Electricity theft detection using big data and genetic algorithm in electric power systems

Shehzad, Faisal; Javaid, Nadeem; Aslam, Sheraz; Javaid, Muhammad Umar

doi:10.1016/j.epsr.2022.107975

Cited by 26 publications

(24 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They are treated as outliers and are removed using the ‘TSR of thumb’. Outliers are removed using the TSR rule as mentioned in [10]

\begin{eqnarray}{\mathrm{f\ }}\left( {\mathrm{v}} \right)\ &&= \left\{ {\frac{{\frac{N}{2},\ {v}_i \in NaN,{v}_i\left( {m - 1} \right),\ {v}_i\left( {m + 1} \right) \in NaN\ }}{{0,\ {v}_i \in NaN,\ {v}_i\left( {m - 1} \right)or\ {v}_{i\ }\left( {m + 1} \right) \in NaN}}} \right\}\nonumber \\ &&{\mathrm{\ \ }}\forall {{\mathrm{v}}}_{\mathrm{i}}{\mathrm{\ and\ v}}_{\mathrm{i}} \notin {\mathrm{NaN}}\end{eqnarray}

\begin{equation*}O\left( {{v}_i,t} \right) = wi\,f\,{v}_i(\bar{t}) &gt; {v}_i(\bar{t})\;{\mathrm{otherwise}}\end{equation*}

where

\begin{equation}w = {\mathrm{avg}}\left( {{v}_i} \right)) + 2s\left( {{v}_i\left( t \right)} \right)\end{equation}

…”

Section: Methodology Proposalsmentioning

confidence: 99%

“…After filling in the missing and erroneous values and removing outlier values as also done in [10], the data values are normalized using min–max normalization.

\begin{equation}{\mathrm{N\ }}\left( {{{\mathrm{v}}}_{\mathrm{i}}\left( {\mathrm{t}} \right)} \right) = \ \frac{{{{\mathrm{v}}}_{\mathrm{i}}\left( {\mathrm{t}} \right) - \min \left( \ \right)}}{{{\mathrm{imax}}\left( {\mathrm{v}} \right) - \min \left( {\bar{v}} \right)}}\end{equation}

vi (t) is the usage of electricity at time t [10], min ( v ) is the usage of minimum electricity [10], and max( v ) is the usage of electricity at the time ( t ).…”

Section: Methodology Proposalsmentioning

confidence: 99%

“…This methodology is grounded in the principles of game theory, which involves the strategic interactions between dishonest consumers (electricity thieves) and utilities [8]. In the game theory, the objective is to attain a Nash equilibrium, whereby the actions of a dishonest consumer in attempting to steal electricity are deterred [9,10]. Employing the game theory approach presents certain advantages in terms of cost-effectiveness, albeit it poses challenges in establishing precise functions for each customer and the utility company for theft detection [8,9].…”

Section: Game Theory-based Methodsmentioning

confidence: 99%

“…By leveraging machine learning methods, utilities can leverage extensive historical data to identify the trend in electricity usage, thereby analyzing consumer behaviour effectively. Despite the integration of Advanced Metering Infrastructures (AMIs) like sensor devices, Internet of Things (IoT), and smart meters, the existing energy theft detection methods have not completely eradicated electricity theft [10]. The implementation of smart meters enables the remote sharing of consumers’ electrical energy usage.…”

Section: Related Workmentioning

confidence: 99%

See 3 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

“…They are treated as outliers and are removed using the ‘TSR of thumb’. Outliers are removed using the TSR rule as mentioned in [10]

\begin{eqnarray}{\mathrm{f\ }}\left( {\mathrm{v}} \right)\ &&= \left\{ {\frac{{\frac{N}{2},\ {v}_i \in NaN,{v}_i\left( {m - 1} \right),\ {v}_i\left( {m + 1} \right) \in NaN\ }}{{0,\ {v}_i \in NaN,\ {v}_i\left( {m - 1} \right)or\ {v}_{i\ }\left( {m + 1} \right) \in NaN}}} \right\}\nonumber \\ &&{\mathrm{\ \ }}\forall {{\mathrm{v}}}_{\mathrm{i}}{\mathrm{\ and\ v}}_{\mathrm{i}} \notin {\mathrm{NaN}}\end{eqnarray}

\begin{equation*}O\left( {{v}_i,t} \right) = wi\,f\,{v}_i(\bar{t}) &gt; {v}_i(\bar{t})\;{\mathrm{otherwise}}\end{equation*}

where

\begin{equation}w = {\mathrm{avg}}\left( {{v}_i} \right)) + 2s\left( {{v}_i\left( t \right)} \right)\end{equation}

…”

Section: Methodology Proposalsmentioning

confidence: 99%

“…After filling in the missing and erroneous values and removing outlier values as also done in [10], the data values are normalized using min–max normalization.

\begin{equation}{\mathrm{N\ }}\left( {{{\mathrm{v}}}_{\mathrm{i}}\left( {\mathrm{t}} \right)} \right) = \ \frac{{{{\mathrm{v}}}_{\mathrm{i}}\left( {\mathrm{t}} \right) - \min \left( \ \right)}}{{{\mathrm{imax}}\left( {\mathrm{v}} \right) - \min \left( {\bar{v}} \right)}}\end{equation}

vi (t) is the usage of electricity at time t [10], min ( v ) is the usage of minimum electricity [10], and max( v ) is the usage of electricity at the time ( t ).…”

Section: Methodology Proposalsmentioning

confidence: 99%

Section: Game Theory-based Methodsmentioning

confidence: 99%

Section: Related Workmentioning

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

show abstract

“…Both methods, PSO and ACO, have high computational complexity. In [31], the total electricity cost was minimized in SGs with short-term time averaged electricity cost as an objective function in GA. Another aspect of theft detection with feature engineering in SGs is presented in [32] using the GA. The dataset used was based on 4000 household records.…”

Section: Related Workmentioning

confidence: 99%

Energy Theft Detection in Smart Grids with Genetic Algorithm-Based Feature燬election

Umair¹,

Saeed²,

Saeed³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

As big data, its technologies, and application continue to advance, the Smart Grid (SG) has become one of the most successful pervasive and fixed computing platforms that efficiently uses a data-driven approach and employs efficient information and communication technology (ICT) and cloud computing. As a result of the complicated architecture of cloud computing, the distinctive working of advanced metering infrastructures (AMI), and the use of sensitive data, it has become challenging to make the SG secure. Faults of the SG are categorized into two main categories, Technical Losses (TLs) and Non-Technical Losses (NTLs). Hardware failure, communication issues, ohmic losses, and energy burnout during transmission and propagation of energy are TLs. NTL's are human-induced errors for malicious purposes such as attacking sensitive data and electricity theft, along with tampering with AMI for bill reduction by fraudulent customers. This research proposes a data-driven methodology based on principles of computational intelligence as well as big data analysis to identify fraudulent customers based on their load profile. In our proposed methodology, a hybrid Genetic Algorithm and Support Vector Machine (GA-SVM) model has been used to extract the relevant subset of feature data from a large and unsupervised public smart grid project dataset in London, UK, for theft detection. A subset of 26 out of 71 features is obtained with a classification accuracy of 96.6%, compared to studies conducted on small and limited datasets.

show abstract

VolcAshDB: a Volcanic Ash DataBase of classified particle images and features

Benet,

Costa,

Widiwijayanti

et al. 2024

Bull Volcanol

View full text Add to dashboard Cite

Volcanic ash provides unique pieces of information that can help to understand the progress of volcanic activity at the early stages of unrest, and possible transitions towards different eruptive styles. Ash contains different types of particles that are indicative of eruptive styles and magma ascent processes. However, classifying ash particles into its main components is not straightforward. Diagnostic observations vary depending on the magma composition and the style of eruption, which leads to ambiguities in assigning a given particle to a given class. Moreover, there is no standardized methodology for particle classification, and thus different observers may infer different interpretations. To improve this situation, we created the web-based platform Volcanic Ash DataBase (VolcAshDB). The database contains > 6,300 multi-focused high-resolution images of ash particles as seen under the binocular microscope from a wide range of magma compositions and types of volcanic activity. For each particle image, we quantitatively extracted 33 features of shape, texture, and color, and petrographically classified each particle into one of the four main categories: free crystal, altered material, lithic, and juvenile. VolcAshDB (https://volcash.wovodat.org) is publicly available and enables users to browse, obtain visual summaries, and download the images with their corresponding labels. The classified images could be used for comparative studies and to train Machine Learning models to automatically classify particles and minimize observer biases.

show abstract

Electricity theft detection using big data and genetic algorithm in electric power systems

Cited by 26 publications

References 34 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

Energy Theft Detection in Smart Grids with Genetic Algorithm-Based Feature燬election

VolcAshDB: a Volcanic Ash DataBase of classified particle images and features

Contact Info

Product

Resources

About