SlideShare a Scribd company logo
1 of 21
โ€œElectricity Theft Detectionโ€
1
Contents
1. Introduction of project
2. Problem statement
3. Scope of project
4. Methodology
5. Literature Survey
6. Propose System
7. System Architecture
8. Limitations, advantage, disadvantage
9. Conclusion
Project Group No: 38 ELECTRICITY THEFT DETECTION 2
Introduction of project
โ€ข Many electric utilities have financial loss due to electricity theft.
โ€ข Here are various types of electrical power theft, including Tapping a line or bypassing the
energy meter.
โ€ข According to a study [citation needed], 80% of worldwide theft occurs in private dwellings
and 20% on commercial and industrial premises.
โ€ข From user fundamental data it is easy task to analyze user behavior.
โ€ข we implement a supervised ML-based theft detection model that identifies whether an
abnormal/fraudulent usage pattern has occurred in the SG(smart grid)meter.
Problem Statement
โ€ข India loses more money to theft than any other country in the world.
โ€ข In this proposed system we use dataset having electricity usage of a smart grid (SG) meter
(or simply smart meter).
โ€ข Using this dataset we does feature selection and preprocessing on dataset.
โ€ข When we have large number of features in dataset then feature selection is very important
part in our Machine Learning.
โ€ข As we use feature selection it gives us most important feature and this feature selection
gives us more accuracy.
Scope of Project
โ€ข Cost-Benefit Analysis
โ€ข Risk Assessment And solutions
โ€ข Control Efficiency And Services
โ€ข Timeline Estimations And optimizing resources
โ€ข Scope of project includes we can use this in electricity utilities.
โ€ข to save Electricity
โ€ข The project model reduces the manual manipulation work and theft.
โ€ข The government saves the money by the control of theft in energy and also beneficial for
customer side and the government side.
โ€ข The metering IC ensures the accurate and reliable measurement of power consumed. Cost
wise low
Methodology
โ€ข In this proposed system we use dataset having electricity usage of a smart meter.
โ€ข Using this dataset we does feature selection and preprocessing on dataset.
โ€ข When we have large number of features in dataset then feature selection is very important part in our
Machine Learning.
โ€ข As we use feature selection it gives us most important feature and this feature selection gives us more
accuracy.
โ€ข Then we perform the preprocessing on that data.
โ€ข After that we use the superiority of XGBoost, a gradient boosting classifier (GBC), over other ML
algorithms for nontechnical loss (NTL) detection
โ€ข Gradient boosting is called gradient boosting because it uses a gradient descent algorithm to minimize
loss when adding new trees.
โ€ข This approach supports both regression and classification predictive
Literature Survey
Sr.NO Title Of The
Project
Year Method Metric Used Usage
1 PPETD: Privacy-
Preserving
Electricity Theft
Detection Scheme
with Load
Monitoring and
Billing for AMI
Networks.
2019 CNN-GRU algorithm Accuracy of theft
detection is 93.2%
Used to classify normal users
and electricity thefts.
2 Electricity theft
detection based on
extreme gradient
boosting in AMI
2020 SVM Algorithm Accuracy of 89.2% To detect electricity thefts
among dataset.
3 Electricity theft
detection in AMI
Based on Clustering
and local Outlier
Factor.
2021 Using Clustering and Local
Outlier Factor(LOF)
Nearly 12% people
in area were
electricity thefts on
average.
To reduce losses due to
electricity thefts.
Literature Survey
Sr. No Title Of The
Project
Year Method Metric Used Usage
4 Deep Attention-
based Neural
Network for
Electricity Theft
Detection
2020 CNN(Deep
Learning )
Accuracy of theft
detection is more
than 90%
To make electricity theft
detection system more
effective.
5 Research and
Implementation of
Current Detection
Technology for
Electricity Stealing
and Omission .
2021 XGBoost
Algorithm
Accuracy of 87.2%
and 83.5 on
training and testing
data.
To detect electricity thefts
among dataset.
Proposed System
โ€ข India loses more money to theft than any other country in the world.
โ€ข In this proposed system we use dataset having electricity usage of a smart grid (SG) meter
(or simply smart meter).
โ€ข Using this dataset we does feature selection and preprocessing on dataset.
โ€ข When we have large number of features in dataset then feature selection is very important
part in our Machine Learning.
Project Group No: 38 ELECTRICITY THEFT DETECTION 9
System Architecture
Project Group No: 38 ELECTRICITY THEFT DETECTION 10
ELECTRICITY THEFT DETECTION 11
Data Flow Diagram
ELECTRICITY THEFT DETECTION 12
โ€ข Activity:
ELECTRICITY THEFT DETECTION 13
UML Diagram
โ€ข Sequence:
ELECTRICITY THEFT DETECTION 14
โ€ข Usecase:
ELECTRICITY THEFT DETECTION 15
โ€ข Component
ELECTRICITY THEFT DETECTION 16
Limitations
โ€ข Billing system fails if no GSM network coverage.
โ€ข Charges may be applicable for network use.
โ€ข Requires fixed GSM number.
Advantages
โ€ข This method reduce energy wastage save lot of energy for future use.
โ€ข We can detect the location from where the power is being stolen which was not possible
before.
โ€ข Customized rates and billing dates.
โ€ข Accurate information from network load to optimize maintenance and investigation.
Disadvantages
โ€ข If Implemented on large scale it may take a lot of time and manual input
โ€ข It is not Capable of Detecting the exact location
โ€ข It is costly
Conclusion
Project Group No: 38 ELECTRICITY THEFT DETECTION
โ€ข It helps electricity utilities to detect electricity theft and they will not have to bare loss.
โ€ข This proposed system detects the electricity theft using xg boost machine learning
method.
โ€ข However, Light GBM appeared to be the fastest classifier.
โ€ข This proposed system helps to electricity utilities to detect electricity theft and they will not
have to bare loss. This is most important application of this project.
20
References
Project Group No: 38 ELECTRICITY THEFT DETECTION
1.J. Nagi, K. Yap, S. Tiong, S. Ahmed, and M. Mohamad, โ€œNontechnical loss de-
tection for metered customers in power utility using support vector machines,โ€
IEEE Transactions on Power Delivery, vol. 25, no. 2, pp. 1162โ€“1171, 2010,
cited By 104.
2 .S. McLaughlin, D. Podkuiko, and P. McDaniel, โ€œEnergy theft in the advanced
metering infrastructure,โ€ Lecture Notes in Computer Science (including sub-
series Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinfor-
matics), vol. 6027 LNCS, pp. 176โ€“187, 2010, cited By 99.
3. G. Tsekouras, N. Hatziargyriou, and E. Dialynas, โ€œTwostage pattern recogni-
tion of load curves for classification of electricity customers,โ€ IEEE Transac-
tions on Power Systems, vol. 22, no. 3, pp. 1120โ€“1128, 2007, cited By 122.
[Online].
4. Y. Zhang, W. Chen, and J. Black, โ€œAnomaly detection in premise energy con-
sumption data,โ€ 2011, cited By 12. [Online].
5. S. Dua and X. Du, Data Mining and Machine Learning in Cybersecurity, 1st
ed. Boston, MA, USA: Auerbach Publications, 2011.
21

More Related Content

Similar to 22CS339- Electricity Theft Final Updated PPT (2).pptx

Project_PPTasdfghjklmnbvcxzwertyuioplkjhffdddsxcbnnn.pptx
Project_PPTasdfghjklmnbvcxzwertyuioplkjhffdddsxcbnnn.pptxProject_PPTasdfghjklmnbvcxzwertyuioplkjhffdddsxcbnnn.pptx
Project_PPTasdfghjklmnbvcxzwertyuioplkjhffdddsxcbnnn.pptx
Geetha982072
ย 
Technologies used in Smart grids for power distribution
Technologies used in Smart grids for power distributionTechnologies used in Smart grids for power distribution
Technologies used in Smart grids for power distribution
Raja Larik
ย 

Similar to 22CS339- Electricity Theft Final Updated PPT (2).pptx (20)

Batch-C10.pptx
Batch-C10.pptxBatch-C10.pptx
Batch-C10.pptx
ย 
IRJET- Automated Energy Metering System
IRJET- Automated Energy Metering SystemIRJET- Automated Energy Metering System
IRJET- Automated Energy Metering System
ย 
Smart grid Intro
Smart grid IntroSmart grid Intro
Smart grid Intro
ย 
Simulation of Smart Meter Using Proteus software for Smart Grid
Simulation of Smart Meter Using Proteus software for Smart GridSimulation of Smart Meter Using Proteus software for Smart Grid
Simulation of Smart Meter Using Proteus software for Smart Grid
ย 
IRJET-Simulation of Smart Meter Using Proteus software for Smart Grid
IRJET-Simulation of Smart Meter Using Proteus software for Smart GridIRJET-Simulation of Smart Meter Using Proteus software for Smart Grid
IRJET-Simulation of Smart Meter Using Proteus software for Smart Grid
ย 
IRJET- Power Theft Detection using Probabilistic Neural Network Classifier
IRJET- Power Theft Detection using Probabilistic Neural Network ClassifierIRJET- Power Theft Detection using Probabilistic Neural Network Classifier
IRJET- Power Theft Detection using Probabilistic Neural Network Classifier
ย 
journal about operation management
journal about operation managementjournal about operation management
journal about operation management
ย 
Technical Writting.pptx
Technical Writting.pptxTechnical Writting.pptx
Technical Writting.pptx
ย 
Applications of big data in electrical energy system
Applications of big data  in electrical energy systemApplications of big data  in electrical energy system
Applications of big data in electrical energy system
ย 
PA group 4.pptx
PA group 4.pptxPA group 4.pptx
PA group 4.pptx
ย 
Importance of Measurements in Smart Grid
Importance of Measurements in Smart GridImportance of Measurements in Smart Grid
Importance of Measurements in Smart Grid
ย 
Smart grid control
Smart grid controlSmart grid control
Smart grid control
ย 
IRJET- IOT Based Residence Energy Control System
IRJET- IOT Based Residence Energy Control SystemIRJET- IOT Based Residence Energy Control System
IRJET- IOT Based Residence Energy Control System
ย 
Smart grid journey
Smart grid journey Smart grid journey
Smart grid journey
ย 
IRJET - Smart Street Light System using IoT
IRJET - Smart Street Light System using IoTIRJET - Smart Street Light System using IoT
IRJET - Smart Street Light System using IoT
ย 
Project_PPTasdfghjklmnbvcxzwertyuioplkjhffdddsxcbnnn.pptx
Project_PPTasdfghjklmnbvcxzwertyuioplkjhffdddsxcbnnn.pptxProject_PPTasdfghjklmnbvcxzwertyuioplkjhffdddsxcbnnn.pptx
Project_PPTasdfghjklmnbvcxzwertyuioplkjhffdddsxcbnnn.pptx
ย 
Smartgrid by suraj mishra37
Smartgrid by suraj mishra37Smartgrid by suraj mishra37
Smartgrid by suraj mishra37
ย 
Design a Talking Energy Meter based on Microcontroller
Design a Talking Energy Meter based on MicrocontrollerDesign a Talking Energy Meter based on Microcontroller
Design a Talking Energy Meter based on Microcontroller
ย 
Smart Grid Future Of Electrical System
Smart Grid Future Of Electrical SystemSmart Grid Future Of Electrical System
Smart Grid Future Of Electrical System
ย 
Technologies used in Smart grids for power distribution
Technologies used in Smart grids for power distributionTechnologies used in Smart grids for power distribution
Technologies used in Smart grids for power distribution
ย 

Recently uploaded

+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
Health
ย 
CHEAP Call Girls in Pushp Vihar (-DELHI )๐Ÿ” 9953056974๐Ÿ”(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )๐Ÿ” 9953056974๐Ÿ”(=)/CALL GIRLS SERVICECHEAP Call Girls in Pushp Vihar (-DELHI )๐Ÿ” 9953056974๐Ÿ”(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )๐Ÿ” 9953056974๐Ÿ”(=)/CALL GIRLS SERVICE
9953056974 Low Rate Call Girls In Saket, Delhi NCR
ย 
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Badshah Nagar Lucknow best Female service
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Badshah Nagar Lucknow best Female serviceCALL ON โžฅ8923113531 ๐Ÿ”Call Girls Badshah Nagar Lucknow best Female service
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Badshah Nagar Lucknow best Female service
anilsa9823
ย 
TECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providerTECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service provider
mohitmore19
ย 
Hand gesture recognition PROJECT PPT.pptx
Hand gesture recognition PROJECT PPT.pptxHand gesture recognition PROJECT PPT.pptx
Hand gesture recognition PROJECT PPT.pptx
bodapatigopi8531
ย 

Recently uploaded (20)

+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
ย 
CHEAP Call Girls in Pushp Vihar (-DELHI )๐Ÿ” 9953056974๐Ÿ”(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )๐Ÿ” 9953056974๐Ÿ”(=)/CALL GIRLS SERVICECHEAP Call Girls in Pushp Vihar (-DELHI )๐Ÿ” 9953056974๐Ÿ”(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )๐Ÿ” 9953056974๐Ÿ”(=)/CALL GIRLS SERVICE
ย 
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Badshah Nagar Lucknow best Female service
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Badshah Nagar Lucknow best Female serviceCALL ON โžฅ8923113531 ๐Ÿ”Call Girls Badshah Nagar Lucknow best Female service
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Badshah Nagar Lucknow best Female service
ย 
5 Signs You Need a Fashion PLM Software.pdf
5 Signs You Need a Fashion PLM Software.pdf5 Signs You Need a Fashion PLM Software.pdf
5 Signs You Need a Fashion PLM Software.pdf
ย 
How To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected WorkerHow To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected Worker
ย 
TECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providerTECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service provider
ย 
Optimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVOptimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTV
ย 
A Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docxA Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docx
ย 
Microsoft AI Transformation Partner Playbook.pdf
Microsoft AI Transformation Partner Playbook.pdfMicrosoft AI Transformation Partner Playbook.pdf
Microsoft AI Transformation Partner Playbook.pdf
ย 
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
ย 
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlanโ€™s ...
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlanโ€™s ...Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlanโ€™s ...
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlanโ€™s ...
ย 
Shapes for Sharing between Graph Data Spacesย - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spacesย - and Epistemic Querying of RDF-...Shapes for Sharing between Graph Data Spacesย - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spacesย - and Epistemic Querying of RDF-...
ย 
Hand gesture recognition PROJECT PPT.pptx
Hand gesture recognition PROJECT PPT.pptxHand gesture recognition PROJECT PPT.pptx
Hand gesture recognition PROJECT PPT.pptx
ย 
Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...
Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...
Try MyIntelliAccount Cloud Accounting Software As A Service Solution Risk Fre...
ย 
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
ย 
Right Money Management App For Your Financial Goals
Right Money Management App For Your Financial GoalsRight Money Management App For Your Financial Goals
Right Money Management App For Your Financial Goals
ย 
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AISyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
ย 
Unlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language ModelsUnlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language Models
ย 
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
ย 
call girls in Vaishali (Ghaziabad) ๐Ÿ” >เผ’8448380779 ๐Ÿ” genuine Escort Service ๐Ÿ”โœ”๏ธโœ”๏ธ
call girls in Vaishali (Ghaziabad) ๐Ÿ” >เผ’8448380779 ๐Ÿ” genuine Escort Service ๐Ÿ”โœ”๏ธโœ”๏ธcall girls in Vaishali (Ghaziabad) ๐Ÿ” >เผ’8448380779 ๐Ÿ” genuine Escort Service ๐Ÿ”โœ”๏ธโœ”๏ธ
call girls in Vaishali (Ghaziabad) ๐Ÿ” >เผ’8448380779 ๐Ÿ” genuine Escort Service ๐Ÿ”โœ”๏ธโœ”๏ธ
ย 

22CS339- Electricity Theft Final Updated PPT (2).pptx

  • 2. Contents 1. Introduction of project 2. Problem statement 3. Scope of project 4. Methodology 5. Literature Survey 6. Propose System 7. System Architecture 8. Limitations, advantage, disadvantage 9. Conclusion Project Group No: 38 ELECTRICITY THEFT DETECTION 2
  • 3. Introduction of project โ€ข Many electric utilities have financial loss due to electricity theft. โ€ข Here are various types of electrical power theft, including Tapping a line or bypassing the energy meter. โ€ข According to a study [citation needed], 80% of worldwide theft occurs in private dwellings and 20% on commercial and industrial premises. โ€ข From user fundamental data it is easy task to analyze user behavior. โ€ข we implement a supervised ML-based theft detection model that identifies whether an abnormal/fraudulent usage pattern has occurred in the SG(smart grid)meter.
  • 4. Problem Statement โ€ข India loses more money to theft than any other country in the world. โ€ข In this proposed system we use dataset having electricity usage of a smart grid (SG) meter (or simply smart meter). โ€ข Using this dataset we does feature selection and preprocessing on dataset. โ€ข When we have large number of features in dataset then feature selection is very important part in our Machine Learning. โ€ข As we use feature selection it gives us most important feature and this feature selection gives us more accuracy.
  • 5. Scope of Project โ€ข Cost-Benefit Analysis โ€ข Risk Assessment And solutions โ€ข Control Efficiency And Services โ€ข Timeline Estimations And optimizing resources โ€ข Scope of project includes we can use this in electricity utilities. โ€ข to save Electricity โ€ข The project model reduces the manual manipulation work and theft. โ€ข The government saves the money by the control of theft in energy and also beneficial for customer side and the government side. โ€ข The metering IC ensures the accurate and reliable measurement of power consumed. Cost wise low
  • 6. Methodology โ€ข In this proposed system we use dataset having electricity usage of a smart meter. โ€ข Using this dataset we does feature selection and preprocessing on dataset. โ€ข When we have large number of features in dataset then feature selection is very important part in our Machine Learning. โ€ข As we use feature selection it gives us most important feature and this feature selection gives us more accuracy. โ€ข Then we perform the preprocessing on that data. โ€ข After that we use the superiority of XGBoost, a gradient boosting classifier (GBC), over other ML algorithms for nontechnical loss (NTL) detection โ€ข Gradient boosting is called gradient boosting because it uses a gradient descent algorithm to minimize loss when adding new trees. โ€ข This approach supports both regression and classification predictive
  • 7. Literature Survey Sr.NO Title Of The Project Year Method Metric Used Usage 1 PPETD: Privacy- Preserving Electricity Theft Detection Scheme with Load Monitoring and Billing for AMI Networks. 2019 CNN-GRU algorithm Accuracy of theft detection is 93.2% Used to classify normal users and electricity thefts. 2 Electricity theft detection based on extreme gradient boosting in AMI 2020 SVM Algorithm Accuracy of 89.2% To detect electricity thefts among dataset. 3 Electricity theft detection in AMI Based on Clustering and local Outlier Factor. 2021 Using Clustering and Local Outlier Factor(LOF) Nearly 12% people in area were electricity thefts on average. To reduce losses due to electricity thefts.
  • 8. Literature Survey Sr. No Title Of The Project Year Method Metric Used Usage 4 Deep Attention- based Neural Network for Electricity Theft Detection 2020 CNN(Deep Learning ) Accuracy of theft detection is more than 90% To make electricity theft detection system more effective. 5 Research and Implementation of Current Detection Technology for Electricity Stealing and Omission . 2021 XGBoost Algorithm Accuracy of 87.2% and 83.5 on training and testing data. To detect electricity thefts among dataset.
  • 9. Proposed System โ€ข India loses more money to theft than any other country in the world. โ€ข In this proposed system we use dataset having electricity usage of a smart grid (SG) meter (or simply smart meter). โ€ข Using this dataset we does feature selection and preprocessing on dataset. โ€ข When we have large number of features in dataset then feature selection is very important part in our Machine Learning. Project Group No: 38 ELECTRICITY THEFT DETECTION 9
  • 10. System Architecture Project Group No: 38 ELECTRICITY THEFT DETECTION 10
  • 11. ELECTRICITY THEFT DETECTION 11 Data Flow Diagram
  • 13. โ€ข Activity: ELECTRICITY THEFT DETECTION 13 UML Diagram
  • 17. Limitations โ€ข Billing system fails if no GSM network coverage. โ€ข Charges may be applicable for network use. โ€ข Requires fixed GSM number.
  • 18. Advantages โ€ข This method reduce energy wastage save lot of energy for future use. โ€ข We can detect the location from where the power is being stolen which was not possible before. โ€ข Customized rates and billing dates. โ€ข Accurate information from network load to optimize maintenance and investigation.
  • 19. Disadvantages โ€ข If Implemented on large scale it may take a lot of time and manual input โ€ข It is not Capable of Detecting the exact location โ€ข It is costly
  • 20. Conclusion Project Group No: 38 ELECTRICITY THEFT DETECTION โ€ข It helps electricity utilities to detect electricity theft and they will not have to bare loss. โ€ข This proposed system detects the electricity theft using xg boost machine learning method. โ€ข However, Light GBM appeared to be the fastest classifier. โ€ข This proposed system helps to electricity utilities to detect electricity theft and they will not have to bare loss. This is most important application of this project. 20
  • 21. References Project Group No: 38 ELECTRICITY THEFT DETECTION 1.J. Nagi, K. Yap, S. Tiong, S. Ahmed, and M. Mohamad, โ€œNontechnical loss de- tection for metered customers in power utility using support vector machines,โ€ IEEE Transactions on Power Delivery, vol. 25, no. 2, pp. 1162โ€“1171, 2010, cited By 104. 2 .S. McLaughlin, D. Podkuiko, and P. McDaniel, โ€œEnergy theft in the advanced metering infrastructure,โ€ Lecture Notes in Computer Science (including sub- series Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinfor- matics), vol. 6027 LNCS, pp. 176โ€“187, 2010, cited By 99. 3. G. Tsekouras, N. Hatziargyriou, and E. Dialynas, โ€œTwostage pattern recogni- tion of load curves for classification of electricity customers,โ€ IEEE Transac- tions on Power Systems, vol. 22, no. 3, pp. 1120โ€“1128, 2007, cited By 122. [Online]. 4. Y. Zhang, W. Chen, and J. Black, โ€œAnomaly detection in premise energy con- sumption data,โ€ 2011, cited By 12. [Online]. 5. S. Dua and X. Du, Data Mining and Machine Learning in Cybersecurity, 1st ed. Boston, MA, USA: Auerbach Publications, 2011. 21