Follow Datanami:
March 9, 2015

A Virtual Reality Lens for Big Data Visualization

Alex Woodie

Visualization tools such as Tableau and QlikView have become indispensable for exploring and identifying trends hidden within data. But now a company called Space-Time Insight is taking big data visualizations to a new level with an Oculus Rift virtual reality headset.

Space-Time Insight is a Silicon Valley firm that helps public utilities, logistics companies, oil and gas firms, and federal agencies utilize their field assets–like electric grids, delivery truck fleets, and drilling rigs–in more effective and efficient manners. The company’s motto–“Situation intelligence for the Internet of things”—gives you a small inkling of what it does.

The company’s flagship product, called the Situation Intelligence (SI) Server, can make sense of large sets of data that have spatial and temporal aspects to them. The software helps users detect anomalies hidden in the data, such as voltage spikes occurring on the grid or a smart water meter that’s failing to phone home, and correlate it with other factors, such as the maintenance history of an asset or the billing history of a customer.

In addition to running predictive models, the software displays the results of its analyses on interactive maps, such as Google Earth or Esri products. It powers and serves the massive, real-time visualizations you see displayed on the operations center walls of electric grid operators, such as California’s Independent System Operator (ISO) in Folsom (an actual customer).

Space_Time_4

SI Server powers the situation awareness of field operations for large organizations.

It’s all about turning big data into small data that can be digested by individuals, says Steve Ehrlich, the company’s senior vice president of marketing and product management.

“We’re pulling all of that data together, processing it in memory, and dealing with large volumes of data very frequently, and deciding based on analytics, what to present to the user,” he tells Datanami. “It’s really about pulling all the information together for the user. Because otherwise they’re just making decisions based on isolated or limited knowledge about what’s going on.”

SI Server lets decision makers see as much of the data as they need, or as little. “We’re trying to help the user understand ‘This needs attention’ or ‘You need to look at that because it’s going to fail’ or ‘Hey there’s a storm coming. Here’s where you should place your crews in advanced of that storm,'” he says. “So we help the user identify, out of the mountain of big data, the key pieces of information, either pure data points or quite often an analysis of the data, that they have to pay attention to.”

Space-Time Insight has a collection of R and Python-based algorithms and the domain expertise to help customers predict how certain events may unfold, such as how a brushfire may impact the section of electric the grid managed by Southern California Edison (a real customer) electric grid or how traffic patterns affect delivery times for FedEx (also a Space-Time user). The data sources, such as satellite imagery for brushfires or real-time traffic information from Google, are critical to making good analysis and driving good decision-making.

Space_Time_logoGetting the data to play nicely together can be difficult, and you could say that’s Space-Time’s specialty. “It’s hard to correlate wind and weather and unstructured data like that with data in enterprise systems,” Ehrlich says. “We’re very good at analyzing data spatially, understanding what’s nearby, and analyzing it temporally–or what happened in the past, what’s happening now, and what’s going to happen in in the future.”

Customers routinely ask SI Server to crunch and correlate data across 30 or more sources. Sometimes it works well, and sometimes it doesn’t, Ehrlich says. Most of the time, it comes down to the quality of the data. The problem is, the quality is only so good in some classes of data.

“When it comes to things that can be well-understood, like asset behavior, the models are really good,” Ehrlich says. “But when you have things like the weather, that’s a different story altogether, because nobody’s being successful in predicting the weather…We certainly incorporate [the weather] into our analyses, but we also give users a confidence score.”

Having a good visualization is critical to what Space-Time Insights does. That’s why it was so interesting to see what the company did when it got its hands on a pre-production set of Oculus Rift’s VR headset.

Space Time_3

Space-Time’s VR app lets users see real-time data generated by an electrical transformer.

The company demonstrated a VR visualization on the Oculus Rift headset at a recent industry conference in San Diego. The attendees were taken aback by the experience, which involved a user walking through an electric substation and inspecting a failing electrical transformer. Information pulled from the transformer was displayed in the VR headset, providing a new level of interactivity.

“People were stunned at that kind of experience,” Ehrlich says. “When you’re looking at stuff on a screen, and it’s a complex problem, you have to click through so many screens to really get to the root cause of a problem. Whereas if I can walk up to it [through the VR experience] and see if there’s smoke or gas coming out of it, I immediately know what the problem is.”

Space-Time foresees the VR visualization being used in several scenarios. It could be very useful for training purposes, Ehrlich says. “The ability to take somebody inside a substation to see what the assets look like and what kind of data they generate can be a huge advantage,” he says. It could also be used for real-time troubleshooting, such as an airline engineer on the ground collaborating with a pilot in the air to identify a failing component on an airplane.

If this is any indication of where the combination of big data, advanced analytics, and visualization is going, we’re about to go on a wild ride, indeed.

“The visualization tools of five or 10 years ago weren’t designed for this volume of data, so we’re looking at new ways, like virtual reality and gaming technology, to deal with the volume and variety of data out there,” Ehrlich says. “There’s many implication of this kind of technology in a big data world. The Internet of Things is coming to life.”

Related Items:

The Secret to Generating Value from IoT Data

A New Model for Big Energy Data

Space-Time Aims to Make the Grid Smarter

 

Do NOT follow this link or you will be banned from the site!
Share This