Custom Outlier Detection for Electrical Energy Consumption Data Applied in Case of Demand Response in Block of Buildings

Abstract

The aim of this paper is to provide an extended analysis of the outlier detection, using probabilistic and AI techniques, applied in a demo pilot demand response in blocks of buildings project, based on real experiments and energy data collection with detected anomalies. A numerical algorithm was created to differentiate between natural energy peaks and outliers, so as to first apply a data cleaning. Then, a calculation of the impact in the energy baseline for the demand response computation was implemented, with improved precision, as related to other referenced methods and to the original data processing. For the demo pilot project implemented in the Technical University of Cluj-Napoca block of buildings, without the energy baseline data cleaning, in some cases it was impossible to compute the established key performance indicators (peak power reduction, energy savings, cost savings, CO2 emissions reduction) or the resulted values were far much higher (>50%) and not realistic. Therefore, in real case business models, it is crucial to use outlier’s removal. In the past years, both companies and academic communities pulled their efforts in generating input that consist in new abstractions, interfaces, approaches for scalability, and crowdsourcing techniques. Quantitative and qualitative methods were created with the scope of error reduction and were covered in multiple surveys and overviews to cope with outlier detection.

Electric Energy Management in Buildings Based on the Internet of Things: A Systematic Review

“…Thus, it is understood that energy management requires reliable numbers to assess and shape energy performance [16]. Therefore, establishing an energy baseline (EBS) from the energy consumption profile is an important step in energy planning, as the EBS acts as a quantitative benchmark that provides the basis of comparison for energy performance [77].…”

“…As for monitoring energy consumption (step 3), Jurj et al [77] proposed an installed building energy management system that allows monitoring through an online visualization of energy data and the generation of local renewable energy sources. According to Moreno et al [6], real-time information about energy consumption in buildings has been largely invisible to users who have to make do with traditional energy bills.…”

“…Solutions that use real-time data on energy consumption in buildings focus on the use of historical consumption data obtained through monthly energy bills or existing databases [77]. Also evidenced in real-time measurement is the use of metering devices [16], sensors [4], and smart meters [8].…”

“…The study developed by Batlle et al [16] emphasizes the use of combined techniques of using historical consumption data and metering devices to analyze the actual consumption profile, aiming to define energy baselines through statistical analysis, considering consumption factors. Jurj et al [77] also used techniques using historical consumption data and metering devices to propose a data cleaning process to improve the quality of baseline data and the evaluation of key performance indicators.…”

Expected benefits and foreseen steps in creating energy communities in Romania

“…The buildings have different occupational characteristics and occupants' behavior, different operating regimes, different administration mode, different operating programs, and different energy use profile. The testing scenarios included voluntary involvement of students, academic and administrative staff [2].…”