Reshaping Consumption Habits by Exploiting Energy-Related Micro-moment Recommendations: A Case Study

Sardianos, Christos; Varlamis, Iraklis; Chronis, Christos; Dimitrakopoulos, George; Alsalemi, Abdullah; Himeur, Yassine; Bensaali, Fayçal; Amira, Abbes

doi:10.1007/978-3-030-68028-2_4

Cited by 11 publications

(24 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Visualizing trend in data using rolling means: Trend is the smooth long‐term tendency of a time series. It might change direction (increase or decrease) as time progresses [26–30]…”

Section: Methodology Proposalsmentioning

confidence: 99%

“…Features are extracted to add additional parameters from the existing to capture relevant patterns or relationships. Relevant features can enhance the efficiency and reliability of electricity theft detecting model [26,27]. Various features collected directly and extracted using statistical functions include Consumer specific unique ID, electricity usage time and date (Timestamp), electricity consumption (kWh), active power, reactive power, average voltage, global intensity, power factor, max_load, min_load, average_load, load dispersion, peak demand, total load profile, seasonal variation, time-ofuse, historical consumption, socio-demographic data, billing information, geographic information, time of day usage, weekday/weekend, and state holiday.…”

Section: Feature Engineeringmentioning

confidence: 99%

“…The focus is on understanding the consumption patterns, identifying anomalies or deviations specific to each consumer, and detecting any unusual behaviour or theft within their consumption data. This approach allows analysis for finding the unique characteristics and consumption patterns of each consumer [26][27][28]. Data aggregation is performed on data consumption over different periods (daily, weekly, monthly).…”

Section: Feature Engineeringmentioning

confidence: 99%

See 2 more Smart Citations

Using machine learning ensemble method for detection of energy theft in smart meters

Kawoosa,

Prashar,

Faheem

et al. 2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

Electricity theft is a primary concern for utility providers, as it leads to substantial financial losses. To address the issue, a novel extreme gradient boosting (XGBoost)‐based model utilizing the consumers’ electricity consumption patterns for analysis is proposed for electricity theft detection (ETD). To remove the imbalance in the real‐world electricity consumption dataset and ensure an even distribution of theft and non‐theft data instances, six different artificially created theft attacks were used. Moreover, the utilization of the XGBoost algorithm for classification, especially to identify malicious instances of electricity theft, yielded commendable accuracy rates and a minimal occurrence of false positives. The proposed model identifies electricity theft specific to the regions, utilizing electricity consumption parameters, and other variables as input features. The authors’ model outperformed existing benchmarks like k‐neural networks, light gradient boost, random forest, support vector machine, decision tree, and AdaBoost. The simulation results using the false attacks for balancing the dataset have improved the proposed model's performance, achieving a precision, recall, and F1‐score of 96%, 95%, and 95%, respectively. The results of the detection rate and the false positive rate (FPR) of the proposed XGBoost‐based detection model have achieved 96% and 3%, respectively.

show abstract

“…Visualizing trend in data using rolling means: Trend is the smooth long‐term tendency of a time series. It might change direction (increase or decrease) as time progresses [26–30]…”

Section: Methodology Proposalsmentioning

confidence: 99%

Section: Feature Engineeringmentioning

confidence: 99%

Section: Feature Engineeringmentioning

confidence: 99%

See 1 more Smart Citation

Using machine learning ensemble method for detection of energy theft in smart meters

Kawoosa,

Prashar,

Faheem

et al. 2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

show abstract

“…Inertia represents the combination of the effect of treating gains differently from losses, giving greater weight to specific outcomes compared to uncertain outcomes, and reducing regret [83,84]. Habits and routines shape the behavior of individuals and organizations [85,86] and it is usually difficult to change behavior because individuals strive to prevent changes in the environment [87]. If the behavior and culture of the group has an environmental commitment, there is less inertia in using energy-efficient technologies and implementation takes less time and costs less [38,88].…”

Section: The Behavioral Perspectivementioning

confidence: 99%

“…Interviewees highlighted that there is resistance among individuals to invest in energy efficiency measures. This is related to the habits and routines formed by individuals and organizational behavior [85,86] and it is usually difficult to change behavior in the short term because individuals strive to prevent changes in the environment [87].…”

Section: Ranking Of Isy' Barriersmentioning

confidence: 99%

The Development of a Transdisciplinary Framework to Overcome Energy Efficiency Barriers in Shipbuilding: A Case Study for an Iranian Shipyard

Vakili

Ölçer

Schönborn

2021

JMSE

View full text Add to dashboard Cite

Through a systematic literature review and a holistic perspective, the study proposes a conceptual transdisciplinary framework to overcome energy efficiency barriers during the shipbuilding phase. The process of the proposed transdisciplinary framework consists of five steps of “goal formation”, “system analyzing”, “scenario construction”, “multi-criteria decision making assessment” and “strategy building” to identify and rank the energy efficiency barriers during ship construction based on decision makers’ priorities. The framework categorizes the barriers into five disciplines—operations, policies and regulations, technology and innovation, the human elements, and economics—and the framework is applied to an Iranian shipyard. The results show that the economic barriers have the greatest impact, while the human barriers have the least impact on the shipyard’s energy performance. Due to the generalized structure of the framework, it categorizes not only energy efficiency barriers according to the importance and priorities of stakeholders in the shipbuilding industry, but can also be applied to other phases of the ship life cycle and even to other industries. By applying the framework, decision-makers can make rational and optimal decisions to be able to invest in energy efficiency measures based on their priorities.

show abstract

Smart power consumption abnormality detection in buildings using micromoments and improved K‐nearest neighbors

et al. 2021

Self Cite

View full text Add to dashboard Cite

Anomaly detection in energy consumption is a crucial step towards developing efficient energy saving systems, diminishing overall energy expenditure and reducing carbon emissions. Therefore, implementing powerful techniques to identify anomalous consumption in buildings and providing this information to end‐users and managers is of significant importance. Accordingly, two novel schemes are proposed in this paper; the first one is an unsupervised abnormality detection based on one‐class support vector machine, namely UAD‐OCSVM, in which abnormalities are extracted without the need of annotated data; the second is a supervised abnormality detection based on micromoments (SAD‐M2), which is implemented in the following steps: (i) normal and abnormal power consumptions are defined and assigned; (ii) a rule‐based algorithm is introduced to extract the micromoments representing the intent‐rich moments, in which the end‐users make decisions to consume energy; and (iii) an improved K‐nearest neighbors model is introduced to automatically classify consumption footprints as normal or abnormal. Empirical evaluation conducted in this framework under three different data sets demonstrates that SAD‐M2 achieves both a highest abnormality detection performance and real‐time processing capability with considerably lower computational cost in comparison with other machine learning methods. For instance, up to 99.71% accuracy and 99.77% F1 score have been achieved using a real‐world data set collected at the Qatar University energy lab.

show abstract

Reshaping Consumption Habits by Exploiting Energy-Related Micro-moment Recommendations: A Case Study

Cited by 11 publications

References 30 publications

Using machine learning ensemble method for detection of energy theft in smart meters

Using machine learning ensemble method for detection of energy theft in smart meters

The Development of a Transdisciplinary Framework to Overcome Energy Efficiency Barriers in Shipbuilding: A Case Study for an Iranian Shipyard

Smart power consumption abnormality detection in buildings using micromoments and improved K‐nearest neighbors

Contact Info

Product

Resources

About