Skip to main content

How to lower energy costs chain-wide

Predictive analytics, automation and AI lower energy costs across a retailer’s portfolio
Gavin Platt
Gavin Platt

Retail buildings spend more than $20 billion on energy annually, according to an EnergyStar.gov report detailing efficiencies, impacts and trends. Heating, cooling and lighting are the highest areas of retail energy consumption, and with each year over the past decade a record-breaker for extreme weather, these outlays will only increase.

Harnessing automation and artificial intelligence technology could reduce these costs by at least $3 billion. Many of the largest retailers are adding energy generation and committing to sustainability goals to further reduce costs. Predictive modeling is critical to managing what can be an overwhelming data stream, incorporating recent and historical data to predict unique outcomes in a commercial building.

While a majority of the stores in a chain’s portfolio are generally similar in size, design and layout, each site’s energy usage pattern is unique. Managing the utility footprint across a chain’s building ecosystem means weighing evolving factors affecting each store – the local climate, equipment needs, pop-up kiosks, customer and employee activity, EV charging stations on site and more.

Identifying how energy is used throughout a commercial building traditionally has meant setting up a multitude of devices to measure and assess, requiring building managers to physically check and compile data from these devices.

Conducting audits, reading meters and manually entering data is error-prone and strains already time- and budget-pressured teams. Integrating a custom data-generating sensor array and a baseline statistical model of energy use is a first step, especially in light of this past year’s uncharacteristic in-store vacancy patterns for most retailers. 

Energy management software can reduce costs and errors and automate many building management tasks. According to a report by Transforma Insights, it’s not too early to start. By 2030 IoT deployment is expected to save more than eight times the energy it consumes, “resulting in net savings of 230 billion cubic meters of water and eliminating one gigaton of CO2 emissions.”

Every aspect of the store – HVAC systems, lighting, inventory, signage, shelves, terminals – can be woven into a data communications network, giving managers a holistic picture of energy use and activity throughout the entire chain’s portfolio. With automation taking on routine tasks and identifying problems, facility managers can instead focus their expertise on more productive areas such as enabling collaboration across teams and overseeing projects.

Establishing a normal-use pattern allows managers to create a benchmark for comparison, determine what is expected, learn as new data is fed into the loop, and react to deviations. Managers can also integrate weather system information and adjust actions (heating, cooling, lighting, ventilation), to seasonal variations and sudden abnormal weather changes.

Predictive analytics also anticipate and manage the lifecycle costs of equipment, a large expense to any commercial enterprise. Setting automated protocols to reduce lighting or the amount of time that a heating or cooling system is operating, or to turn off malfunctioning equipment, will add up to significant cost savings over the life of the equipment. Predictive modeling also alerts managers to set demand shedding protocols to prevent the failure of the entire system when demand outpaces energy capacity. 

An integrated data network can promote a multitude of savings across a store site:

  • Sensors that detect when rooms are unoccupied can safely conduct ultraviolet light sanitation;
  • Electronic displays, often left on when stores are closed, can be automated for off-hour shutdowns;
  • Other electronics (computers, printers, coffee makers, vending machines, etc.) that are generally left plugged in even when no one is on-site can have power diverted;
  • Freezer malfunctions can be identified immediately, saving products and money; and
  • Employees can be alerted to excessive hot-water usage, triggering awareness of waste and expense.

Even stores that are rated highly for energy use are at risk of anomalous situations that reduce their efficiency, either through fluctuating occupancy, severe weather or overlooked system changes. Predictive modeling learns from real-time data and recognizes these changes, automatically adjusting systems. This model becomes an essential part of the manager’s arsenal for monitoring and predicting energy consumption throughout a store space.

As building managers are tasked with corporate sustainability mandates for zero waste, reducing carbon emissions and lowering costs, predictive modeling software that benchmarks and continuously learns offers ease and efficiency. 

With a unified view of all commercial assets, managers can understand operating trends and asset conditions, analyze the total cost of buildings, anticipate and plan for equipment upgrades, and make real-time procurement decisions. Commercial building managers have powerful tools to help them in their roles of meeting sustainability standards and protecting a chain’s portfolio of structural assets.

Gavin Platt, VP product, Acuity Brands, is a multidisciplinary user experience designer and product leader who collaborates to build elegant, transformative products that make a lasting impact on people and the planet (https://www.acuitybrands.com/)

More Blog Posts in This Series

X
This ad will auto-close in 10 seconds