A new approach to operating a building’s cooling system using machine learning techniques and Internet of Things (IoT) data can help to drive down energy consumption and costs, as the global demand for energy increases.
The buildings sector is one of the largest energy-consuming entities, accounting for a staggering 40 percent of global energy consumption today1. What makes this statistic grim is that building energy consumption is projected to increase by 50 percent by 2050, unless energy efficiency strategies are actively embraced to curb the growth. To put this in perspective, the 50 percent increase is equivalent to the combined energy consumption of Russia and India today2. Global pressure for improving environmental sustainability, combined with increasing electricity prices across several nations worldwide, are pushing corporations to reduce the energy consumption incurred in operating their buildings.
Heating, ventilation and air-conditioning (HVAC) systems dominate energy usage in commercial buildings, accounting for between 40 percent and 70 percent of the total building electricity consumption3. The International Energy Agency expects that the demand for space cooling will increase three-fold between 2010 and 20502. We must design new techniques now for improving the energy efficiency of HVAC systems and ultimately pave the way for reducing overall building energy consumption, carbon footprint and operating electricity costs.
Predicting HVAC energy efficiency
I collaborated with an international team of researchers to develop a novel data-driven approach for operating a building’s HVAC system. Specifically, we used machine learning techniques on IoT sensor data spanning 4 years from 3 large commercial buildings located in downtown Hong Kong. One of them is a 27-storey office building called Two Pacific Place, shown in Fig. 1. We sought to accurately predict the energy efficiency of HVAC chillers, typically referred to as the coefficient of performance (COP). We then showed that driving HVAC chiller operation using these COP predictions can lower the electricity consumption and costs associated with cooling the buildings by an average 30 percent, as shown in Fig 2. We published these results at the highly selective ACM International Conference on Future Energy Systems (ACM e-Energy) in Germany in June 2018. The paper also received the prestigious Best Paper Award at the conference, highlighting the significant interest in this area of research and its potential impact on improved environmental sustainability in the commercial buildings sector.
Pre-cooling to reduce energy consumption
This work complements an earlier project in which we collaborated with Townsville City Council to develop a novel data-driven pre-cooling methodology for reducing the peak demand, energy consumption and electricity bills associated with HVAC cooling in commercial buildings. We built a thermal model, underpinned by IoT sensor data and machine learning techniques, to predict the temperature evolution inside a building, taking into consideration the impact of weather and occupancy. We then showed that cooling a building systematically, in advance of expected increase in occupancy (i.e. pre-cooling), is able to lower the cooling energy and cost footprints by up to 30 percent. We published these results at the ACM e-Energy conference in Hong Kong in May 2017.
It may come as a surprise that the adoption of these technologies into buildings or cities would not require any major capital expense, as much of the IoT sensor data is readily available from any modern building management system. Real-world deployment would be simple and straightforward, offering a low-cost means for reducing the energy and cost footprints of buildings. These solutions not only make good business sense in terms of reducing building operating costs, they also will be critical to more sustainable energy usage across the globe.
I firmly believe that these research contributions, which harness the potential of IoT sensor data to realise energy and cost savings, can play a key role in making the world a better place, one building at a time.
- United Nations Environment Programme, “Sustainable Buildings.”
- International Energy Agency, “Transition to Sustainable Buildings: Strategies and Opportunities to 2050.”
- Energy Exchange, Government of Australia, “Heating and Cooling.”
The post IoT and Machine Learning to Reduce Energy Use in Cooling Systems appeared first on IBM Blog Research.