麻豆村

, artificial intelligence (AI) holds tremendous promise while also invoking challenges in its applications and use.

AI鈥檚 capabilities to synthesize mammoth amounts of data are being harnessed across every industry. However, running and iterating on the algorithms that compute new, innovative solutions faster also means energy to power them is needed in greater magnitudes.

The pace at which AI is now advancing also requires consideration of how to efficiently and sustainably power the technology, and long-term, thoughtful strategies, said聽, executive director of the聽Wilton E. Scott Institute for Energy Innovation(opens in new window).

鈥淎t Carnegie Mellon, we are leading AI for the world, but we're also leading energy for the world,鈥� he said. 鈥淲e've been leading work at the intersection of AI and energy for decades."

As part of that mission, the Scott Institute is hosting聽麻豆村 Energy Week(opens in new window), this year bringing together energy and sustainability leaders to combine forces and exchange ideas at the intersection of AI and energy.

鈥淭here are good reasons why AI is being pursued in the way it is,鈥� Tkacik said. "It's going to make our lives better in a myriad of ways, and there are a lot of smart people trying to make sure that this is done in an ethical and responsible way."

Harnessing AI鈥檚 Possibilities Starts with Definitions and Data

, Raj Reddy Assistant Professor in the聽 in the聽, who was recently named聽, said solutions regarding AI efficiency should start with agreeing upon what defines something as artificial intelligence, then measuring and reporting the energy usage.

厂迟谤耻产别濒濒听 funded by the U.S. National Science Foundation's (NSF) Expeditions in Computing Awards program hoping to lay this type of groundwork for sustainable computing.

鈥淚n order to make informed decisions and policies 鈥� for example, around energy use and the relationship between AI and future energy use in the U.S., due to data centers 鈥� we need a much better understanding of the actual drivers of that energy use,鈥� they said.

Strubell is among the Carnegie Mellon researchers examining these frontiers related to AI in energy and climate solutions set to聽contribute to discussions as part of Energy Week(opens in new window).

鈥淚鈥檝e been thinking about the foundational work,鈥� they said. 鈥淭here's a need for data. And there's a lot of analysis that we can do in academia with the information that's available to us, but there's also a lot that we can't do because there's not enough data about things like what the workloads actually are in data centers.鈥�

Without Batteries, Devices Storing Energy Create Possibilities

Efficiency in computing also stems from more efficient processing systems, including computer chips, which has been the focus of work by聽, Kav膷i膰-Moura Professor of Electrical and Computer Engineering in the聽, for the past 10 years.

鈥淲e need to make computing more energy efficient, because if we don't do that, we can't continue to add functionality to these kinds of energy-constrained devices,鈥� he said. 鈥淲e can't continue to push AI and computing forward in general without energy efficiency. Going forward, for the next five to 10 years, energy is the only thing that matters.鈥�

Lucia and his research team are聽 that use energy-harvesting devices and intermittent computing, a term that his team established.

The devices collect energy from the environment, such as solar energy, radio waves or vibrational mechanical energy, which is stored in a chargeable capacitor that is simpler than one that uses a battery.

鈥淭here's no environmental impact of having to produce, distribute and dispose of batteries, and there's no maintenance in having to replace batteries,鈥� Lucia said of the project. 鈥淵ou have these devices which have all these other benefits, but they have an unfortunate side effect 鈥� they turn off, because you don't always have power in the environment. And when they turn off, your system goes haywire.鈥�

That鈥檚 where intermittent computing comes in, Lucia said.聽

Lucia began to push forward intermittent computing, and he and聽, associate professor in the School of Computer Science, co-advised then-doctoral student Graham Gobieski on work on spatial dataflow architectures that were well-suited for intermittent computing. The trio founded聽 to commercialize the spatial dataflow architecture.聽

鈥淲ith that little tiny bit of energy, the biggest impediment to the progress of those batteryless devices was the inefficiency of computing to begin with,鈥� Lucia said. 鈥淭his spatial dataflow architecture is what unlocks all that efficiency, and so we've been developing those efficient architectures.鈥澛�

Devices using these technologies could be used in complex environments that are difficult to access, where those with batteries would otherwise require changing or charging by humans, such as space exploration, disaster response, and construction or industrial sites. Fewer batteries would also lessen the environmental impact of otherwise disposing of or recycling used batteries.

鈥淲ith these batteryless devices, you can extend the lifetime of the device essentially indefinitely, until the energy transducer, like a solar panel, starts to break down,鈥� Lucia said. 鈥淪o that might be a five- to 10-year lifetime, up to 30 years, in some cases.鈥�

Ultimately, energy is a cornerstone on which future innovation rests, Lucia said, especially when it comes to applications such as personal devices for each of the seven and a half billion people on the planet.

鈥淲e need to think about energy,鈥� he said. 鈥淭he defining problem for humanity for the next several decades is how to match the need for computing with the energy required, and that includes AI, but not just AI. 鈥� Energy is the biggest problem facing humanity.鈥�

AI Increases Speed of Progress Toward Nuclear Fusion Power

Using AI could help unlock a new potential source of energy to solve that problem, including work by聽Jeff Schneider(opens in new window), research professor in the School of Computer Science, and聽his research team studying nuclear fusion.

The reaction, where atoms collide 鈥� distinct from the splitting atoms of nuclear fission already used in nuclear power plants 鈥� are created in a tokamak machine. The billion-dollar reactor heats hydrogen until it becomes plasma, which is then formed into a donut-shape, wrapped with magnets and confined within a magnetic field. The system simultaneously controls the injection of hydrogen particles, the shape of the plasma, and its current and density.

鈥淲e just don't know how to keep that plasma in place at high enough temperatures and pressures for long enough periods of time so that it can be used in a power plant,鈥� said Schneider, who will also be speaking as part of Energy Week. 鈥淭hat's basically the one thing that's standing between us and unlimited clean energy.鈥�

Machine learning is helping the team synthesize decades of data from past experiments to better understand exactly how each of the 鈥渟hots鈥� taken inside the machine at the DIII-D National Fusion Facility in San Diego.聽

鈥淥ver the decades there have been tens of thousands of these shots that have happened, and all of that you can feed to a machine learning model to learn to predict those steps from one state to the next to use that to make a simulator,鈥� Schneider said.

The simulator can then perform millions of shots, 鈥渕ore than have ever been run in real time,鈥� he said. 鈥淚t just keeps practicing until it finds a control policy, and now what we can do is get to the real bottleneck to progress, the limited time 鈥斅爋nly a few hours per year 鈥� available to run experiments on the tokamak.鈥�

Schneider said with machine learning, the team has been able to double the number of shots that could happen without disruption as a result of their experiments, and because of that, collaborators asked to run the same algorithm at the KSTAR tokamak in South Korea.

鈥淭hese methods are getting us these results faster than we otherwise would be able to get them,鈥� he said. 鈥淭hese are both examples of things that physicists have known about and been interested in for years, that you know they just hadn't been able to reach yet. Now, we've proven that we have the tools to solve them, and so what we're really trying to do now is to get the resources to roll this out at scale.鈥�

Making progress on the science behind nuclear fusion will lead to progress toward power plants that can produce considerable energy from a renewable, emission-free source.

鈥淚f you think about the world's grand challenges, many of them are just energy problems,鈥� Schneider said, citing global warming and food and water accessibility. 鈥淎ll these things are just clean energy problems, so that's why I'm really excited about solving the problems with clean energy, specifically with fusion.鈥�

Building Data Synthesized by AI Could Reduce Energy Usage

When it comes to research aiding systems that are already in place,聽, assistant professor in building technology with the聽, is using AI to make building design more efficient.

Setting a benchmark standard for buildings鈥� energy usage of a typical size in a specific location allows for future designs to use those figures to continue to improve efficiency, but many cities don鈥檛 have those comprehensive energy benchmarking data to compare past designs with those under development, Sawyer said.

鈥淲e realized we could actually use the power of AI and machine learning to analyze a lot of data from other similar cities and similar environments to predict what it would be for a city that's missing those benchmarks right now,鈥� she said.聽

Sawyer received a seed grant from the Scott Institute(opens in new window) with her Ph.D. student Tian Li for this work to address the need to reduce carbon emissions and energy use in buildings across the country, then identify ambitious and achievable decarbonization targets.聽

Previously, building scientists would apply statistical methods, she said. Now, using AI, researchers can augment those approaches by uncovering nonlinear patterns to make even better predictions聽 and classifications based on larger and more complex datasets.

鈥淎I really changes how we do research,鈥� she said. 鈥淚t gives you the opportunity to really do true exploration: Here鈥檚 an idea area, I don鈥檛 necessarily know everything that鈥檚 out there, but I have this amount of data and can ask it to find patterns that our human eyes don鈥檛 see.鈥�

In another project, she is working with doctoral student Niloofar Nikookar to develop a dynamic lighting system based on AI.

Static lighting systems remain the same regardless of the amount of daylight filtered through a building鈥檚 windows or the color of the light, which could affect the moods and productivity of the people inside.

Adjusting lighting through smart systems can not only help people feel better, but also improve energy efficiency, Sawyer said.

鈥淥ur hope is that once we have the datasets of how people respond to different colors of lighting and different sky conditions, then we could actually train the model to create a dynamic lighting system using AI that responds to how someone feels and what kind of space they're in,鈥� she said.聽

Building design could also benefit from predicting occupant behavior, which can also impact energy usage, Sawyer said, such as how people react to blinds that adjust on their own to create shade and reduce glare.聽

鈥淲e鈥檙e designing for people,鈥� she said. 鈥淲e want to design responsibly so it doesn鈥檛 harm the environment and so it doesn鈥檛 negatively impact the people that are using our spaces.鈥�

Monitoring Household Systems with AI Could Reduce Energy Usage

, professor in the聽, examines the way existing buildings monitor and use energy in order to make them more efficient.

His research involves what is known as non-intrusive load monitoring, which analyzes smart meter data, identifying appliance usage and predicting malfunctions.

鈥淚f you can be smart about how to analyze the data that's coming from your smart meter, then you are going to be able to fingerprint individual appliances and also get to know a lot about the behavior of people in the home through their usage of devices that consume electricity,鈥� Berg茅s said.聽

Then, computer systems can be trained to analyze the data from the meter and provide feedback on how to improve energy consumption.

鈥淪ay your washing machine is breaking down. There are signatures of that motor failing that could be detected from the smart meter itself,鈥� he said. 鈥淚f you're careful about what you're paying attention to, you can know not only that these things are on or off, but also what they could be doing, and whether they are malfunctioning.鈥�

Even though all the possible signatures from every appliance would be difficult to identify, systems could use AI to recognize anomalies closely enough to monitor them and make the data accessible.

His team has used artificial intelligence to develop learning-based controls for heating, ventilation and air condition systems. AI can monitor the building, then emulate how to manage the temperatures before making it more efficient.

Instead of managing only one building at a time, a set of buildings could be managed together and the energy usage could be coordinated using an algorithm. The energy can then be stored or released as needed.

鈥淭hen you are essentially allowing all these buildings to act as a very big thermal battery,鈥� he said. 鈥淎ll of them together are creating this storage and they are allowing for the excess production of electricity to be stored.鈥�

Transforming Energy Solutions with AI Starts with Research

Using artificial intelligence in each of these ways requires human innovation and ingenuity, including the interdisciplinary collaboration encouraged by Carnegie Mellon and facilitated by the Scott Institute.

The faculty members agreed that the students and colleagues at 麻豆村 are what makes considering and working toward solutions to these energy-related challenges possible.

鈥淲e have the best students to work on these projects, and it really takes the best folks in AI and machine learning to tackle such hard problems,鈥� said Schneider.

The future benefits of artificial intelligence will depend on how the research and innovation being pursued now also balance sustainability and the environment.

鈥淵ou can have both innovation and sustainability. We just need to sort of think about things differently,鈥� Strubell said. 鈥淣ow is a critical time to be thinking about this, because I think we are about to build out a ton of data center infrastructure and the supporting energy systems to power those data centers, and I do believe that we can do that in a way that is compatible with sustainability in various ways.鈥�

Processes using AI that improve energy usage, storage and reliance developed now through research at 麻豆村 will continue to transform and establish sustainable systems well into the future.

鈥淚'm optimistic, and the Scott Institute is optimistic, which is why we're pursuing this line of research,鈥� Tkacik said. 鈥淭here are many applications of AI for energy and climate yet to be discovered, and these discoveries are being pursued in a very responsible way by a number of scholars, both across the country and right here at Carnegie Mellon."