Solving complex issues like reducing building emissions can be a difficult task for facility owners. Understanding energy consumption patterns and gaining insight into how to address inefficiencies requires the right technology, and the right mindset to implement change. 

As regulations for climate initiatives such as New York's Local Law 97 take effect, many buildings will need to find effective strategies to combat increasing energy consumption. One solution gaining traction within commercial building energy efficiency optimization is the use of Artificial Intelligence (AI) and Machine Learning (ML). AI and ML enhancements provide the cutting-edge ability to uncover patterns, produce accurate predictions, and automatically respond to those predictions.

Improving building efficiency starts with data, getting it organized, and ensuring its quality. With quality data, you can then deploy machine learning algorithms that can constantly consume and analyze information from a variety of sources, such as equipment, sensors, and devices to provide insights and recommendations.

This blog will give an overview of the various AI applications being used to reduce building energy consumption and carbon emissions.  Here's how you can use AI to get (and stay) compliant with Local Law 97.

Intelligent Building Monitoring

Ensuring effective building energy management is a challenge due to needing to understand every area in which a building consumes energy and electricity. With more than 76% of all U.S. electricity use and more than 40% of all U.S. energy use and associated greenhouse gas emissions coming from buildings, there is value in reducing these numbers.

According to the EIA, commercial buildings consume power within the following top five areas: 

• Lighting
• Cooling
• Ventilation
• Refrigeration
• Computers & Office Equipment 

Each of these systems is complex and unique and requires different tactics to make an impact on how much power it is consuming. One available option many building owners are currently taking is utilizing AI-powered intelligent building monitoring.

Intelligent building monitoring systems collect data and apply analytics to continuously monitor and analyze different types of building systems. Using AI to monitor building environments in real time can help give insight into usage, provide information on current inefficiencies, and allow facilities managers to strategize techniques to reduce energy consumption.

Artificial Intelligence for Smart Buildings

AI isn't just being used to monitor the various energy-consuming systems within a building, it's also being used to manipulate the building and make it smarter. In fact, the market for building energy management and its smart building capabilities is expected to grow substantially in the coming years. As various advancements have been made, there have been a growing number of applications for AI to make buildings smart.

Building automation uses advanced technology to optimize performance and enhance occupant experience along with making the building's use more efficient. AI is being used alongside IoT devices, sensors, and other equipment to collect information on a building's operation, energy usage, and occupancy pattern. This information allows the smart building system to control and automate various building systems such as lighting, cooling, heating, ventilation, security, and more. 

By implementing the various tools that can make a building smarter, building owners are also making those buildings more energy efficient. Commercial buildings use a lot of energy and a lot of that energy is wasted, such as when things are on during non-occupied hours. Smart building tools can automate systems to turn off and to only be used when occupants are in the area leading to reduced energy waste and energy costs. 

AI for Predictive Maintenance & Fault Detection

A key to optimizing energy efficiency within buildings and a great strategy for reducing CO2 emissions for a commercial building is using AI to improve performance for various systems through predictive maintenance and fault detection. 

Predictive maintenance uses machine learning to analyze data coming from system sensors to predict when equipment will fail, while fault detection detects an issue and informs you on what can be done to solve it. Tools such as these could be deployed on various systems in commercial buildings to improve operational efficiency and reduce maintenance costs. Here is a list of just some of the systems in buildings and how predictive maintenance can support them. 

These systems have various components, all of which must work together to perform optimally. When one part of the system isn't properly maintained it could degrade performance in other areas. Needing to maintain systems outside of planned maintenance results in extra costs, unplanned downtime, and additional labor. 

Along with using AI to predict maintenance and detect faults, it's also important to improve current maintenance practices in order to regularly check on systems and collect data for analytics. Putting these energy efficiency measures in place can lead building owners to meet specific carbon emissions limits and reduce how much energy is being consumed. 

Machine Learning for BMS Controls Optimization

Did you know that the U.S. Energy Information Administration (EIA) projects air-conditioning energy use to grow faster than any other use in buildings from now until 2050? Being able to optimize the energy efficiency of these systems will bring the most savings to both overall costs and energy consumption. 

Unfortunately for many, HVAC system controls aren't adaptable to their current conditions. They don't take into account changes in building load or weather forecasts or differences in temperature and time of day. When the system can't adapt to its surroundings, machine learning technology can provide analytics for optimized control settings based on varying conditions. 

Beacon AI for cooling optimization helps energy, sustainability, and facilities managers leverage existing HVAC equipment data and external data such as outdoor temperature and building load to achieve autonomous cooling optimization. Beacon uncovers significant economic value in the form of cost reduction, and benefits ESG (and Local Law 97 compliance) initiatives by lowering carbon emissions.

Meet Local Law 97 Emissions Limits With AI Tools

With a goal of reducing carbon emissions from New York City buildings by 40% in 2030, the time is now for building owners and operators to optimize energy efficiency. Local Law 97 emissions limitations go into effect beginning in 2024. By utilizing AI for smart building enhancements and HVAC optimization, building owners can see a reduction in their energy consumption, operating costs, and emissions. 

With Beacon's machine learning technology, we've seen an average 10-20% reduction in energy and water costs without impacting building comfort. 

Tagup is on a mission to make the machines that power the world more reliable and efficient, including commercial HVAC systems. Optimizing the most energy-consuming part of your building will help meet carbon emission limits and support compliance with New York Local Law 97.

Interested in learning more? Let's chat.