Energy Theft Identification Using Adaboost Ensembler in the Smart Grids

Muhammad Irfan,Nasir Ayub,Saleh Mohammed Ghonaim,Fahad Salem Alkahtani,Zain Ali,Hesham Abdushkour,Muhammad Idrees,Faisal Althobiani,Saeed Ullah,Abdullah Saeed Alwadie,Saifur Rahman,Piotr Gas,Samar Alqhtani

doi:10.32604/cmc.2022.025466

Abstract

One of the major concerns for the utilities in the Smart Grid (SG) is electricity theft. With the implementation of smart meters, the frequency of energy usage and data collection from smart homes has increased, which makes it possible for advanced data analysis that was not previously possible. For this purpose, we have taken historical data of energy thieves and normal users. To avoid imbalance observation, biased estimates, we applied the interpolation method. Furthermore, the data unbalancing issue is resolved in this paper by Nearmiss undersampling technique and makes the data suitable for further processing. By proposing an improved version of Zeiler and Fergus Net (ZFNet) as a feature extraction approach, we had able to reduce the model's time complexity. To minimize the overfitting issues, increase the training accuracy and reduce the training loss, we have proposed an enhanced method by merging Adaptive Boosting (AdaBoost) classifier with Coronavirus Herd Immunity Optimizer (CHIO) and Forensic based Investigation Optimizer (FBIO). In terms of low computational complexity, minimized over-fitting problems on a large quantity of data, reduced training time and training loss and increased training accuracy, our model outperforms the benchmark scheme. Our proposed algorithms Ada-CHIO and Ada-FBIO, have the low Mean Average Percentage Error (MAPE) value of error, i.e., 6.8% and 9.5%, respectively. Furthermore, due to the stability of our model our proposed algorithms Ada-CHIO and Ada-FBIO have achieved the accuracy of 93% and 90%. Statistical analysis shows that the hypothesis we proved using statistics is authentic for the proposed technique against benchmark algorithms, which also depicts the superiority of our proposed techniques

Highlights

By adding new transmission technology, i.e., smart meters, a traditional power network becomes an Smart Grid (SG) infrastructure
As the accuracy of our suggested model is increases, on the other side the loss of our model is decreasing with the iterations as shown in Figs. 5a and 5b, which shows the superiority of our methodology
We present two new algorithms namely: Ada-Coronavirus Herd Immunity Optimizer (CHIO) and Ada-Forensic based Investigation Optimizer (FBIO) to detect energy theft in Advanced Meter Infrastructure (AMI)

Summary

Introduction

By adding new transmission technology, i.e., smart meters, a traditional power network becomes an SG infrastructure. The work in [4] proposes a hierarchical energy delivery system that avoids peak hours and exchanges more power for less money. To reduce the unpredictable nature of green energy, a strategy based on information-gap decision theory [5] is applied. In an SG, the meter reading shares data among energy users and the infrastructure. It stores an immense amount of data, including consumers’ electrical energy usage. Artificial intelligence techniques may manipulate these data to map customer energy usage trends and reliably detect power thieves through using them

Methods

Results

Conclusion