Endorsing domestic energy saving behavior using micro-moment classification

Alsalemi, Abdullah; Ramadan, Mona; Bensaali, Fayçal; Amira, Abbes; Sardianos, Christos; Varlamis, Iraklis; Dimitrakopoulos, George

doi:10.1016/j.apenergy.2019.05.089

Cited by 42 publications

(22 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following the micro‐moments based recommendation strategy , 34 the proposed system first detects micro‐moments of special meaning to the daily user routine. In terms of an energy efficiency recommendation system, 7,35,36 this involves the identification of user’s habitual actions, the analysis of the conditions that hold and the prediction of when actions will happen. For example, learn when the user turns the A/C on or off, in terms of time, environmental conditions, such as temperature and humidity (inside and outside).…”

Section: Proposed Methodologymentioning

confidence: 99%

The emergence of explainability of intelligent systems: Delivering explainable and personalized recommendations for energy efficiency

et al. 2020

Self Cite

View full text Add to dashboard Cite

Section: Proposed Methodologymentioning

confidence: 99%

The emergence of explainability of intelligent systems: Delivering explainable and personalized recommendations for energy efficiency

et al. 2020

Self Cite

View full text Add to dashboard Cite

“…-An anomaly detection dataset based on real data with its ground-truth labels is generated based on an experimental campaign performed at Qatar University Energy Lab, namely Qatar University dataset (QUD), in order to test and validate the proposed anomaly detection system. In addition, two other existing datasets, namely Dutch Residential Energy Dataset (DRED) [38] and Power Consumption Simulated Dataset (PCSiD) [39], are also considered in this study. Accordingly, their ground-truths are also generated and used to investigate the performance of the proposed solution.…”

Section: Paper Contributionsmentioning

confidence: 99%

“…In addition, consumption profiles of individual devices from five other households were collected at a sampling rate of 6 s for various collection periods varying from 39 to 655 days. And besides, in [39], the PCSiD (http://em3.i-know.org/datasets/) was proposed, which was conceived based on data generation of hourly consumption profiles for a period of 2 years at a device level. Device's manufacturer specifications were used to define power consumption patterns of each appliance in watts.…”

Section: Energy Consumption Datasetsmentioning

confidence: 99%

“…Alongside two kinds of datasets used in the evaluation process are the realistic datasets including QUD and DRED datasets, which are produced through measurement campaigns and the PCSiD repository already described in [39], which is a simulated dataset. In the empirical evaluation, the accuracy of each classifier is investigated using a 10-fold cross-validation arrangement.…”

Section: Performance Measurementioning

confidence: 99%

See 1 more Smart Citation

A Novel Approach for Detecting Anomalous Energy Consumption Based on Micro-Moments and Deep Neural Networks

et al. 2020

Self Cite

View full text Add to dashboard Cite

Nowadays, analyzing, detecting, and visualizing abnormal power consumption behavior of householders are among the principal challenges in identifying ways to reduce power consumption. This paper introduces a new solution to detect energy consumption anomalies based on extracting micro-moment features using a rule-based model. The latter is used to draw out load characteristics using daily intent-driven moments of user consumption actions. Besides micro-moment features extraction, we also experiment with a deep neural network architecture for efficient abnormality detection and classification. In the following, a novel anomaly visualization technique is introduced that is based on a scatter representation of the micro-moment classes, and hence providing consumers an easy solution to understand their abnormal behavior. Moreover, in order to validate the proposed system, a new energy consumption dataset at appliance level is also designed through a measurement campaign carried out at Qatar University Energy Lab, namely, Qatar University dataset. Experimental results on simulated and real datasets collected at two regions, which have extremely different climate conditions, confirm that the proposed deep micro-moment architecture outperforms other machine learning algorithms and can effectively detect anomalous patterns. For example, 99.58% accuracy and 97.85% F1 score have been achieved under Qatar University dataset. These promising results establish the efficacy of the proposed deep micro-moment solution for detecting abnormal energy consumption, promoting energy efficiency behaviors, and reducing wasted energy.

show abstract

“…After analyzing and exploring the energy consumption databases used in the validation process, the primary issue that might exist is micro-moment class imbalance [25]. Class imbalance commonly reveals an inequitable partition of variables over classes within the database.…”

Section: A Ensemble Bagged Treesmentioning

confidence: 99%

Achieving Domestic Energy Efficiency Using Micro-Moments and Intelligent Recommendations

et al. 2020

Self Cite

View full text Add to dashboard Cite

Excessive domestic energy usage is an impediment towards energy efficiency. Developing countries are expected to witness an unprecedented rise in domestic electricity in the forthcoming decades. A large amount of research has been directed towards behavioral change for energy efficiency. Thus, it is prudent to develop an intelligent system that combines the proper use of technology with behavior change research in order to sustainably transform end-user behavior at a large scale. This paper presents an overview of our AI-based energy efficiency framework for domestic applications and explains how micro-moments can provide an accurate understanding of user behavior and lead to more effective recommendations. Micromoments are short-term events at which an energy-saving recommendation is presented to the consumer. They are detected using a variety of sensing modules placed at prominent locations in the household. A supervised machine learning classifier is then used to analyze the acquired micro-moments, identify abnormalities, and formulate a list of energy-saving recommendations. Each recommendation is presented through the end-user mobile application. The results so far include a mobile application in the front-end and a set of sensing modules in the backend that comprise, an ensemble bagging-trees micro-moment classifier (achieving up to 99.64% accuracy and 98.8% F-score), and a recommendation engine.

show abstract

Endorsing domestic energy saving behavior using micro-moment classification

Cited by 42 publications

References 27 publications

The emergence of explainability of intelligent systems: Delivering explainable and personalized recommendations for energy efficiency

The emergence of explainability of intelligent systems: Delivering explainable and personalized recommendations for energy efficiency

A Novel Approach for Detecting Anomalous Energy Consumption Based on Micro-Moments and Deep Neural Networks

Achieving Domestic Energy Efficiency Using Micro-Moments and Intelligent Recommendations

Contact Info

Product

Resources

About