eprintid: 10141464 rev_number: 12 eprint_status: archive userid: 608 dir: disk0/10/14/14/64 datestamp: 2022-01-10 12:04:16 lastmod: 2022-01-10 12:04:16 status_changed: 2022-01-10 12:04:16 type: proceedings_section metadata_visibility: show creators_name: Bentley, PJ creators_name: Lim, SL creators_name: Jindal, S creators_name: Narang, S title: Generating synthetic energy usage data to enable machine learning for sustainable accommodation ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F48 keywords: Correlation, Mechatronics, Digital twin, Computational modeling, Machine learning, Tools, Generators note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: Machine Learning has the potential to discover new correlations between energy usage in apartments and variables such as seasonality, apartment location, size, efficiency and details of those staying in the apartments, thus helping apartments to become more sustainable and helping those who stay in them to use less energy. The biggest impedance to creating such ML tools is lack of viable data - without the data, the tools cannot be created - yet it is not feasible to wait for several years' worth of good data before creating the tools. Here we present a solution to this problem: the use of a digital twin to generate synthetic data. This approach is viable even when there is no existing data, but when expert knowledge about the relationship between systems exist. To achieve this, we develop a new agent-based synthetic data generator (ASDG) and explore a case study with a corporate housing and luxury alternate accommodation marketplace called TheSqua.re. We show that unlimited quantities of realistic data can be automatically generated, including data for different scenarios, and that it can be used by Machine Learning to discover the underlying correlations. date: 2021-11-13 date_type: published publisher: IEEE official_url: https://doi.org/10.1109/ICECCME52200.2021.9591016 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1907598 doi: 10.1109/ICECCME52200.2021.9591016 isbn_13: 9781665412629 lyricists_name: Bentley, Peter lyricists_name: Lim, Soo lyricists_id: PJBEN84 lyricists_id: SLLIM63 actors_name: Bentley, Peter actors_id: PJBEN84 actors_role: owner full_text_status: public publication: International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021 place_of_pub: Mauritius, Mauritius event_title: 2021 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) book_title: 2021 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) citation: Bentley, PJ; Lim, SL; Jindal, S; Narang, S; (2021) Generating synthetic energy usage data to enable machine learning for sustainable accommodation. In: 2021 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME). IEEE: Mauritius, Mauritius. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10141464/1/ICECCME_v10.pdf