Maximpact Blog

How Artificial Intelligence Creates Smarter Buildings

AdobeBuilding

The Adobe World Headquarters in San Jose, California is one of the most energy efficient buildings in the United States. October 21, 2007 (Photo by Coolcaesar) Creative commons license via Wikipedia

By Sunny Lewis

BALTIMORE, Maryland, August 22, 2019 (Maximpact.com News) – “Artificial intelligence or AI involves a computer’s ability to adapt to a situation and create a unique solution that was not directly programmed. The energy industry has been tapping into the innovative world of AI to learn how to improve processes, ensure energy resiliency and to enhance the customer experience, among other pertinent goals,” Chris Buzby writes on the Constellation Energy Resources blog.

Based in Baltimore, Constellation, an Exelon company, provides power, natural gas, renewable energy, and energy management products and services for homes and businesses across the continental United States.

Constellation, like other energy companies, is exploring AI to determine if it will cut its customers’ energy costs and increase the prospects of more efficient consumption of energy by making buildings smarter.

Senior Manager of Corporate Strategy, Innovation and Sustainability at Exelon, Buzby writes that, “Beyond the home, we are seeing AI enter every part of the energy value chain. Examples include the work being done at Exelon, such as the generation facilities leveraging AI to better predict failure and optimize when to schedule maintenance.”

Constellation is exploring how the company can leverage AI to deliver the right person the right insight at the right time to make more informed decisions that have a direct impact on their energy costs.

“On the distribution side,” writes Buzby, “utilities are using AI-based technology to better respond to storm-related outages. There are many other use cases being explored, and some have already been put into practice.”

For commercial energy managers, new solutions such as utility bill review and auditing, as well as energy forecasting, are becoming available.

No longer are energy managers logging into one of a multitude of dashboards and searching for anomalies. Now, they are being notified when an issue emerges or an opportunity arises to create value for their organization.

AI can enhance an energy manager’s capabilities. Customers will be able to forecast load as well as cost to help determine the value of energy efficiency and distributed energy resources.

In sustainability, writes Buzby, “AI can help you balance the risk tolerance of your organization with your greenhouse gas-related goals to assist Constellation experts in the creation of a customized commodity product for your business, including offsite renewables and managed commodity products, that meet your needs.”

But using AI to improve energy efficiency is not always that easy.

It’s often tough to convince building managers to invest in energy efficiency. Buildings and building systems are supposed to be highly efficient, but performance deteriorates rapidly or never matches the intentions of the architects and designers.

Building owners and operators must first pinpoint which locations or energy sources are the main energy leakers, and then understand the causes behind these issues.

Another barrier that makes energy efficiency so difficult to scale across large building portfolios is the high cost of performing on-site energy audits and installing monitoring and control hardware. Costs can run into the thousands just for the diagnostics, so energy efficiency can get pushed into the background in commercial buildings.

ReichstagDome

Open to the public, the glass Reichstag dome has a 360 degree view of the surrounding Berlin cityscape. The debating chamber of the Bundestag, the German parliament, can be seen below. A mirrored cone in the center of the dome directs sunlight into the building, which was designed to be environmentally friendly. Energy efficient features that use the daylight shining through the mirrored cone were applied, decreasing the carbon emissions of the building. August 21, 2013 (Photo by Mariano Mantel) Creative commons license via Flickr

Then there’s just plain lack of action. Building managers without an energy efficiency background may struggle to appreciate the savings and to understand the nuances of their energy-saving options. They can give in to decision fatigue, putting off selecting the best solution for their needs. Vetting and selecting an energy conservation measure is often accompanied by transaction costs.

Now, new software tools have been developed to help. DEXMA, Europe’s energy management software provider, has developed a new platform called EnergyGrader, designed to help any organization with an energy bill to identify energy-saving opportunities in a fast and frictionless way.

Using Big Data algorithms and machine learning, Energy Grader turns costly energy bills into revenue streams for businesses. There is no need to install expensive energy monitoring equipment or wait months for audit results. Users simply type in the address and what they know about the building, and let EnergyGrader benchmark it against thousands of similar ones.

Everything is done in the cloud, eliminating the need for any kind of hardware installation or on-site audit. Personalized energy insights and automatic recommendations are made possible due to proprietary pattern recognition algorithms that automatically benchmark users’ energy spending and behavior against a database of 50,000 buildings so as to detect similar patterns.

The EnergyGrader recommendation library is the result of translating this complex AI system into simple energy-saving solutions. This AI platform for energy savings can recommend several different solutions automatically, including: which period of the year produces savings, insights into energy efficiency project capital expenditures, when to expect savings, and payback periods.

EnergyGrader’s recommendation library will continue to expand and provide increasingly precise recommendations over time, as it learns from users’ energy spending behavior and building profiles.

Back in the United States, products like intelligent light bulbs and thermostats are currently in use across the country, reducing energy usage. The more complex question is how to use artificial intelligence in energy businesses.

“As companies face dual incentives of saving money and protecting the environment, green building is on the rise nationally. Green building, or the concept of incorporating energy efficiency and environmental responsibility in every stage of a building, from design to construction, is gaining popularity as companies increasingly recognize both the cost efficiency and positive PR,” says the U.S. Green Building Council.

In Cleveland, Ohio, Case Western Reserve University, through its Great Lakes Energy Institute (GLEI), last August entered into a one-year agreement with the Irish multinational company Johnson Controls, that produces electronics and HVAC equipment for buildings, to further develop and begin marketing new technology – software that uses smart-meter electricity datasets to conduct a virtual energy audit of a commercial or retail building at about a tenth of the cost of on-site audits.

“A great deal of attention is paid to supporting renewable energy, but energy efficiency is commonly the cheapest way to reduce electricity usage and carbon emissions,” said Alexis Abramson, co-director of the GLEI. “Our joint partnership will enable further development of a data analytics tool that will make energy efficiency as easy to do as it is not to do!”

The tool, called an Energy Diagnostics Investigator for Efficiency Savings is described as “mapping a building’s DNA through a rigorous analysis of multiple data streams,” including weather, insulation and utility meter data.

“We are able to conduct a virtual audit without ever setting foot on site,” said Chris Littman, commercialization and operations director at the GLEI. “We take smart-meter data, conduct our analysis and provide a report with detailed recommendations for the customer to make conservation measures–and perpetually save money.”

Most current energy audits involve going to a building, performing leak tests, infrared imaging, blower door tests, and other procedures. They can be expensive and take days to conduct, which may also disrupt normal business operations.

This new technology was developed by the two partners – Case Western and Johnson Controls – over the last two years with the support of a $1.3 million U.S. Department of Energy grant via the Advanced Research Projects Agency (ARPA). Littman said this most recent agreement is an extension of that partnership, but also the possible precursor to a more expansive licensing agreement.

More and more, building systems are data-enabled and connected to the web. Johnson Controls is partnering with customers to build smart buildings enabled by artificial intelligence and the Internet of Things.

Johnson Controls helps enterprises put their building data to work, helping facilities managers gain insights, find efficiencies, and create sustainability.

Johnson Controls is at the forefront of smart facilities. These next-generation smart buildings have unique characteristics that unlock new possibilities for how building occupants interact with their environment, creating what the company calls “self-conscious, self-healing, and occupant-driven” buildings.

In April, the U.S. Department of Energy’s Advanced Research Projects Agency-Energy (ARPA-E) announced up to US$20 million in funding to accelerate the incorporation of machine learning and artificial intelligence into energy technology and product design processes.

“Artificial intelligence and machine learning has the potential to literally transform every aspect of the world as we know it, and accelerating this technology is crucial to strengthening our country’s economic and national security,” said U.S. Secretary of Energy Rick Perry. “DOE-fueled artificial intelligence is being utilized across all sectors, from strengthening cybersecurity and national security, [to] increasing energy efficiency [and] optimizing grid security and resiliency.”

Maximpact AI machine learning main image