Automated data mining framework for building energy conservation aided by generative pre-trained transformers (GPT)

Data mining technologies have showed promising capabilities in extracting building operation patterns from massive amounts of building operational data for energy conservation. However, the number of the extracted operation patterns is always large. It is time-consuming and tedious for users to find valuable operation patterns among them. To overcome this barrier, this study proposes an automated data mining framework based on maximal frequent itemset mining and generative pre-trained transformers (GPT). An improved maximal frequent itemset mining-based data mining method is developed to extract non-redundant operation patterns from numerous building operational data for reducing the number of the extracted operation patterns. A template-based prompt generation method is proposed to transform the extracted operation patterns into prompts. The prompts are inputted into GPT to determine whether there are energy waste patterns hidden in the extracted operation patterns. It liberates humans from the tedious work on analyzing the extracted operation patterns. The framework is applied to analyze the one-year operational data from a real-world building chiller plant system for verifying its performance. Most of the energy waste patterns in this system are detected successfully, such as valve faults, low chilled water outlet temperature, small chilled and cooling water temperature differences, and improper coordinated control among devices. The detection accuracy of GPT is 89.17 % for energy waste patterns and 99.48 % for normal operation patterns. The response time and cost of GPT are 6747.60 s and $17.68, respectively.