Strata Hadoop World 2016 Recap

GridCure was honored to present a 40 minute talk entitled “Using the Explosion of Data in the Utility Industry to Prevent Explosions in Utility Infrastructure” at Strata + Hadoop World in New York City.  The conference, which was held in the Javits Convention Center, is one of the largest big data conferences in the world and brings together thousands of experts from academia, government, and industry.

I was excited to have a chance to talk about the rapidly expanding opportunities to analyze big data in the utility industry. Before the advent of the smart grid, utilities analyzed meter data by manually taking readings once per month. Currently, the amount of smart grid data recorded annually in the US can be measured in petabytes. Making full use of this data will require innovative thinking from the big data community, so Strata was a very appropriate venue to highlight some of the future challenges the industry faces.

Key takeaways:

  • The number of outages in the US is increasing partially due to aging infrastructure.
  • New preventative maintenance procedures have the potential to make equipment maintenance vastly more efficient, saving both the utilities and customers money.
  • Smart grid data can be used to automatically keep a detailed history of major and minor events that have occurred in the lifetime of a piece of equipment.
  • As demonstrated by GridCure’s feeder cable maintenance predictive model, the use of smart grid data can greatly enhance the ability to predict equipment failures.

If you would like to learn more about GridCure’s preventative maintenance modules, please contact us here

Smart Grid Analytics for Cooperatively-Owned Utilities

GridCure loves cooperatively owned utilities (Co-ops).

We’ve previously talked on this blog about where the idea and industry need for GridCure comes from, and we see the Co-op space as particularly underserved when it comes to tools and technologies.  Bringing the most valuable aspects of cloud computing and SAAS software to the utility industry, GridCure can deploy more quickly and cheaply than existing providers, dramatically shortening the time to deliver value to our clients.

So, GridCure. Why Co-ops?

Co-ops are, by definition, are value driven organizations with deep ties to their communities.  Roughly half the United States is powered by Co-op utilities, and many of these are the more rural areas where our food is grown and our products are made.  If you’ve ever driven outside a metropolis area to get ‘out into the country’, you’ve probably been in Co-op territory.  

Co-ops are innovative.  Due to their often rural nature, Co-ops often have a low density of customers (often tracked as ‘customers per mile’ of distribution line), with the result that sometimes there’s a Farmer Betty who might be the only house on many miles of line.  This makes the economic return of erecting the poles, wires, and transformers out to Farmer Betty a difficult square to circle.  

To solve this kind of issue, Co-ops have lead the charge on many renewable energy projects to help maintain the levels of reliability and to service their far-flung networks.  By placing a generating asset like a solar panel or wind turbine closer to Farmer Betty and removing the need to deploy as much equipment, Co-ops not only serve their community (making Farmer Betty happy) and improve their organization by lowering costs, but also help the world by generating cleaner energy.

Co-ops have a changing workforce.  The next few years are going to see many senior executives and holders of irreplaceable institutional knowledge retire and a new generation of employees step into their places.  For both Co-ops, as well as our work at GridCure, this represents an opportunity to retain and automate much of this precious institutional knowledge through analytics and present it to the incoming generation using updated and modern user interfaces.

So, Co-ops. Why GridCure?

We’re utility engineers. We understand the utility workflow, and we’ve built the tools we would want to use ourselves on the front lines.  GridCure’s products all have beautifully designed apps and interfaces built responsively for use on desktop, tablet, or mobile device, and each analytical module on the platform has feature sets that solve specific engineering challenges for your network so you get exactly the analytical solution you need without the bloat.  On top of that, your data is likely far more valuable than you expect.  For most of GridCure’s offerings, clients already collect the information we need: no new sensors and no new servers required.

We’re designed to be modular.  Each module is designed to address a specific problem on the network, and a Co-op may choose to use one, three, ten, or any number of modules once signed up for the platform.  This allows Co-ops to pick and choose exactly what they need, and customize solutions to their grids’ very specific challenges.  

We’re a Software-as-a-Service (SaaS) solution.  With simple, transparent, pay-as-you-go pricing, as well customizable levels of support, GridCure brings the ease of SaaS into the utility sector.  We want our Co-op clients to love our products and continue to use them year after year because they get such unbelievable value from them, not because they’re locked up in an unbreakable contract.

We love Co-ops so much, we recently launched a Co-op utility specific beta program.  Interested?

Sign up for more information and a free account on the GridCure platform

The Roadshow Continues - Come Find Us At Strata

GridCure is on the road again! Our very own Head of Analytics, Dr. Kim Montgomery, was selected to speak at the renowned Strata + Hadoop World conference in New York City this coming Thursday, September 29. Strata + Hadoop World is where big data's most influential business decision makers, strategists, architects, developers, and analysts gather to shape the future of their businesses and technologies - and Kim will be leading the charge with her presentation!

Her session, titled Using the Explosion of Data in the Utility Industry to Prevent Explosions in Utility Infrastructure, is about the ways in which big data tools are advancing the practice of preventative maintenance in the utility industry. Read her abstract below:

The electrical utility industry, an industry accustomed to gathering customer usage data on a monthly basis, now has access to a regular stream of data from smart meters and other smart sensors.  Analyzing these new streams of data has given utilities the opportunity to understand their customer usage patterns, perform preventative maintenance,  detect fraud, exercise demand management, and allocate resources more effectively.

Outages can cost US businesses up to 150 billion dollars per year.  Due to aging infrastructure, the number of outages in the US has increased 285% since 1984.  Utilities need improved data driven methods for determining which infrastructure is most critically in need of replacement.  Improving maintenance procedures for key pieces of equipment such as transformers, feeder cables, and reclosers can substantially reduce the risk of an outage.  We will discuss ways in which analysis of smart grid sensor data can lead to better methods for replacing equipment before catastrophic failures occur.

If you happen to be at the conference, we’d love to pick your brain. Schedule a one-on-one with Kim using this link!

Interested in learning more about what we're up to?  Contact us here!

Predicting the Unpredictable (Part 2)

Animals and Vegetation

Some of the most common causes of power outages include vegetation and animals interfering with electrical equipment. Problems caused by vegetation include trees or tree limbs falling on power lines and roots growing into feeder cables. Squirrels, birds, snakes and other animals interacting with power lines, transformers, or other equipment can also easily cause an outage.

Predicting where problems with vegetation and animals are likely to occur is not as daunting as it may sound.  Vegetation interference can be detected both through smart readings, image analysis, and past maintenance records. The same image recognition technology that is driving the development of self-driving cars can be used to recognize trees in satellite and other images, giving an indication of where vegetation may be near an aerial line. Changes in power and voltage along a power line may also indicate that vegetation is becoming a problem. Also, maintenance records contain valuable information about where vegetation has been a problem in the past. All of this information can be integrated to predict areas of the network which may be prone to problems.

The computer vision technology allowing automated detection of objects such as trees in images is well developed. Since 2012, the problem of automatic image recognition has been attacked most successfully by one type of algorithm, convolutional neural networks. The imagenet competition illustrates how revolutionary the technique of convolutional neural networks was for the field of computer vision. The annual contest involves taking a set of images, classifying the object in the images into 1000 classes, and drawing a box around the classified item. In 2010 and 2011, before the advent of convolutional neural networks, the winning entries had misclassification error rates of 28.2 percent and 25.8 percent respectively. In 2012, a group from the University of Toronto won with an error rate of only 16.4 percent, crushing the efforts of the other teams. The method used to win the competition, a convolutional neural network, has become the standard method for attacking image recognition problems.

Further refinements of convolutional neural networks over the past 4 years have yielded increased accuracy. In this year’s imagenet competition, Microsoft research used a 150 layer neural network to classify a set of 100,000 images with an error rate of less than 3.5 %. Computer vision technology has been used by driverless vehicles to identify pedestrians, other vehicles, and signs quickly and accurately. It has been used for medical applications such as automatically detecting tumors in x-rays or the development of retinopathy from an eye exam photo. By applying computer vision to satellite and street-level images and comparing them with smart sensor readings from the same area, regions of potential interference of tree branches with aerial lines can be identified before major problems occur.

Animal interference with power lines and other electrical equipment is another common cause for power outages. At first, it may seem difficult to predict something as random as a squirrel jumping onto the aerial lines. However, there are things that can be done to predict the probability of animal interference in different areas. The problem is closely correlated with vegetation in the area.  Mathematical models exist for predicting the density of animals such as squirrels given the distribution and type of vegetation in an area.1 Pratter et. al formulated a multiple regression model indicating a relationship between forest density and squirrel density for a squirrel population in Arizona. The model, based on various measures of forest cover accounted for 89% of the variation in squirrel density over the region. Similar models of tree cover and types of vegetation in a region could predict the density of squirrels in the region.  Combining that information with information about past instances of squirrel interference and locations where squirrel guards have been installed could be used as a preventative measure.

In order to integrate the diverse information involved in predicting an outage, it’s necessary to combine data from multiple sources including sensor readings, weather data, maintenance records, and satellite imagery. GridCure is leading the way in data integration and predictive modeling solutions allowing utilities to access, visualize, and understand their data with a single easy-to-use interface. Our predictive modeling modules make sophisticated use of disparate data to answer a diverse range of questions; each module answers a specific question or group of related questions, and we’re able to stack our modules on top of one another allowing for a customizable and flexible solution. We currently offer several asset health predictive maintenance modules, as well as anomaly detection and technical and nontechnical loss modules. Always looking to expand our product offering to encompass the most pressing utility needs, we're very interested in developing a vegetation module to address the many outages caused by animal and vegetation interference.

Interested in learning more about what we're up to?  Sign up for our newsletter here!


1 “Landscape Models to Predict the Influence of Forest Structure on Tassel-Eared Squirrel Populations” John W. Prather, Norris L. Dodd, Brett G. Dickson, Haydee M. Hampton, Yaguang Xu, Ethan Aumack, Thomas D. Sisk, Journal of Wildlife Management, 7(03) (June 2006) pp. 723-731.

GridCure Hosts Panel at IEEE ISGT

Thank you, Minneapolis!  

GridCure recently hosted a panel at the global IEEE ISGT conference on the topic of ‘Distibuted Energy Resources in Unique Markets’. Bringing together speakers from Enernex, Solar City, and GridCure’s own experience, the panelists shared their thoughts, anecdotes, and predictions on distributed energy around the world.  

While many distributed energy resource (DER) related conversations and conferences discuss the more common technologies and funding processes, we wanted to explore the interesting and unique: what are some of the projects the audience wouldn’t have heard of?  What are the cultural pressures that changed how this project was implemented?  

Key takeaways and learnings from the sessions included:

  • A discussion on the regulatory ‘push’ and consumer ‘pull’ for many DER projects, and how the onus is on the regulatory body of a given area to understand the direction of their consumers want to go.  The panel discussed specific projects and areas that had successfully conducted this kind of consumer interaction to drive regulatory changes, and how one of the most successful practices was to ensure that feedback was always heard from a new voice: it is too easy and too common for a particularly vocal group or organization to dominate these discussions.
  • Cultural considerations are critical.  The impact of a DER program in many parts of the world relies strongly on the support of the local community, and when this community hasn’t been engaged properly the project ultimately fails.  The panel shared specific stories regarding how improperly engaged communities resort to stealing electricity or equipment, or how systems would fall into disrepair if the community did not feel enough ownership over its maintenance.
  • We’re in for an exciting couple of years in terms of technology.  The panel and audience in particular spoke to smart-inverter technologies, the increased ability to automate decisions on the electrical network through data, and the ever-increasing energy conversion efficiencies.  

Our thanks from the whole GridCure team to the panelists, IEEE and DoE organizing team, and the wonderful audience for the panel!

Outages: Predicting the Unpredictable (Part 1: Preventative maintenance)

Both the duration and frequency of power outage events has increased markedly over the last decade.  Due to aging infrastructure, the US has more outages than any industrialized country. Climate change and increased demand for electricity have increased the pressure on an already stressed system.  With each outage costing millions of dollars, any preventative measures that might protect against an outage could save utilities and businesses considerable financial strain.

In order to prevent outages, it would be logical to start by analyzing their causes.  A quick glance at recent news gives an overview of some common causes of outages.

Equipment failures:

Equipment failures due to age or overuse can lead to disruption of service in large portions of the network.

Transformer failure in Colorado

An electrical transformer went out causing a major outage in Glenwood Springs, CO.

Underground cable explosion

An underground feeder cable explosion and fire caused electricity to be cut off to a quarter of downtown St. Louis.

Broken electrical pole

A broken electrical pole in New Brunswick caused loss of power to 15,000 people.



Snakes in South Carolina

A snake interfering with substation equipment caused 15,000 people to lose power in South Carolina.  

Monkeys in Kenya

A similar event involving a monkey caused an outage throughout Kenya.  

A Bird in Texas

A bird cause a brief power loss in Texas.

Squirrels Almost Everywhere

@cybersquirrel1 created a map of animal related disruptions.


Weather-related events:

Storms, ice, and lightning strikes can lead to equipment failure and blackouts.

Lightning strikes in Wyoming

A lightning strike left more than 9000 customers without power in Wyoming.


Human activity:

Construction, car accidents, and other human activities can also disrupt the electrical system.

Car accident in Virginia

An outage was caused when a van struck an electrical pole in Virginia.

A protest causes an electrical shutdown in California

A protester climbing an electrical pole caused an outage in California.



Tree limbs falling on aerial lines or roots growing into feeder cables are common causes of equipment failures.

A tree downs an aerial cable in Canada

A limb hitting an aerial line caused a widespread outage in Saskatchewan.


To tackle the problem of predicting and ultimately preventing outages, it is necessary to consider the extent to which the major causes for an outage are predictable.   The failure of a piece of equipment which has had past maintenance issues might be highly predictable, while a lightning bolt striking a new transformer might not be.  In this first instalment, we’ll look at the problem of predicting mechanical failures.  

Traditional power utility maintenance systems frequently rely on a run to failure system in which equipment is replaced only after a failure occurs.  In cases in which allowing equipment to fail is not desirable, scheduling equipment replacement based on age is a common method.  However, age-based replacement is far from an ideal solution as it may lead to the replacement of expensive equipment that still has decades of life left while doing little to limit catastrophic failures.  The goal of GridCure’s preventative maintenance program is to provide a more sophisticated diagnosis of which equipment is likely to fail so that maintenance and replacement efforts can focus on the equipment that is in need of replacement.

In some cases, machine learning can be used to augment existing maintenance procedures.

One of the most expensive and critical pieces of equipment in the electrical system are large power  transformers at electrical substations, which can weigh up to 400 tons and cost millions of dollars.  Substation transformers perform the role of stepping the voltage of an incoming line up or down.  A transformer malfunction can be a catastrophic event involving explosions or fires and damage to surrounding transformer equipment. Because of the safety issues that a malfunctioning transformer can cause, it is desirable to repair or replace transformers before a failure actually occurs.

Transformer malfunction is generally detected using dissolved gas analysis. Large transformers contain oil, which serves as a cooling agent.  Electrical discharge events or overheating cause various chemical reactions in the insulation and oil.   There are a number of criterion for analyzing the concentration of various gasses in the oil and ratios of concentrations of gases in the oil in order to assess the health of the transformer.  One of the most commonly used is Duval’s triangle, a method for comparing the concentration of methane, ethane, and acetylene to classify what type of fault has occurred.

Duval’s triangle and similar methods are useful in determining whether a transformer has already undergone a fault, but the method can be unreliable near the boundaries of the graph, and may not catch a fault in the early stages.  Also, it is a fairly simple method that doesn’t take into account other features such as the progression of the readings over time, the load that the transformer has experienced, or the maintenance history of  the transformer.  It would be desirable to develop more sophisticated methods for determining whether a transformer is likely to fail.

The simplest way statistically to determine which transformer is most likely to fail would be to find a large number of transformers of the same age, brand, DGA results and level of wear and tear.  Of course, in reality, finding a large number of transformers that are qualitatively the same would be quite difficult.  It’s likely that one wouldn’t find enough “similar transformers” to get good statistics.  Instead of looking for transformers that are exactly the same in all qualities, it makes sense to think about what features of the transformer are most important.  Which transformers should be in a comparison group? Transformers of the same age? Transformers of the same brand? Transformers with the same usage level?  One fairly simple way to determine which features are most important is using  a decision tree such as the one below.  For the transformer fault problem, a decision tree could be used to repeatedly find the variable most useful in separating groups of transformers that are more likely to fail from transformers that are less likely to fail.  It does this by minimizing a loss function at each split.  In the below diagram the best criterion for grouping similar transformers is age and brand, but more complicated decision trees could take into account many factors.  The tree can be read by following the decisions from root to the bottom leaf.  A transformer less than 25 years old with more than would have a probability of failure of approximately 679/2679 or 25.3%, while a transformer that was more than 25 years old and had brand A would have an approximate failure rate of 179/291 or 61.5%.


Decision trees are simple to understand, but there are other methods that give better results in practice.  Random forest and gradient boosting machines are different methods of combining large numbers of decision trees to create more complicated probability predictions.  Other methods like neural networks and support vector machines can be used to create more complicated nonlinear combinations of variables as a criterion for failure, which are likely to produce better results than more simple linear rules of thumb such as Duval’s triangle.

Using a variety of machine learning methods learning methods, GridCure is developing sophisticated methods for combining all information about transformer and other pieces of key equipment to determine which equipment may be approaching a failure well before a dangerous situation occurs.

GridCure Launches Its New Beta Platform at Start ETS!

GridCure is incredibly pleased to be launching a new Beta platform for cooperative and municipal utilities. The first demonstrations will be given at the start@ETS conference in Austin, TX, where the team was selected to present as one of five promising young companies in the energy space.

With GridCure’s new platform clients are able to easily create accounts and review the preventative maintenance, reliability, and loss-related analytical modules. Specifically geared toward the data analysis and technical needs of smaller utilities, key features include:

  • Simple data ingestion - consolidating data from disparate systems has never been easier
  • Transparent pricing - software-as-a-service pricing to ensure clients purchase a correctly-sized system
  • Speed - integration with the GridCure platform in a matter of weeks, not years like traditional vendors
  • Customizability - GridCure will work with you to understand and meet needs specific to your utility

Sign up for a free demo and reserve your place in the Beta program here!

Take Our Survey

We’re building a smart grid data analytics platform and would love your feedback. This survey will only take a few minutes, and you could win a $200 gift card!

As we bring our new platform and products to market, we’re excited to share what we’re working on, and eager to learn about the unique problems your utility is trying to solve.

We’ve put together a few questions, and we are looking forward to hearing your thoughts.

To show our appreciation, the first 100 survey participants will be entered into a raffle to win the following prizes:

- (1) $200 Gift Card at any of the following stores: Cabelas, Bass Pro Shops, REI, or Amazon

- (1) $100 Gift Card at any of the following stores: Cabelas, Bass Pro Shops, REI, or Amazon

- (5) Conductive Ink Pen

Participants who enter will also receive early access to demo our Alpha Platform, and qualified utilities can receive access to special Alpha Pricing. If you have any questions, feel free to contact

*By entering the raffle, you agree to be contacted by someone from our team.

**We will not sell or disclose your information to any 3rd parties


GridCure Hits the Road

GridCure has been securing our foothold as industry experts and have been invited to present at well-renowned conferences around the globe. We’re currently kicking off our North American tour, and we’ll be hitting a number of cities along our journey.

Join us on the road or email us to schedule a personal demo:

September 09, Minneapolis - IEEE Innovative Smart Grid Technologies:

The IEEE Innovative Smart Grid Technologies Conference will be a forum for the participants to discuss issues and effective strategies for grid modernization given the changing electric industry landscape due to the advent of information and communication technology and the emergence of renewable and distributed energy resources. GridCure has been selected to moderate a panel about distributed energy resource strategy and implementation across unique markets.

September 14, Austin - start@ETS:

start@ETS is a fast-paced day around tech and energy to push knowledge exchange for startups, entrepreneurs, executives, and influencers. GridCure will pitch our solution as part of the Startup Competition presented by Direct Energy.

September 29, New York - Strata + Hadoop World:

Strata + Hadoop World is where big data's most influential business decision makers, strategists, architects, developers, and analysts gather to shape the future of their businesses and technologies. Our Head of Analytics, Dr. Kimberly Montgomery, will discuss ways in which big data tools are advancing the practice of preventative maintenance in the utility industry in her session titled, Using the Explosion of Data in the Utility Industry to Prevent Explosions in Utility Infrastructure.

October 30 - November 1, Palm Beach - Rural Smart Grid Summit:

The Rural Smart Grid Summit is a unique and highly interactive event for utility executives seeking the latest industry research, regulatory news, standards, and cutting edge technology. GridCure is a participating sponsor and will be hosting several intimate boardroom sessions.

December 13 - December 15, Orlando - Renewable Energy World International:

Renewable Energy World International (formerly Renewable Energy World Conference & Expo North America) has a proven track record as renewable energy’s leading conference. GridCure has been selected to present our abstract, The Innovation of Jordan’s Grid - The Macroeconomic Impact of a Distributed and Renewable Energy Strategy and the Analytics that Drive It.


Needless to say, it’ll be an exciting few weeks… and we’re just getting started!

Interested in learning more about what we're up to?  Contact us here!

Hello, We're GridCure

Hi, I’m Tagg. I’m the founder of GridCure, a smart grid analytics company focused on bringing simplicity of design, transparency in pricing, and fast time-to-value to smart grid software. 

I started GridCure because I saw first-hand how the available toolset wasn't capable of handling the explosion in smart grid data.  Utility engineers, IT departments, and planning departments are challenged by multiple disparate systems, tool sets, applications.

My first insight into the software that would eventually become GridCure was with Simpa Networks in Bangalore, India.  We built and delivered small solar home systems using innovative mobile-billing technology to meter the power used, delivering across Northern and Central-Southern India, dealing with transacting and analyzing data passed primarily over the cell network.

Eventually having eaten my fill of dhosa, I subsequently was part of the smart meter rollout for a large Canadian utility, deploying cutting-edge systems that were the main component of the business case for the project.  Access to top-tier engineers, subject matter experts, and internationally-recognized software firms gave a deep understanding of how smart grid systems in general are revolutionizing energy networks around the world.

What a smarter grid means for a utility:

  • A smart grid deployment - be it smart meters, a better communicating SCADA system, or any other communicating device - means the local utility has somewhere between 1000 and 100,000 times more data being generated by their network every day.
  • At a minimum, this means upgrading servers to store this data.  More than likely, it means traditional business intelligence tools don’t work any more.  Copy-pasting a terabyte of smart meter data into Excel is going to cause your laptop to melt.  Almost assuredly - and confirmed by the dozens of sessions at utility conferences over the past few years addressing this exact topic - it means there is an ever-growing big data and data science skill gap in the industry.
  • So what *does* the industry look like today?  We’ve got dozens of different walled gardens and proprietary communication protocols, obscure pricing with burdensome service contracts, overbuilt systems that require a complete IT overhaul, and user interfaces that make IBM green screens look elegant.  

That’s where the idea of GridCure was born.  Using lessons learned from leading utilities - check out the wonderful Duke Data Mining Analytics Initiative - we are building big data analytical tools, designed beautifully, that work with existing data stores and are priced both transparently and reasonably.

GridCure provides software-as-a-service (SAAS) analytics to utilities to help improve reliability, increase efficiency, and boost revenue throughout the smart grid lifecycle. Focused on utility-internal solutions like predictive maintenance, loss identification, and asset planning, GridCure has worked with utilities around the globe.

We’re on a mission to bring most valuable aspects of cloud computing and SAAS to the utility industry.  The team can get your utility set up on the platform in seconds, deploy analytical module in a matter of weeks, and demonstrate the return on investment with the data you already have on-hand.

We’re always looking for forward-thinking utilities to work with, amazing individuals to join our growing team, and industry partners who would like to share in our plans to transform the utility industry.  Drop us a line, and come see us speak at IEEE ISGT and Strata Hadoop in the fall.