The US electrical grid is truly an engineering marvel consisting of more than 600,000 miles of transmission power lines connecting more than 9,200 generating units that have a generating capacity of more than a million MW’s. The 40-year-old equipment is overworked and running out of lifespan. It is one of the most vulnerable infrastructures we have, especially today with the US moving toward more renewables and a growing population.
Our federal government recently stepped in with support for our electrical grid. In November 2022, the DOE (Department of Energy) announced $13 billion in new financing opportunities for the expansion and modernization of the nation’s electric grid with the Bipartisan Infrastructure Law. This resulted in the largest single direct federal investment in critical transmission and distribution infrastructure ever through the Grid Resilience and Innovation Partnership (GRIP) program and the Transmission Facilitation Program. The GRIP program money will be divided across three programs: Grid Resilience Utility and Industry Grants ($2.5 billion), Smart Grid Grants ($3 billion), and Grid Innovation Program ($5 billion). The remaining monies ($2.5 billion) will be allocated through the Transmission Facilitation Program.
The advancement of our renewables will require more transmission lines and many of our existing power lines will need to be replaced with power lines that are capable of a higher capacity. In addition, we need technological improvements for its protective equipment and tech-advanced devices, capable of detecting a developing problem and automatically taking action to divorce from the suspect power source and sync to a dependable source. The grid operator will then be notified of the change(s) and the problem, so action can be taken to correct the initiating event.
Incorporating AI (artificial intelligence) into our grid operations is also needed. It can help in several ways, by providing accurate prediction of consumer demand and generation, in parallel with real-time grid operation. Accurate power demand predictions aid in planning for power plant operations and our spinning reserves, which in turn, can reduce operating costs and carbon emissions by providing the grid operators with the information needed to reduce or eliminate the power units producing these emissions.
Predicting our electrical demand is heavily associated with the weather, business activities and everything that affects those business activities, and historical data to determine patterns associated with our demand and the weather. Accurate weather predictions are very important today with wind and solar power sources. Currently, most companies use numerical optimization to improve power plant operation but as our renewables increase these numerical calculations will become more complex with many more decision variables, that are dramatically affected by the weather. Numerical optimization falls short in solving the weather prediction – in real time, especially when there is high uncertainty in the power sources. Incorporating AI reinforcement learning with the weather models can be trained to make decisions in a fraction of a second, as opposed to numerical methods that can require minutes and sometimes hours to predict. However, this too is not perfect, with numerical or mathematical optimizations, you have hard-coded constraints in the system, but with AI reinforcement learning, there is a reliance on its training. Therefore, numerous adjustments in the AI reinforcement learning will be needed as our grid evolves. So, the speedy AI decision will not guarantee an unsafe solution, especially when it comes to our complex energy systems or operational power systems.
Since 2011, when the term “smart grid” was revealed, we have made great strides in its technology. For example – should an underground fault or single loss of a power source occur on an underground residential loop, S&C Electric’s EdgeRestore system automatically locates and isolates the fault and reroutes power from an alternate source – all within 60 seconds. This device reduces the impact of sustained outages that commonly last for hours and eliminates the need for immediate crew intervention, keeping power on until the underlying issue can be resolved. The automatic isolation of the fault(s) simplifies the process of locating the fault(s) on an underground residential circuit and reduces the voltage exposure for electrical crews servicing the problem. Furthermore, S&C Electric claims this device does not need any programming, firmware updates, computers, internet connectivity, batteries, radios, or antennas. Truly modernizes the last mile of an underground power distribution system, reducing sustained power outages to momentary interruptions and making the grid safer, smarter, and more resilient throughout weather challenges and growing electricity demands.