"Appifying" the utility enterprise
- January 18, 2016
- 700 views
Thousands of intelligent endpoints have created exponential growth in the amount of analytical data that utilities are attempting to make sense of to improve grid reliability, increase efficiency and provide superior customer service. In addition, utilities have to evaluate the operational and cost impact of demand reduction programs, renewable energy integration, regulatory changes, and consumer behavior.
Where once utilities only had to respond to operational data in structured format (databases) that resided in such disparate systems as SCADA EMS, DMS, CIS, etc., the intelligent grid concept forces Utilities to break the barriers of these data silos, and integrate this structured data with unstructured data in such places as the internet, social media, news and weather. They also need to tap into their organization’s tribal knowledge in the unstructured form of reports, emails, evaluations, presentations, and observations.
Even with the advent of big data, the integration of all this structured and unstructured data would appear to be a monumental achievement with the database management and analytical tools the industry has come to rely on. Complicating the challenge is the aging utility workforce that will retire much of the expertise required to query this data in such a way that it will provide meaningful, actionable information.
Even if we could somehow blend this data, would we then need thousands of canned reports, or a highly trained data analytics expert in every operating department to make use of it? Perhaps the better answer is staring back at us from our smart phones.
“Waze-like” apps across energy/utility IT & OT systems
We as consumers are no strangers to the union of the structured and unstructured datasets. A commuter, for example, used to rely on Google maps to get from his office to home. But with the advent of apps like “Waze,” not only can he get directions and arrival times based on mileage and speed data, but can also combine this intelligence with feeds from on social media and crowd-sourced opinions on traffic congestion.
While utilities are quickly discovering the value of apps they provide their customers to modify behavior and improve customer loyalty, few have embraced the use of apps to improve their own operational efficiency and risk management. Significant advances in the power of in-memory processing, machine learning, artificial intelligence, and natural language processing have the potential to blend millions of data points from tribal knowledge, operational systems, and the Internet of Things -- using apps no more complicated than Google Maps.
Imagine an app that can blend grid management data with renewable asset intermittency data and weather reports by invoking a simple English language query such as “how do we optimize generation dispatch at 2 PM tomorrow if there is 40% cloud cover?”
Cross pollinate this app with another app that blends SCADA, distribution and outage management data with field workforce maintenance reports, and grid resiliency forecasting can be simple as asking “Which transformers are most likely to fail in the first week of August and how long will it take to restore service?”
Here is a small sampling of potential AI apps that utilities could be adopting across the globe:
- Social media analytics to detect outages and power theft
- AI apps that combine regulatory FERC documents with operational systems that alert the operator or compliance exposures.
- Apps that understand smart meter patterns to auto-calibrate demand response in line with renewable forecasts.
- Apps that integrate with smart field devices to auto-create predictive maintenance trouble tickets on assets that are likely to fail.
As simple as typing a question in Google
The key is the artificial intelligence and machine learning that create the right algorithms and train the apps to locate and retrieve the best information based on rankings of the most relevant query results. Eventually the apps begin to learn what you’re trying to answer. It’s just like typing a question in Google that seems to know who you are, where you are, and what information you have searched for in the past.
Another added value these apps provide is information citizenship – the notion that anyone who can ask a question has the same access to any information as a seasoned IT data analyst.
The value proposition of “appifying” operational management, decision support and risk management is too big to ignore. Apps have been transformational in the way we intelligently manage our lives, and I predict they will be just as transformational in the way Utilities intelligently manage their enterprise.
Krishna Kumar is chief executive officer of App Orchid Inc.