Data Driven Chiller Sequencing for Reducing HVAC Electricity Consumption in Commercial Buildings

• DOI: 10.1145/3208903.3208913
• Publication Date: 2018-05-25T16:02:26Z
• Authors: Zimu Zheng; Qiong Chen; Cheng Fan; Nan Guan; Arun Vishwanath; Dan Wang; Fangming Liu
• Keywords: Chiller; Chiller boiler system; Cooling load

It is well-known that the HVAC (heating, ventilation and air conditioning) dominates electricity consumption in commercial buildings. Alongside, prices are increasing several nations around world, putting pressure on facility managers to reduce incurred operating their In this paper, we focus one of core problems building operation, namely chiller sequencing for reducing consumption. Our contributions threefold. First, make a case why it important quantify performance profile chiller, coefficient (COP), at runtime, by developing data-driven COP estimation methodology. Second, show predicting accurately non-trivial problem, requiring considerable computation time. To overcome barrier, develop dominant-graph based prediction technique time-constrained algorithm integrating predictions, which strikes good balance between reduction ease use real-world deployment. Finally, evaluate our scheme applying data, spanning 4 years, obtained from multiple chillers across 3 large buildings Hong Kong. The results solution able save average 21 MWh each buildings, an improvement over 30% compared current mode operation We offer framework under time constraints as effective practical mechanism associated with