Power Consumption Behavior Research Articles

Abnormal Detection of Electricity Consumption of User Based on Particle Swarm Optimization and Long Short Term Memory With the Attention Mechanism

In the process of power transmission and distribution, non-technical losses are usually caused by users' abnormal power consumption behavior. It will not only affect the dispatch and operation of the distribution network, bring hidden dangers to the security of the power grid, but also damage the operating costs of power companies and disrupt the operation of the power market. Aiming at users' abnormal electricity consumption behavior, this paper proposes a model based on particle swarm optimization and long-short term memory with the attention mechanism (PSO-Attention-LSTM). Firstly, according to the actual electricity theft behavior, six typical electricity theft modes are summarized, and 4 composite modes are obtained by combining them, so as to comprehensively test the detection performance of the model for various electricity theft behaviors. Secondly, a detection model based on PSO-Attention-LSTM is proposed, and the model is built using the TensorFlow framework. The model uses the attention mechanism to give different weights to the hidden state of LSTM, which reduces the loss of historical information, strengthens important information and suppresses useless information. Use PSO to solve the difficult problem of model parameter selection, and optimize the hyperparameters to improve the model performance. Finally, the data set of the University of Massachusetts was used for simulation and compared with convolutional neural network-long short term memory (CNN-LSTM), attention mechanism-based long short term memory (Attention-LSTM), LSTM, gated recurrent unit (GRU), support vector regression (SVR), random forest (RF) and linear regression (LR) to verify the effectiveness and accuracy of the method used in this article. In this paper, Matlab software is used to analyze and visualize the detection result data.

A secure and privacy preserving lightweight authentication scheme for smart-grid communication using elliptic curve cryptography

Abstract In last few decades, smart-grid architecture has evolved as a new power service provider that can accomplish regulations of power generation with significant capabilities to monitor power consumption behaviour of the consumers and help in stabilization of the power system. With the huge progress of the delay sensitive smart grid network, it has to encounter various challenges. One of them is cyber-threats to the transmitted messages, control information of the smart-grid, and privacy-preservation of the consumers over smart-grid environment that leave annihilate consequences in real word. One of the key solutions of these cyber-threats is mutual authentication and setting up safe communication between the consumer and the utility-provider. In this paper, we have addressed novel mutual authentication scheme between consumer and substations formed on elliptic curve cryptography with trifling operations for smart-grid environment that is robust against all possible security threats. This scheme also provides a session key negotiation phase to provide secure communication with significantly less communication and computation overheads. The mathematical security testingand formal security testing using broadly-accepted BAN-logic has established that our scheme is robust against all relevant security threats. Further, the simulation result of the proposed schemethrough well-known AVISPA confirms that our scheme is well secure.Finally, to validate the practical ability, the proposed scheme is evaluated using well-accepted network simulator tool NS-2, that shows the proposed scheme is efficient to be implemented in realistic scenario.

Characteristic parameters and process maps for fully-filled twin-screw extruder elements

The shape and form of twin-screw extruder elements determine the physical conditions under which the material is processed. In this work, we investigated the pressure build-up, power consumption, dissipation and distributive mixing behavior of fully filled extruder elements via Smoothed Particle Hydrodynamics simulations, covering a wide range of conveying, kneading and mixing elements used in the ZSE12, ZSE18 and ZSE27 pharma extrusion equipment series. As a result, a comprehensive parameter catalogue of characteristic values was computed. These parameters allow studying the pressure build-up, power consumption and mixing behavior for all elements under various operating conditions. Additionally, we show novel process maps which support optimizing the length of a process zone. Properly used, the catalogue can assist a rational selection of screw elements during process design and transfer.

A Novel Approach for Detecting Anomalous Energy Consumption Based on Micro-Moments and Deep Neural Networks

Nowadays, analyzing, detecting, and visualizing abnormal power consumption behavior of householders are among the principal challenges in identifying ways to reduce power consumption. This paper introduces a new solution to detect energy consumption anomalies based on extracting micro-moment features using a rule-based model. The latter is used to draw out load characteristics using daily intent-driven moments of user consumption actions. Besides micro-moment features extraction, we also experiment with a deep neural network architecture for efficient abnormality detection and classification. In the following, a novel anomaly visualization technique is introduced that is based on a scatter representation of the micro-moment classes, and hence providing consumers an easy solution to understand their abnormal behavior. Moreover, in order to validate the proposed system, a new energy consumption dataset at appliance level is also designed through a measurement campaign carried out at Qatar University Energy Lab, namely, Qatar University dataset. Experimental results on simulated and real datasets collected at two regions, which have extremely different climate conditions, confirm that the proposed deep micro-moment architecture outperforms other machine learning algorithms and can effectively detect anomalous patterns. For example, 99.58% accuracy and 97.85% F1 score have been achieved under Qatar University dataset. These promising results establish the efficacy of the proposed deep micro-moment solution for detecting abnormal energy consumption, promoting energy efficiency behaviors, and reducing wasted energy.

Energy resource control via privacy preserving data

Although the frequent monitoring of smart meters enables granular control over energy resources, it also increases the risk of leakage of private information such as income, home occupancy, and power consumption behavior that can be inferred from the data by an adversary. We propose a method of releasing modified smart meter data so specific private attributes are obscured while the utility of the data for use in an energy resource controller is preserved. The method privatizes data by injecting noise conditioned on the private attribute through a linear filter learned via a minimax optimization. The optimization contains the loss function of a classifier for the private attribute, which we maximize, and the energy resource controller’s objective formulated as a canonical form optimization, which we minimize. We perform our experiment on an aggregated dataset of household consumption with solar generation and another from the Commission for Energy Regulation (CER) that contains household smart meter data with sensitive attributes such as income and home occupancy. We demonstrate on the CER data that our method is able to reduce the ability of an adversary to classify a binary income label to that of random guessing while maintaining an objective value for an energy storage controller within 10% of optimal.

Robust purchase and sale transactions optimization strategy for electricity retailers with energy storage system considering two-stage demand response

A new two-stage demand response is designed for the electricity retailers with energy storage system (ESS-ER) in the deregulated power market. The ESS-ER could response to the output of different power sources by adjusting the charging-discharging behavior according to the bidding power price. The paper models the two-stage demand response for electric power retailers and proposed a two-layer coordinated optimal model for the purchase and sale of the electric power retailers. In the upper layer model, the conditional value at risk method and robust stochastic theory are applied to describe the uncertainty influence of wind power and Photovoltaic (PV) power, and the minimum whole cost of power purchasing is taken as the objective. In the lower-layer, the power consumption behaviors of different customers are considered to get the maximum revenue of power selling by implementing differentiated demand response. Then, to solve the two-layer mathematical model, the lower-layer model is converted into the Karush-Kuhn-Tucker (KKT) optimality conditions. The results show that: (1) The two-stage demand response could smooth the curves of power purchasing and terminal users’ load, which could bring more flexible transaction space. (2) The proposed two-layer transaction model could balance the cost and risk of power purchasing, bringing more trading opportunities for wind power and PV, which can also reduce the energy consumption cost of the end-users. (3) By introducing the risk cost coefficient, confidence degree and robust coefficient, the decision-makers can adjust the power trading behaviors, and establish the optimal power trading scheme in line with their expected situation. (4) When higher energy storage capacity is set, the efficiency of demand response rises. When the capacity ratio of wind to energy storage is 4:1, the efficiency of demand response reaches the best. When larger energy storage capacity is set, the demand response turns to be more effective. However, when the capacity ratio of wind and PV to energy storage is 4:1, the effect of demand response reaches the best. Overall, the proposed model could provide an effective tool for power retailers in China's electric power market.

A Statistical Data-Filtering Method Proposed for Short-Term Load Forecasting Models

Reliability assessment of the SCADA-system based load data is necessary for improving accuracy of short-term load forecasting (STLF) methods in a distribution network (DN). Specifically, the reliability evaluation of the load data is to properly eliminate noise/outliers caused by random power consumption behaviors or the sudden change in load demand from industrial and residential customers in the DN. Thus, this paper proposes a novel statistical data-filtering method, working at an input data pre-processing stage, which will evaluate the reliability of input load data by analyzing all possible data confidence levels in order to filter-out the noise/outliers for accuracy improvement of different short-term load forecasting models. The proposed statistical data-filtering method is also compared to other existing data-filtering methods (such as Kalman Filter, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Discrete Wavelet Transform (DWT) and Singular Spectrum Analysis (SSA)). Moreover, several case studies of short-term load forecasting for a typical 22 kV distribution network in Vietnam are conducted with an Artificial Neural Network (ANN) model, a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) model, a combined model of Long Short-Term Memory Network and Convolutional Neural Network (LSTM-CNN), and a conventional Autoregressive Integrated Moving Average (ARIMA) model to validate the statistical data-filtering method proposed. The achieved results demonstrate which the STLF using ANN, LSTM-RNN, LSTM-CNN, and ARIMA models with the statistical data-filtering method can all outperform those with the existing data-filtering methods. Additionally, the numerical results also indicate that in case the SCADA-based load data is normally distributed, time-series forecasting models should be more preferred than neural network models; otherwise, when the SCADA-based load data contains multiple normally distributed sub-datasets, neural network-based prediction models are highly recommended.

Accuracy improvement of various short-term load forecasting models by a novel and unified statistical data-filtering method

ABSTRACTTime-series and machine-learning methods are being strongly exploited to improve the accuracy of short-term load forecasting (STLF) results. In developing countries, power consumption behaviors could be suddenly changed by different customers, e.g. industrial customers, residential customers, so the load-demand dataset is often unstable. Therefore, reliability assessment of the load-demand dataset is obviously necessary for STLF models. Hence, this paper proposes a novel and unified statistical data-filtering method with the best confidence interval to eliminate unexpected noises/outliers of the input dataset before performing various short-term load forecasting models. This proposed novel data-filtering method, so-called the data pre-processing method, is also compared to other existing data-filtering methods (e.g. Kalman filter, Density-Based Spatial Clustering of Applications with Noise, Wavelet transform, and Singular Spectrum Analysis). By using an SCADA system-based database of a typical 22kV distribution network in Vietnam, NYISO database, and PJM-RTO database, case studies of short-term load forecasting have been conducted with a conventional ARIMA model, an ANN forecasting model, an LSTM-RNN model, an LSTM-CNN combined model, a deep auto-encoder (DAE) network, a Wavenet-based model, a Wavenet and LSTM hybrid model, and a Wavelet Neural Network (WNN) model, which are to validate the novel and unified statistical data-filtering method proposed. The achieved numerical results demonstrate which the accuracy of the aforementioned STLF models can be significantly improved due to the proposed statistical data-filtering method with the best confidence interval of the input load dataset. The proposed statistical data-filtering method can considerably outperform the existing data-filtering methods.

An artificial synapse by superlattice-like phase-change material for low-power brain-inspired computing**Project supported by the National Science and Technology Major Project of China (Grant No. 2017ZX02301007-002), the National Key R&D Plan of China (Grant No. 2017YFB0701701), and the National Natural Science Foundation of China (Grant Nos. 61774068 and 51772113). The authors acknowledge the support from Hubei Key Laboratory of Advanced Memories

Phase-change material (PCM) is generating widespread interest as a new candidate for artificial synapses in bio-inspired computer systems. However, the amorphization process of PCM devices tends to be abrupt, unlike continuous synaptic depression. The relatively large power consumption and poor analog behavior of PCM devices greatly limit their applications. Here, we fabricate a GeTe/Sb2Te3 superlattice-like PCM device which allows a progressive RESET process. Our devices feature low-power consumption operation and potential high-density integration, which can effectively simulate biological synaptic characteristics. The programming energy can be further reduced by properly selecting the resistance range and operating method. The fabricated devices are implemented in both artificial neural networks (ANN) and convolutional neural network (CNN) simulations, demonstrating high accuracy in brain-like pattern recognition.

Axial flow hollow fiber forward osmosis module analysis for optimum design and operating conditions in desalination applications

In this article, a mathematical model is developed for axial flow hollow fiber (HF) forward osmosis (FO) module and validated with unsteady-state FO experimental data of NaCl-H2O system. A maximum of 0.7 and 12% deviation in draw solution (DS) and feed solution (FS) concentration shows a good agreement between experimental results and model outputs. Simulations were carried out at various module length and operating conditions to analyze their effects on permeate flow rate and power consumption. Based on the simulation results, a multi-objective optimization (MOO) was formulated to get optimal Pareto between FO water flux and power supplied to the pump by considering the module length, DS and FS pressure and flow rate as decision variables. The optimization analysis revealed the exponential behavior of power consumption with respect to the permeate flow rate. Finally, a procedure to optimize the FO plant performance using MOO optimal Pareto is presented.

Three-Dimensional Maturity Model of Regional Power Users Against the Background of the Ubiquitous Power Internet of Things

As the Ubiquitous Power Internet of Things (UPIoT) is being developed, the data volume collected by various terminals such as smart electricity meters is increasing daily. The efficient extraction of information from massive data and the provision of value-added services to users, power grids, and market entities are crucial aspects and research directions. A data analysis and application framework for smart meter data based on cloud-fog computing and data contextualization is established, and a data contextualization model based on three-dimensional (3d) maturity analysis of industrial power users is proposed to evaluate the power consumption characteristics of users from the three aspects of the load level, power consumption behavior, and interaction. The results of a case study show that this model allows power grid operators to understand quickly and intuitively the load behavior pattern and power demand of industrial power users, thereby enabling an efficient and accurate assessment of the power supply and an ability to provide value-added services.

An Approach of Electrical Load Profile Analysis Based on Time Series Data Mining

In the current electrical load profile analysis, considering the shortage of traditional methods on the typical load profile extraction of single consumers and the load profile feature extraction, this paper proposes an approach based on time series data mining. Firstly, this method reduces the dimension of the load profile of a single consumer based on the Piecewise Aggregate Approximation(PAA), and re-expresses the load profile of the consumer over a period based on the Symbolic Aggregate approXimation(SAX), representing the consumer’s load profile with a symbolic string to extract the typical load profile. Then, combined with the load characteristic indices and time series-based features, the typical load profiles of different consumers are clustered based on the K-means algorithm to analyze the power consumption behaviors. Finally, this paper performs a case analysis with a UCI test data set, and the results show that the proposed approach can excavate typical power consumption behaviors of consumers and improve the electrical load profile analysis efficiency and the clustering quality.

Multi-Step Short-Term Power Consumption Forecasting Using Multi-Channel LSTM With Time Location Considering Customer Behavior

Short-Term Load Forecasting (STLF) is one critical assignment regarding the power supply and demand in the smart grid. Multi-step STLF provides strong evidence for decision-making to achieve consistent, quick supply and reduce direct or indirect cost. However, most of the current research only focuses on one-step STLF, which cannot satisfy the human-beings needs. Besides, short-term consumption fluctuates significantly in different periods and people, which increases the difficulty of forecasting. In this paper, we present a novel deep model named multi-channel long short-term memory (LSTM) with time location (TL-MCLSTM) in a multiple output strategy to forecast the multi-step short-term power consumption. The proposed model contains three channels: power consumption, time location, and customer behavior channels, respectively. Power consumption channel reflects the change and general trend of use; Time location channel reflects the hidden pattern of customer habits, which records the information consisting of time, day of the week, holidays. Moreover, we combine a convolution autoencoder and k-means to identify the type of behavior at the customer behavior channel. Power consumption and time location channels are trained individually through the LSTM as it has excellent memory function. Extracted features from LSTM in power consumption and time location channels are combined with customer behavior as comprehensive features to forecast. We designed, trained, and verified our proposed deep model on two nature data sets, and compared with other leading deep learning-based methods. The comparative studies have confirmed the effectiveness and priority of TL-MCLSTM for multi-step short-term consumption forecasting.

Hybrid CNN-LSTM Model for Short-Term Individual Household Load Forecasting

Power grids are transforming into flexible, smart, and cooperative systems with greater dissemination of distributed energy resources, advanced metering infrastructure, and advanced communication technologies. Short-term electric load forecasting for individual residential customers plays a progressively crucial role in the operation and planning of future grids. Compared to the aggregated electrical load at the community level, the prediction of individual household electric loads is legitimately challenging because of the high uncertainty and volatility involved. Results from previous studies show that prediction using machine learning and deep learning models is far from accurate, and there is still room for improvement. We herein propose a deep learning framework based on a combination of a convolutional neural network (CNN) and long short-term memory (LSTM). The proposed hybrid CNN-LSTM model uses CNN layers for feature extraction from the input data with LSTM layers for sequence learning. The performance of our developed framework is comprehensively compared to state-of-the-art systems currently in use for short-term individual household electric load forecasting. The proposed model achieved significantly better results compared to other competing techniques. We evaluated our proposed model with the recently explored LSTM-based deep learning model on a publicly available electrical load data of individual household customers from the Smart Grid Smart City (SGSC) project. We obtained an average mean absolute percentage error (MAPE) of 40.38% for individual household electric load forecasts in comparison with the LSTM-based model that obtained an average MAPE of 44.06%. Furthermore, we evaluated the effectiveness of the proposed model on different time horizons (up to 3 h ahead). Compared to the recently developed LSTM-based model tested on the same dataset, we obtained 4.01%, 4.76%, and 5.98% improvement for one, two, and six look-forward time steps, respectively (with 2 lookback time steps). Additionally, we have performed clustering analysis based on the power consumption behavior of the energy users, which indicate that prediction accuracy could be improved by grouping and training the representative model using large amount of data. The results indicated that the proposed model outperforms the LSTM-based model for both 1 h ahead and 3 h ahead in forecasting individual household electric loads.

Electricity Safety Analysis and Improvement Based on User Classification

Analyzing electricity consumption behavior by classifying user groups and knowing each group’s characteristics are an important way to realize intelligent power consumption. This paper firstly classifies different types of users based on power consumption data and grasps the power consumption behavior of typical users. The main causes of accidents and alarms are then discussed based on the recorded events and power consumption curve. Finally, the corresponding solutions, which take the user’s social attributes and electricity consumption behavior into consideration are put forward to avoid the potential accidents.

A novel smart meter data compression method via stacked convolutional sparse auto-encoder

With the wide deployment of smart meters in distribution systems, a new challenge emerges for the storage and transmission of huge volume of power consumption data collected by smart meters. In this paper, a deep-learning-based compression method for smart meter data is proposed via stacked convolutional sparse auto-encoder (SCSAE). An efficient and lightweight auto-encoder structure is first designed by leveraging the unique characteristics of smart meter readings. Specifically, the encoder is designed based on 2D separable convolution layers and the decoder is based on transposed convolution layers. Compared with the existing auto-encoder method and traditional methods, the proposed structure is redesigned, and the parameters and reconstruction errors are efficiently reduced. In addition, cluster-based indexes are used to represent the regularity of power consumption behavior and the relationship between electricity consumption behavior and compression effect is studied. Case studies illustrate that the proposed method can attain significant enhancement in model size, computational efficiency, and reconstruction error reduction while maintaining the most abundant details. And grouping compression considering users’ electricity consumption rules can further improve the compression effect.

OPEC: Daily Load Data Analysis Based on Optimized Evolutionary Clustering

Customers’ electricity consumption behavior can be studied from daily load data. Studying the daily load data for user behavior pattern analysis is an emerging research area in smart grid. Traditionally, the daily load data can be clustered into different clusters, to reveal the different categories of consumption. However, as user’s electricity consumption behavior changes over time, classical clustering algorithms are not suitable for tracing the changes, as they rebuild the clusters when clustering at any timestamp but never consider the relationship with the clusters in the previous state. To understand the changes of consumption behavior, we proposed an optimized evolutionary clustering (OPEC) algorithm, which optimized the existing evolutionary clustering algorithm by joining the Proper Restart (PR) Framework. OPEC relied on the basic fact that user’s energy consumption behavior would not abruptly change significantly, so the clusters would change progressively and remain similar in adjacent periods, except for an emergency. The newly added PR framework can deal with a situation where data changes dramatically in a short period of time, and where the former frameworks of evolutionary clustering do not work well. We evaluated the OPEC based on daily load data from Shanghai, China and the power load diagram data from UCI machine learning repository. We also carefully discussed the adjustment of the parameter in the optimized algorithm and gave an optimal value for reference. OPEC can be implemented to adapt to this situation and improve clustering quality. By understanding the changes of the users’ power consumption modes, we can detect abnormal power consumption behaviors, and also analyze the changing trend to improve the operations of the power system. This is significant for the regulation of peak load in the power grid. In addition, it can bring certain economic benefits to the operation of the power grid.

Optimized approach for antipattern detection in service computing architecture

Maintainability of a software can be enhanced by using refactoring activities. Refactoring activities aims at eliminating antipatterns from the system Application of refactoring techniques negatively impacts the power and energy consumption behavior of software systems. In other words, maintainability sometimes leads to sustainability degradation. Antipatterns depict suboptimal implementation choices that lead to more error prone and highly maintainable systems. A large number of antipatterns have been defined in the literature which are used by developers to detect system design issues. Despite the large number of antipatterns which are defined, their accuracy is still a subjective measure. Objective: There are multiple issues like uncertainty, boundary definition, metric combination and rule conversion. To overcome these limitations the research paper focusses on the use of optimized algorithms for antipattern detection. Method: The research paper deals with the existing antipattern detection techniques and proposal of a new optimized algorithm which not only works on static metrics but also takes into consideration dynamic metrics for execution. Later on the results are optimized using genetic algorithm. A comparative analysis of the existing models with the proposed model is also done. The analysis clearly depicted that the proposed approach has better precision and recall rate of approximately 90 %. Result: The proposed approach was successful in identification of five antipatterns (Multi Service, Fine Grained Web Service, Chatty Web Service, Data Web Service and Ambiguous Web Service).

Research on Power Behavior Analysis Based on Clustering

This research is based on data clustering to analyze power users’ electricity consumption behavior, and analyzes the load curve to obtain the users’ electricity consumption characteristics and classify users according to the characteristics of electricity consumption behavior. It is of far-reaching significance to the power industry and socio-economic development. This paper introduces the principle and flow of the main clustering algorithm K-means, fuzzy clustering and neural network clustering algorithm. The data preprocessing method is given. The clustering algorithm and the optimal clustering number are determined by defining the clustering volatility and clustering accuracy index. Then the power consumption behavior of the user is analyzed through the load curves and characteristic parameters obtained through clustering.

Adaptive on-line unsupervised appliance modeling for autonomous household database construction

Enabling diagnosis capabilities of Appliance Load Monitoring (ALM) necessitates providing in-operation information of appliances’ behavior. Due to both appliances’ time-varying model parameters and operations, household aggregated consumption has a dynamic structure. Existing time-invariant load models, built of off-line datasets with static information, are not sufficient to capture the actual behavior of the power consumption. In fact, these models, generally obtained from exhaustive training phases are intended to satisfy load monitoring goals. Therefore, a time-variant load modeling is more practical to capture such a dynamic property of the power consumption. Accordingly, this paper presents an adaptive on-line appliance-level load modeling approach, to design a load monitoring structure for diagnosis purposes. By using the aggregated power consumption of individual households, our proposed structure results in an autonomous household database construction. The modeling procedure begins with a designed recurrent pattern recognition system that is capable of detecting and maintaining load models. This load model structure is determined by using a hidden Markov model (HMM) with dynamic parameters, that are extracted from aggregated signal and trained within an on-line learning process. Our proposed approach can detect time-varying power consumption behavior and estimate the robust load models of appliances. Additionally, our novelty in employing a set of straightforward algorithms, suggests the practicality of our database construction approach.