Thursday, January 11, 2018

Wisconsin utility crews to depart for Puerto Rico Jan. 13

Three months after Hurricane Maria hit Puerto Rico, more than 40 percent of residents are still in the dark. Thousands of power restoration workers from U.S. energy companies are answering the island’s need for assistance, including about 35 We Energies and 25 Wisconsin Public Service (WPS) employees. The two companies will work together to respond to the widespread loss of power in Puerto Rico. They depart for an estimated six-week assignment in the San Juan area this Saturday, Jan. 13, from General Mitchell International Airport in Milwaukee.

Supervisors from We Energies and WPS already have made the trip to the island and are preparing for crews to arrive. Vehicles and equipment from both companies were sent by barge earlier this month. Crews plan to work 12- to 16-hour days restoring power to the island.

While they face uncertainty, unfamiliar conditions and terrain, and devastation of infrastructure like they’ve never seen, the employees are excited to answer the call to service.
We Energies and WPS supervisors departed for Puerto Rico from Milwaukee on Jan. 9. 

 “An opportunity like this – to go to an island and help restore power – has never come up before,” said Craig Kahoun, operations manager – WPS, in an interview with a Green Bay news station.

While crews from We Energies and WPS responded to Hurricane Irma in Florida and Georgia last year and to other hurricanes in years past, this is the first time the companies have performed restoration efforts outside of the continental U.S.

Peter Klafka, operations supervisor – We Energies, was interviewed by a Milwaukee news station and highlighted the importance of safety while on this trip. “There’re going to be a lot of hazardous conditions we’re going to encounter down there. The crews’ safety is the most important and the biggest challenge we’re going to have to face,” he said. 

“Everything we’ll work on there – it’s devastated,” Kahoun said. “So we’re going to have a lot of reconstruction.” The hurricane caused extensive damage to electric infrastructure in Puerto Rico. Additionally, accessing areas in need of restoration is further complicated by the islands narrow streets and rugged terrain.

The crews are willing to take on all of these challenges. Chris Vanlaarhoven, a We Energies lead line mechanic in Iron Mountain, is ready to start improving conditions for the people of Puerto Rico: “It’s a good feeling on our part, and I’m sure the people will be very happy down there once we turn the power back on for them.”

Friday, January 5, 2018

Marquette University’s GasDay program helps us deliver natural gas efficiently

A cold front moves down from Canada, and heaters start humming. A holiday comes along, and businesses shut down. Many different factors can influence natural gas use on any given day. To provide you, our customers, with reliable and cost-effective service, we depend on accurate forecasts of natural gas demand.

Those forecasts are made with the help of software developed by researchers and engineers at Marquette University. Director Ronald Brown launched Marquette’s GasDay program in 1993. We Energies was one of the first companies to test the lab’s models. Now approximately 35 natural gas companies rely on GasDay software nationwide, and our natural gas controllers use it to analyze demand and guide natural gas flow on a daily basis.

The software evaluates weather and market data to provide a “point forecast,” a single number representing how much natural gas customers will need. In 2016, natural gas controllers asked the GasDay researchers if they could provide even more information. It would be helpful to see the total range of possibilities in addition to the most likely forecast.

Saber defends his Ph.D. dissertation at the GasDay Lab. 
That’s where Mohammad Saber stepped in. The doctoral student in Electrical and Computer Engineering was inspired to make probabilistic forecasting possible for GasDay. Probabilistic forecasting incorporates uncertainty in its results: How likely is it that demand will fall in this range versus that one?

This method is common in some fields, such as finance, but rarely has been used in the energy industry due to its complexity. Saber knew that if GasDay could show probabilistic results, it would present a more complete view of the risks that could lead to over- or under-supply, helping natural gas companies cut down on costs.

“It’s interesting – in everyday life, we think in probabilistic forecasting,” Saber said. “Maybe you’re thinking about how long it will take to get home from work. You don’t have any point forecasting in mind. If the traffic is heavy, you’ll leave earlier.”

But modeling probability isn’t so intuitive. When Saber chose this topic for his Ph.D. dissertation, he set out to develop not only new ways of generating probabilistic forecasts for the energy industry, but also new methods of evaluating and communicating those forecasts. He began implementing his research at the GasDay Laboratory in early 2017, and he successfully defended his dissertation in September. The next step? Incorporating it into the software we use.
Example of a probabilistic forecast predicting
the amount of natural gas needed on an hourly basis.

Saber’s research soon may support our natural gas controllers as they make cost-effective choices and plan for the uncertainties ahead. It is just one example of the ways the GasDay Lab learns from and gives back to its customers.

“We love working with our local utilities,” said Tom Quinn, GasDay business director.

We’re glad to have GasDay predictions on our side this winter – helping us provide you with reliable and affordable natural gas service.