Detecting unusual customer consumption profiles in power distribution systems &amp;#x2014; APSPDCL

Babu, T. Vandana; Murthy, T. Satyanarayana; Sivaiah, B.

doi:10.1109/iccic.2013.6724264

Cited by 20 publications

(16 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Babu et al in [22] use fuzzy C-Means clustering to categorize consumers based on their consumption patterns. The difference of clustering to classification is mainly that the latter one has a training dataset where the response of the observations is already known and classifies new data.…”

Section: Artificial Intelligence-basedmentioning

confidence: 99%

Detection of Non-technical Losses in Smart Distribution Networks: A Review

Fragkioudaki

Cruz-Romero

Gómez-Expósito

et al. 2016

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

With the advent of smart grids, distribution utilities have initiated a large deployment of smart meters on the premises of the consumers. The enormous amount of data obtained from the consumers and communicated to the utility give new perspectives and possibilities for various analytics-based applications. In this paper the current smart metering-based energy-theft detection schemes are reviewed and discussed according to two main distinctive categories: A) system state-based, and B) artificial intelligence-based.

show abstract

Section: Artificial Intelligence-basedmentioning

confidence: 99%

Detection of Non-technical Losses in Smart Distribution Networks: A Review

Fragkioudaki

Cruz-Romero

Gómez-Expósito

et al. 2016

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

show abstract

“…The usage data is one-month span data which consist of 10,000 customers in order to minimize the losses in the company since the electricity payment by the customer is done monthly and the transaction of the customer's credit purchase by the company is done also per month. Therefore the determination of this time span is very relevantfor the process [7], [4].…”

Section: Identification Of Relevant Variablesmentioning

confidence: 99%

“…There have been many related works on the abuse of electrical energy usage has been proposed by previous researchers as follows . Babu,et al,in[4]used FCM to investigate nontechnical loss detection by monitoring the profile of irregular customer consumption in power distribution systems. Their Fuzzy based classification method detected non-technical losses with accuracy of 80%.Depuru, et al,in [5] proposes the detection of electricity theft through energy consumption patterns of some customers involved in the theft.…”

Section: Introductionmentioning

confidence: 99%

Identifying Irregularities Usage of Smart Electric Voucher using Support Vector Machines

Wungo¹,

Lawi²,

Hartono³

2019

Proceedings of the Proceedings of the 1st Workshop on Multidisciplinary and Its Applications Part 1, WMA-01 2018, 19-20 January

View full text Add to dashboard Cite

This paper applies machine-learning approach in identifying the irregularities of customer behaviour to the purchase transaction of smart electric vouchers. The Support Vector Machine (SVM) is used as the classification machine learning to identify the irregularities usage into two classes. The performance of the classification system is evaluated using the 10-fold cross-validation technique. Validation results are measured using accuracy, precision, and recall values. Our implementation results showed the use of SVM method gives very good performances in classifying the electrical consumption behaviour. Experimental results with different amounts of data testing indicated that the SVM method has high degree of accuracy, precision, and recall of 99 to 100%.

show abstract

“…In [28] the customer data was analyzed using an Autoregressive (AR) model so as to predict the amount of energy consumed within a specific interval and then compare the result obtained against the user's current record that is low. A technique based on diffuse clustering is proposed in [29] in which number of clusters or groups is predefined. In [30] an artificial neural network is applied to the user classification process to be inspected.…”

Section: Introductionmentioning

confidence: 99%

A Novel Rule Based Technique to Detect Electricity Theft in India

Chandel¹,

Thakur²

2019

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

It is high time to control and prevent power theft by manipulating the meter reading and tampering of the meter. It is possible to deal power theft by developing Advanced Metering Infrastructure (AMI) and smart grids. For most of the distribution companies, utility smart meters' data is serving as wealthy source of information beyond billing. There are numerous methods for detection of meter inconsistencies and dishonest behavior like meter tampering based on past data. This paper proposes a "Rule Based" electricity theft detection methodology based on the detection of abnormal readings of phase voltages, currents and power factor communicated by smart energy meters to the central server of the utility in constant time interval of fifteen minute. Individual customer theft detection rate of 94.8% is achieved with 10% False Positive Rate, which is low. The proposed method is tested on real time data collected from smart meters installed in Raipur city of Chhattisgarh State Electricity Board India.

show abstract

Detecting unusual customer consumption profiles in power distribution systems — APSPDCL

Cited by 20 publications

References 3 publications

Detection of Non-technical Losses in Smart Distribution Networks: A Review

Detection of Non-technical Losses in Smart Distribution Networks: A Review

Identifying Irregularities Usage of Smart Electric Voucher using Support Vector Machines

A Novel Rule Based Technique to Detect Electricity Theft in India

Contact Info

Product

Resources

About