| Title |
Mining typical load profiles in buildings to support energy management in the smart city context |
| ID_Doc |
38996 |
| Authors |
Capozzoli, A; Piscitelli, MS; Brandi, S |
| Title |
Mining typical load profiles in buildings to support energy management in the smart city context |
| Year |
2017 |
| Published |
|
| Abstract |
Mining typical load profiles in buildings to drive energy management strategies is a fundamental task to be addressed in a smart city environment. In this work, a general framework on load profiles characterisation in buildings based on the recent scientific literature is proposed. The process relies on the combination of different pattern recognition and classification algorithms in order to provide a robust insight of the energy usage patterns at different levels and at different scales (from single building to stock of buildings). Several implications related to energy profiling in buildings, including tariff design, demand side management and advanced energy diagnosis are discussed. Moreover, a robust methodology to mine typical energy patterns to support advanced energy diagnosis in buildings is introduced by analysing the monitored energy consumption of a cooling/heating mechanical room. (C) 2017 The Authors. Published by Elsevier Ltd. |
| PDF |
https://doi.org/10.1016/j.egypro.2017.09.545
|
