Argonne scientists created a new artificial neural network model that handles a power system’s static and dynamic features with relatively high accuracy. With a new neural network, lab scientists helped create formulas to bridge a power system’s static and dynamic features — a difficult feat.
America’s power grid system is extensive but dynamic, making it incredibly challenging to manage. Human operators know how to maintain systems when conditions are static. But when conditions change quickly due to sudden faults, operators lack a straightforward way of anticipating how the system should best adapt to meet system security and safety requirements.
At the U.S. Department of Energy’s (DOE) Argonne National Laboratory, a research team has developed a novel approach to help system operators understand how to control power systems with the help of artificial intelligence. According to a recent article in IEEE Transactions on Power Systems, their new approach could help operators manage power systems more effectively, enhancing the resilience of America’s power grid.
Converging dynamic and static calculations
The new approach allows operators to make decisions considering static and dynamic power system features in a single decision-making model with better accuracy — a historically tough challenge.
Argonne computational scientist Feng Qiu, who co-authored the study, said: “The decision to turn a generator off or on and determine its power output level is an example of a static decision, an action that does not change within a certain amount of time. Electrical frequency, though — which is related to the speed of a generator — is an example of a dynamic feature. It could fluctuate over time in case of disruption (e.g., a load tripped) or operation (e.g., a switch closed). If you put dynamic and static formulations together in the same model, it’s essentially impossible to solve.”
In power systems, operators must hold frequency within a specific range of values to meet safety limits. Static conditions, such as the number of generators online, affect the system’s ability to have a frequency and other dynamic features.
Most analysts calculate static and dynamic features separately, but the results fall short. Meanwhile, others have tried to develop simple models that can bridge both types of calculations. Still, these models are limited in scalability and accuracy, particularly as systems become more complex.
Artificial neural networks connect the dots between static and dynamic features.
Rather than trying to fit existing static and dynamic formulas together, Qiu and his peers developed an approach for creating new recipes that could bridge the two—their approach centres on using an artificial intelligence tool known as a neural network.
Yichen Zhang, Argonne postdoctoral appointee and lead author of the study, said: “A neural network can create a map between a specific input and a specific output. If I know the conditions we start with and those we end with, I can use neural networks to figure out how they map to each other.”
While their neural network approach can apply to bulk-power systems, the team tested it on a microgrid system, a controllable distributed energy resource network, such as diesel generators and solar photovoltaic panels.
The team used the neural network to track how a set of static conditions within the microgrid system mapped to a group of dynamic needs or values. More specifically, researchers used it to optimize the static resources within their microgrid so the electrical frequency stayed within a safe range.
Simulation data served as the inputs and outputs for training their neural network. The information was static data, and the results were dynamic responses, specifically the safe range of frequencies. When the researchers passed both data sets into the neural network, it ”learned” to map estimated emotional responses for a group of static conditions.
Qui said: “The neural network transformed the complex dynamic equations that we typically cannot combine with static equations into a new form that we can solve together.”
Opening doors for new types of analyses
Researchers, analysts, and operators can use the Argonne scientists’ approach as a starting point. For example, operators could potentially use it to anticipate when they can turn generation resources on and off while at the same time ensuring that all the online resources can withstand specific disruptions.
Argonne postdoctoral appointee and co-author Tianqi Hong said:
“It is the kind of scenario that system operators have always wanted to analyze, but were unable before too because of the challenges of calculating static and dynamic features together. Now we think this work makes this type of analysis possible.”
Argonne’s Electric Power Grid Program director Mark Petri said: “We’re excited by the potential for this analytical approach. For instance, this could provide a better way for operators to quickly and safely restore power after an outage, a problem challenged by complex operational decisions entangled with system dynamics, making the electric grid more resilient to external hazards.”
DOE’s Office of Electricity, Advanced Grid Modeling Program supports this work using Argonne’s Laboratory Computing Resource Center.
Argonne National Laboratory seeks solutions to pressing national problems in science and technology. Argonne, the nation’s first national laboratory, conducts leading-edge basic and applied scientific research in virtually every scientific discipline. Argonne researchers work closely with researchers from hundreds of companies, universities, and federal, state and municipal agencies to help them solve their specific problems, advance America’s scientific leadership and prepare the nation for a better future. With employees from over 60 countries, Argonne is managed by UChicago Argonne, LLC, for the U.S. Department of Energy’s Office of Science.
The U.S. Department of Energy’s Office of Science is the most prominent supporter of basic research in the physical sciences in the United States and is working to address some of the most pressing challenges of our time.
Source:
Press Release JOAN KOKA energy.gov/sscience
Date: AUGUST 20, 2020
Ananova 