Smart grid security enhancement by detection and classification of
            <scp>non‐technical</scp>
            losses employing deep learning algorithm

Pitchaimani, Jeyaraj; Nadar, Edward Rajan Samuel; Aravind, C. K.; Asokan, Siva Prakash

doi:10.1002/2050-7038.12521

Cited by 17 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…"0" refers to the absence of correlation, while "1" indicates that correlation is perfect. 47 PCC can be computed by Equation (3) as…”

Section: Influence Of Different Factors On Electrical Demand By Pcc Analysismentioning

confidence: 99%

“…Correlation is considered very strong if the value is between 0.75 and 1, moderate if the value is between 0.75 and 0.5 and weak if the value is between 0.25 and 0.5. “0” refers to the absence of correlation, while “1” indicates that correlation is perfect 47 . PCC can be computed by Equation (3) as

italicPCC = \frac{italicCov ((), X, Y)}{S_{D} ((), X) * S_{D} ((), Y)} = \frac{\sum X_{i} Y_{i} - \frac{\sum X_{i} Y_{i}}{n_{o}}}{\sqrt{(\sum {X_{i}}^{2} - \frac{\sum {X_{i}}^{2}}{n_{o}}) (\sum {Y_{i}}^{2} - \frac{\sum {Y_{i}}^{2}}{n_{o}})}}

…”

Section: Optimal Bra‐based Lf Strategy Incorporating Pccmentioning

confidence: 99%

See 1 more Smart Citation

Optimal BRA based electric demand prediction strategy considering instance‐based learning of the forecast factors

Waseem

Liu

Zhang

et al. 2021

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

With the grid's evolution, the end-users demand becomes more vital for demand side management (DSM). Accurate load forecasting (LF) is critical for power system planning and using advanced demand response (DR) strategies.To design efficient and precise LF, information about various factors that influence end-users demand is required. In this paper, the impact of different factors on electrical demand and capacity of climatic factors existence and their variation is discussed and analysed. The Pearson correlation coefficient (PCC) is utilized to express the degree of electric demand correlation with metrological and calendar factors. Then, the optimal-Bayesian regularization algorithm (BRA) based on ANN for LF is presented. The effect of the number of neurons in hidden layers on output is observed to select the most appropriate option. Additionally, heating degree days (HDDs) and cooling degree days (CDDs) indices are investigated to consider the impact of air conditioners' (ACs) loads in different seasons. Case studies on data from Dallas, Texas, USA, are used to

show abstract

“…"0" refers to the absence of correlation, while "1" indicates that correlation is perfect. 47 PCC can be computed by Equation (3) as…”

Section: Influence Of Different Factors On Electrical Demand By Pcc Analysismentioning

confidence: 99%

italicPCC = \frac{italicCov ((), X, Y)}{S_{D} ((), X) * S_{D} ((), Y)} = \frac{\sum X_{i} Y_{i} - \frac{\sum X_{i} Y_{i}}{n_{o}}}{\sqrt{(\sum {X_{i}}^{2} - \frac{\sum {X_{i}}^{2}}{n_{o}}) (\sum {Y_{i}}^{2} - \frac{\sum {Y_{i}}^{2}}{n_{o}})}}

…”

Section: Optimal Bra‐based Lf Strategy Incorporating Pccmentioning

confidence: 99%

Optimal BRA based electric demand prediction strategy considering instance‐based learning of the forecast factors

Waseem

Liu

Zhang

et al. 2021

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

show abstract

“…This conditional fine-tuning under the empirical distribution ofŷ, Figure 3 shows the fine-tuning by backpropagation. In residential load, forecasting for each 30 Here, error (Y forecast , Y target ) is the squared error function, Y i,forecast is the load forecasted for i input data, and Y i , target is the predicted load for i input data by the proposed PDNN.…”

Section: Performance Optimization By Finetuning Proposed Pdnnmentioning

confidence: 99%

Computer‐assisted demand‐side energy management in residential smart grid employing novel pooling deep learning algorithm

Pitchaimani¹,

Nadar²

2021

Int J Energy Res

Self Cite

View full text Add to dashboard Cite

Demand-side energy management increases the unpredictability and ambiguity of forecasting the load profiles of residential energy management. The energy management accuracy seems to be low by employing a traditional residential energy forecasting algorithm. This research work emphasizes on design and development of computer-assisted residential energy management by forecasting employing a deep learning algorithm. Hankel matrix is formed using copula function to process the collected automatic metering infrastructure (AMI) load data in the smart grid. From this data processing, model optimization was obtained by the proposed novel pooling-based deep neural network (PDNN). Moreover, this proposed PDNN avoid overfitting problem in training and testing by increasing AMI data variety and data size. The proposed PDNN is implemented in the TensorFlow platform. Based on real-time AMI southern grid data onto Tamil Nadu Electricity Board, India testing case studies was carried. Compared to traditional residential energy management techniques the proposed deep learning model outperforms support vector machine by 9.5% and 12.7%, deep belief network by 6.5% and 9.5%, and neural network auto aggressive integral moving average by 20.5% and 8.5% in terms of accuracy of energy forecasting and mean absolute error, respectively. Overall, the obtained results proved the effectiveness of the proposed deep learning algorithm for residential short-term load forecasting and management over other traditional methods. Highlights In this research work: • Novel pooling-based deep neural network is applied for residential energy management in a smart grid. • The copula fusion theory is adopted to improve the accuracy of load management in a smart grid. • Day-ahead and week-ahead prediction load on Tamil Nadu Electricity Board dataset in summer and winter season was used to validate the performance of the proposed method with other data-driven methods.

show abstract

“…After detecting the nontechnical loss, the pathfinding program based on the algorithm can find the consumption point of the nontechnical loss. Jeyaraj et al [10] put forward a multidimensional deep learning algorithm to learn and classify nonperiodical electricity and then can detect user theft of electricity from the periodic load curve.…”

Section: Smart Grid Ntl Detectionmentioning

confidence: 99%

Smart Grid Nontechnical Loss Detection Based on Power Gateway Consortium Blockchain

Wang

Liu

et al. 2021

Security and Communication Networks

View full text Add to dashboard Cite

The rapid development of the smart grid brings convenience to human beings. It enables users to know the real-time power supply capacity, the power quality, and the electricity price fluctuation of the grid. However, there are still some threats in the smart grid, which increase all kinds of expenses in the grid and cause great trouble to energy distribution. Among them, the man-made nontechnical loss (NTL) problem is particularly prominent. Recently, there are also some NTL detection programs. However, most of the schemes need huge amounts of supporting data and high labor costs. As a result, the NTL problem has not been well solved. In order to better avoid these risks, problems such as tampering of smart meter energy data, bypassing the smart meter directly connected to the grid, and imbalance between revenue and expenditure of the smart grid are tackled, and the threat scene of NTL is constructed. A hierarchical grid gateway blockchain is proposed and designed, and a new decentralized management MDMS system is constructed. The intelligent contract combined with the elliptic curve encryption technology is used to detect the storage and the acquisition of power data, and the detection of NTL problems is realized. At the same time, it has a certain ability to resist attacks such as replay, monitoring, and tampering. We tested the time consumption and throughput of this method on Hyperledger Fabric. At the same time, eight indexes of other methods proposed in the literature are compared. This method has a good effect.

show abstract

Smart grid security enhancement by detection and classification of non‐technical losses employing deep learning algorithm

Cited by 17 publications

References 21 publications

Optimal BRA based electric demand prediction strategy considering instance‐based learning of the forecast factors

Optimal BRA based electric demand prediction strategy considering instance‐based learning of the forecast factors

Computer‐assisted demand‐side energy management in residential smart grid employing novel pooling deep learning algorithm

Smart Grid Nontechnical Loss Detection Based on Power Gateway Consortium Blockchain

Contact Info

Product

Resources

About