We are creating some awesome events for you. Kindly bear with us.

Industry Collaboration Powers New Generation of Grid Emergency Control Technology

bussiness hand working with email icon modern computer touch screen on blue sky background as internet conept

Grid operators face huge challenges and massive alternatives on the subject of managing by way of emergency circumstances that disrupt energy service. The rising quantity of energy outages within the United States value an estimated $30–50 billion and have an effect on hundreds of thousands of prospects every year. The problem and the chance each lie in optimising energy system responses when the surprising occurs. Optimisation can reduce the results of these occasions.

U.S. Researchers at Pacific Northwest National Laboratory (PNNL) are collaborating with several companies to develop a real-time adaptive emergency control system to safeguard the grid in opposition to pricey disturbances from excessive climate and different disruptive occasions. The technology considerably improves on current strategies, which require grid operators to depend on offline research to find out acceptable system responses throughout actual occasions.

However, these events do not always unfold as the researchers expect, and grid conditions can change in fractions of a second. Some online tools considered by current standards to operate in “real-time” can trail behind actual events happening in the system by five to 15 minutes.

The scalable High-Performance Adaptive Deep-Reinforcement-Learning-based Real-Time Emergency Control (HADREC) platform – being additional developed and examined under three-year funding from the Department of Energy’s Advanced Research Projects Agency-Energy (ARPA-E) – makes use of a kind of synthetic intelligence (AI) known as deep reinforcement studying, alongside high-performance computing, to automate decision-making and system responses inside seconds of a disturbance.

Deep reinforcement studying improves on typical reinforcement studying in its potential to raise the scale and rapidly and successfully apply current patterns to an actual occasion’s unpredicted issues throughout 1000’s of a system property. Initial outcomes present the HADREC technology will assist scale back system response time 60-fold and enhance system recovery time by no less than 10%. This helps stop cascading disruptions, thus permitting extra environment-friendly and resilient grid operation.

Sometimes grid operators have traditional ways to solve a particular problem, but it is difficult and time-consuming and they still may not arrive at a feasible and effective answer. An ARPA-E project like this one pulls parties together to guide development from multiple perspectives, and combine that with the benefit of strong research capabilities to solve real-world problems more efficiently and effectively.

– Qiuhua Huang, PNNL Electrical Engineer

The project’s collaborators are realising the advantages of combining various views and experiences from all angles of the issue whereas working effectively towards an answer. During year one, the crew established efficiency strategies and benchmarks for the HADREC algorithms and commenced testing them utilising a mock system at the scale of the Texas grid.

Now, as they enter year three, the crew will concentrate on demonstrating the technology utilising precise utility and grid knowledge. By the top of the project in 2022, the technology can be developed and sufficiently examined for integration with an actual manufacturing system.

As reported by OpenGov Asia, researchers at Pacific Northwest National Laboratory (PNNL) has also utilised technology to lessen the impact of natural disasters. They are expanding PNNL’s operational Rapid Analytics for Disaster Response (RADR) image analytics and modelling suite to mitigate damage to key energy infrastructure. PNNL collaborates with the Department of Defence’s Joint Artificial Intelligence Centre, and the Department of Homeland Security.

By using a combination of image capturing technology such as satellite, airborne, and drone images, artificial intelligence (AI), and cloud computing, the team works to assess as well as predict the damage. Accurately forecasting the movement of natural disasters such as wildfires, floods, hurricanes, windstorms, tornados, and earthquakes allows the responders to take measures to reduce damage, conduct advanced resource planning, and increase infrastructure restoration time.

Send this to a friend