Based on current global energy consumption, world energy demand is set to increase by 50 percent by 2030. In the U.S. alone, it is estimated that residential and commercial buildings will consume over 41 percent of the total energy production. It is therefore no surprise that investments in Energy Management Systems (EMS) for commercial buildings are expected to touch $67 billion by 2020.
Energy usage and costs are crucial components of effective building management, and as a result, organizations today need a more data-driven energy management plan. Leveraging analytics can help them identify usage patterns and areas for improvement and make more informed decisions on energy usage.
Energy Management System: for achieving targeted energy usage goals
Energy Management Systems encompasses multiple functions such as heating, ventilation, air-conditioning, and refrigeration. For a given set of environmental conditions such as ambient temperature and humidity, the chiller or heating capacity must function optimally, to hit the targeted energy usage goals.
In such a scenario, analytics can be used to compare the previous and actual energy usage against a defined benchmark. Analytical models can automatically calculate the efficiency curves across the entire operating range for all assets. Moreover, by using various types of sensors, it is now possible to conduct non-intrusive and automated measurements. This helps organizations evaluate the health of each element of the chiller unit, such as actuators, valves, and controllers. It also enables them to carry out preventive maintenance to minimize downtime.
Optimizing energy usage through analytical scorecards
A set of analytical scorecards can be employed to evaluate real-time data from multiple sources. For example, one set of scorecards could record the environmental conditions of the building and relay information to the Energy Management Systems. This, in turn, computes the operational parameters of the chiller and maintains the corresponding water temperature.
The other set of scorecards can be used to record details regarding occupancy patterns and levels, and the number of blowers in operation. This helps evaluate the amount of energy required to maintain a specific temperature in the room.
Forecasting energy consumption
Analytics can be used to deploy a causal model to accurately forecast the future energy requirement. Inputs from historical data can be used to forecast loads based on geography and weather conditions. This helps in managing the run time of each Energy Management System element, thereby optimizing usage and limiting functional wear-and-tear.
Controlling demand charges
The demand charge is related to the peak usage for a predetermined time period and often contributes significantly to the energy bill. It is therefore critical to estimate demand loads and minimize peak loads. As the volume of data increases, analytical solutions can be deployed to leverage data collected by sensors, actuators, and controllers. This data can be used to understand consumption patterns at a granular level across devices, predict and benchmark energy usage, and gain better control over demand charges.
With the rising cost of commercial energy, smart energy management systems are likely to gain widespread adoption in commercial buildings. The use of predictive analytical models and reports can help organizations gain a better understanding of the underlying efficiency drivers. Forecasting and tracking energy consumption empowers them to make more informed decisions regarding energy and cost-saving measures.
What is your organization’s strategy to optimize energy consumption?
This article is published in collaboration with Tata Consultancy Services. Publication does not imply endorsement of views by the World Economic Forum.
To keep up with the Agenda subscribe to our weekly newsletter.
Author: Akhil Bhardwaj is a Senior Manager in the Analytics and Insights division of Tata Consultancy Services.
