the road, and sees satisfaction dramatically improves as they see how much time is being saved and how their work days are improving.
This is aligned with one of the main themes of Daniel Susskind’s A World Without Work: Technology, Automation, and How We Should Respond, in that jobs aren’t disappearing, the tedious, repeatable portions of them are. Not everyone will be in favor of that, but a large percentage of people will be doing more rewarding work and being more productive than ever. As this case study shows, with increasing automation comes massively increasing work effort in many cases, and so automation can take over the highly repetitive portions of the effort.
Chaudhry points out the parallels with the inventions of steam engines, electricity, and the first waves of computerization. For every job that went away, other jobs were created. Jobs usually got better, not worse.
Buzz Solutions has testimonials from customers who started out anxious and ended up with positive reviews about much better results. Among other things, the system automatically connects to utilities’ work order systems, automatically creating word orders, another efficiency that’s boring to do manually.
Our conversation actually sprung up because Buzz Solution’s PR agency reached out to me based on the results they had in the Canadian province of Newfoundland. The Electric Power Research Institute (EPRI), a non-profit global independent energy R&D organization founded in 1972, had Buzz Solutions in its incubation lab. It includes a 3-month project with a utility. Buzz Solutions had originally been connected with the Newfoundland utility through AltoMaxx, a drone-services innovator based in Newfoundland working in construction, real estate, and utilities. AltoMaxx does a lot of power inspection services of its transmission and distribution infrastructure. The company had connected with Buzz Solutions at the end of 2021, wanting analysis services. A small pilot project with AltoMaxx and Newfoundland Power has turned into a larger engagement.
For those unfamiliar with Newfoundland, it’s a vast, very sparsely populated, steep, and forested part of Canada. And it has a massive hydroelectric facility at Muskrat Falls that ships electricity to the US using HVDC transmission. The power infrastructure is much bigger than one would expect. The joke is that there’s one transmission pole per person in the province. The terrain makes it very difficult to get to the infrastructure to inspect it, and drones have made it much easier. The province also has extreme weather, including massive snowfalls, testing the Buzz Solutions platform to its limits, giving assurance to all of its clients that it’s robust.
Buzz Solutions is working with New York Power Authority, having discussions with PG&E, and is in conversations with many other utilities. Its coverage crosses the continent geographically, from Texas to Newfoundland and California to New York, and it has international clients now as well. Buzz Solutions works with utility aviation, vegetation management, transmission, distribution, and inspection teams. It also does a lot of work with drone and helicopter inspection service providers which provide services to the utilities.
Buzz Solutions is doing a lot with its 11 employees, but is actively hiring, aiming for over 50% growth in staff in the near term. The company has strong revenue numbers and is in the black, although privately held still so holding that close to their chests. It is a cleantech startup success story.
Chaudhry says that part of their success was spending a lot of time learning the utilities’ business model. Utilities are an industry undergoing massive change. His guidance is to be patient. Things move slowly, but when they move, they make a major impact. He referred to the latest IPCC report which pointed out the grave consequences of not decarbonizing. He advises people to get invested and engage in this renewables and cleantech, find problems to solve, and that there is a cleantech community to support startups.
Albertoli says it’s great to wake up every day and make an impact in a fundamental part of our economy. In addition to patience, she leans on feedback from their customers, listening to several customers and major players to refine their product to help keep Buzz Solutions on the cutting edge of innovation. She feels being passionate about what you are doing, and continually reminding yourself on why you are doing what you do.
I don't like paywalls. You don't like paywalls. Who likes paywalls? Here at CleanTechnica, we implemented a limited paywall for a while, but it always felt wrong — and it was always tough to decide what we should put behind there. In theory, your most exclusive and best content goes behind a paywall. But then fewer people read it! We just don't like paywalls, and so we've decided to ditch ours. Unfortunately, the media business is still a tough, cut-throat business with tiny margins. It's a never-ending Olympic challenge to stay above water or even perhaps — gasp — grow. So ...
Sign up for daily news updates from CleanTechnica on email. Or follow us on Google News!
Have a tip for CleanTechnica, want to advertise, or want to suggest a guest for our CleanTech Talk podcast? Contact us here.