Machine learning based disaggregation of air‐conditioning loads using smart meter data

Najafi, Behzad; Narzo, Luca Di; Rinaldi, Fabio; Azimi, Reza

doi:10.1049/iet-gtd.2020.0698

Cited by 15 publications

(6 citation statements)

References 29 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Najafi et al [60] proposed another method for disaggregation of air-conditioning load from smart meter data, in which an extended pool of input features was extracted from both smart meter data and the corresponding weather conditions' dataset. Input features included calendar-based variables and features inspired by buildings' thermal behaviour (e.g.…”

Section: Traditional Methods and Shallow Algorithmsmentioning

confidence: 99%

“…Hosseini [77] shows that their suggested model performs efficiently with low-resolution data (15 minutes) in identifying most of the ESH loads (electric heaters), although the model performs inadequately in capturing the peaks and causing unwanted variations in lower demand. Najafi et al [60], however, achieved a high R2 value for recognising AC loads through the use of feature selection. High-resolution data measurements are widely used for development of disaggregation methods, but may not be applicable to hourly datasets, which are far more available and more commonly used in real-life applications.…”

Section: Evaluation Of Datasets and Requirementsmentioning

confidence: 99%

See 1 more Smart Citation

Advances in Machine-Learning Based Disaggregation of Building Heating Loads: A Review

Lien,

Najafi,

Rajasekharan

2023

Energy Informatics

Self Cite

View full text Add to dashboard Cite

This review article investigates the methods proposed for disaggregating the space heating units' load from the aggregate electricity load of commercial and residential buildings. It explores conventional approaches together with those that employ traditional machine learning, deep supervised learning and reinforcement learning. The review also outlines corresponding data requirements and examines the suitability of a commonly utilised toolkit for disaggregating heating loads from lowfrequency aggregate power measurements. It is shown that most of the proposed approaches have been applied to high-resolution measurements and that few studies have been dedicated to low-resolution aggregate loads (e.g. provided by smart meters). Furthermore, only a few methods have taken account of special considerations for heating technologies, given the corresponding governing physical phenomena. Accordingly, the recommendations for future works include adding a rigorous preprocessing step, in which features inspired by the building physics (e.g. lagged values for the ambient conditions and values that represent the correlation between heating consumption and outdoor temperature) are added to the available input feature pool. Such a pipeline may benefit from deep supervised learning or reinforcement learning methods, as these methods are shown to offer higher performance compared to traditional machine learning algorithms for load disaggregation.

show abstract

Section: Traditional Methods and Shallow Algorithmsmentioning

confidence: 99%

Section: Evaluation Of Datasets and Requirementsmentioning

confidence: 99%

Advances in Machine-Learning Based Disaggregation of Building Heating Loads: A Review

Lien,

Najafi,

Rajasekharan

2023

Energy Informatics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The following is a definition of precision: [58] 𝑃 𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛 = 𝑇 𝑃 𝑇 𝑃 + 𝐹 𝑃 (9) Recall: Attempts to respond to the question: What percentage of actual positives were correctly identified? Mathematically, recall is defined as follows [58] 𝑅𝑒𝑐𝑎𝑙𝑙 = 𝑇 𝑃 𝑇 𝑃 + 𝐹 𝑁 (10) F1 Score: The F1 score is a harmonic mean of precision and recall, with the best and worst values corresponding to 1 and 0 respectively. Precision and recall both contribute equally in terms of percentage to the F1 score.…”

Section: Metricsmentioning

confidence: 99%

“…Building performance analysis and commissioning pave the way to notable energysaving opportunities [7], reductions in emissions, and cuts in the operating costs of buildings [8]. In this context, a few works have been focused on employing machine learning-based analysis of smart meter data for disaggregating [9] the consumption of the buildings' HVAC systems [10,11], which is a key step in analyzing the performance of these units.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Based Estimation of Buildings’ Characteristics Employing Electrical and Chilled Water Consumption Data: Pipeline Optimization

Raymand

Najafi

Mamaghani³

et al. 2023

Preprint

View full text Add to dashboard Cite

“…Other previous work in individual residence HVAC load disaggregation includes a random forest machine learning model training procedure and pipeline optimization with detailed automated feature selection considering weather, calendar-based, pattern-based, statistical, etc. [25]. The model was tuned using 182 homes and tested on 10, all from the Pecan Street experimental database with an overall R 2 of 0.905 over eight days.…”

Section: Introductionmentioning

confidence: 99%

Forecast of Community Total Electric Load and HVAC Component Disaggregation through a New LSTM-Based Method

Gong

Alden

Patrick³

et al. 2022

Energies

View full text Add to dashboard Cite

The forecast and estimation of total electric power demand of a residential community, its baseload, and its heating ventilation and air-conditioning (HVAC) power component, which represents a very large portion of a community electricity usage, are important enablers for optimal energy controls and utility planning. This paper proposes a method that employs machine learning in a multi-step integrated approach. An LSTM model for total electric power at the main circuit feeder is trained using historic multi-year hourly data, outdoor temperature, and solar irradiance. New key temperature indicators, TmHAVC, corresponding to the standby zero-power operation for HVAC systems for summer cooling and winter heating are introduced using a V-shaped hourly total load curve. The trained LTSM model is additionally run with TmHVAC and zero irradiance inputs yielding an estimated baseload, which is representative of typical occupancy patterns. The HVAC power component is disaggregated as the difference between total and baseload power. Total power forecasts of an aggregated residential community as seen by major distribution lines are experimentally validated with a satisfactory MAPE error below 10% based on a 4-year dataset from a representative suburban community with more than 1800 homes in Kentucky, U.S. Discussions regarding the validity of the separation method based on combined considerations of fundamental physics, statistics, and human behavior are also included.

show abstract

Machine learning based disaggregation of air‐conditioning loads using smart meter data

Cited by 15 publications

References 29 publications

Advances in Machine-Learning Based Disaggregation of Building Heating Loads: A Review

Advances in Machine-Learning Based Disaggregation of Building Heating Loads: A Review

Machine Learning Based Estimation of Buildings’ Characteristics Employing Electrical and Chilled Water Consumption Data: Pipeline Optimization

Forecast of Community Total Electric Load and HVAC Component Disaggregation through a New LSTM-Based Method

Contact Info

Product

Resources

About