Power Consumption Data Research Articles

A Novel High-Performance Deep Learning Framework for Load Recognition: Deep-Shallow Model Based on Fast Backpropagation

This paper proposes a novel high-performance deep learning framework for load recognition. The framework consists of a deep-shallow model and a fast backpropagation (FBP) algorithm. In the deep-shallow model, power-related wave patterns are perceived by a convolutional neural network (CNN), and feature statistics of the power consumption data are analyzed by a sparse feed-forward neural network. The new architecture improves model interpretability and prevents information loss problems in CNNs. The architecture also greatly boosts the convergence speed and significantly enhances the test set accuracy of a neural network. Compared with conventional CNN models utilized by many load recognition applications, the FBP algorithm consisting of four sub-algorithms converges faster at the start of the training process and reduces at least 87.5% of the filter gradient computations on average. The deep-shallow-fast model that combines the deep-shallow model and the FBP algorithm attains 97.62% accuracy on the test set in the load recognition task. To fully utilize the training data, a data augmentation technique is invented that transforms the voltage and current time series into an image-like 4-D tensor. Experiments illustrate that the proposed framework is much more accurate and converges considerably faster than the conventional CNN model that many deep-learning-based load recognition applications are based upon.

Evaluation of energy management strategies for fuel cell/battery-powered underwater vehicles against field trial data

• Evaluation of Energy Management Strategies (EMS) against field trial data. • Fuel cell/battery-hybrid power system is modelled in Simulink®. • Performance criteria include energy efficiency, degradation and power reliability. • Choice of EMS depends on character of mission: high-autonomy missions require more complex EMS. This study combines high-fidelity simulation models with experimental power consumption data to evaluate the performance of Energy Management Strategies (EMS) for fuel cell/battery hybrid Autonomous Underwater Vehicles (AUV). The performance criteria are energy efficiency, power reliability and system degradation. The lack of standardized drive cycles is met by the cost-efficient solution of synthesizing power profiles from sampled AUV field trial data. Three power profiles are used to evaluate finite-state machine, fuzzy logic and two optimization-based EMS. The results reveal that there is a trade-off between the objectives. The rigidity of the EMS determines its load-following behavior and consequently the performance regarding the objectives. Rule-based methods are particularly suitable to design energy-efficient operations, whereas optimization-based methods can easily be tuned to provide power reliability through load-following behavior. Both classes of EMS can be best-choice methods for different types of missions.

Data-Driven Approach for the Short-Term Business Climate Forecasting Based on Power Consumption

With the fast development of intelligent data-mining technologies, some advanced artificial intelligence approaches are widely developed and employed to help the decision-making of enterprises and government. The application of advanced and intelligent approaches successfully helps the enterprises and government find out the valuable information hidden in the massive economic data. This study presents a novel data-driven approach to forecast the short-term business climate using the electric power consumption data of large enterprises. In addition, the climate conditions, interactions between different industries, the business cycle, and some other related variables are also considered and included in the developed forecasting model. To be specific, the business climate prediction model based on support vector machine (SVM) is proposed firstly, and the human-simulated particle swarm optimization algorithm (HSPSO) in our previous work is employed to optimize the parameters of the developed forecasting model. Secondly, a novel power-consumption-based business climate index (BCI) system is developed and comprehensively analyzed. The developed BCI system that contains the index for each separate industry (BCI-I), the index for tertiary industry (BCI-T), the index for secondary industry (BCI-S), and the index for the entire province (BCI-P) is proposed. In addition, the developed BCI system is employed to normalize the output of SVM-based forecasting model to directly indicate the business climate, which is very important to the decision-making of enterprises and government under the background of smart cities. Finally, the real data of Guangdong province in China, including the gross output values (GOV) and detailed power consumptions of more than 38000 enterprises, are employed to test the proposed approach. Experimental results show that the GOV of each industry and the whole society predicted by HSPSO-SVM matches the real data well. Moreover, the predicted BCI can directly indicate the business climate in advance, which is of great value for economic-decision and policy-making of both enterprises and government.

Monitoring, Controlling & Conserving of Electrical Energy Using IOT

Energy consumption refers to the amount of energy consumed by an individual or organization which has been taken for granted in daily life by consumers especially at home.A circuit is designed, to take care of electrical energy consumption which helps the consumers to focus on the extra charges incurred due to minor changes in slab categories which affect the consumer’s bill severely[1]. This system utilizes a sensor module that is connected with ARDUINO along with GSM, ESP 8266, and energy meter to measure the power consumption at the home[2].The main aim of this paper is to make consumers aware of the power consumption and to control the excess power consumption, by using a IoT Based Electrical Energy Consumptıon Live Monitoring & Controlling System.The power consumption data is collected and stored in to IoT cloud services[3]. Daily usage is updated to the consumer periodically through a mobile application which helps to reduce over usage of power.

Privacy Preserving Data Aggregation for Smart Grid with User Anonymity and Designated Recipients

Smart grids integrate modern Internet of Things technologies with the traditional grid systems, aiming to achieve effective and reliable electricity distribution as well as promote clean energy development. Nowadays, it is an indispensable infrastructure for smart homes, wisdom medical, intelligent transportation, and various other services. However, when smart meters transmit users’ power consumption data to the control center, sensitive information may be leaked or tampered. Moreover, distributed architecture, fine-grained access control, and user anonymity are also desirable in real-world applications. In this paper, we propose a privacy-preserving data aggregation scheme for a smart grid with user anonymity and designated recipients. Smart meters collect users’ power consumption data, encrypt it using homomorphic re-encryption, and then transmit the ciphertexts anonymously. Afterward, proxies re-encrypt the aggregated data in a distributed fashion so that only the designated recipients can decrypt it. Therefore, our proposed scheme provides a more secure and flexible solution for privacy-preserving data aggregation in smart grids. Security analyses prove that our scheme achieves all the above-mentioned security requirements, and efficiency analyses demonstrate that it is efficient and suitable for real-world applications.

Privacy-preserving statistical analysis over multi-dimensional aggregated data in edge computing-based smart grid systems

Smart grid systems enable bidirectional data communication between users and a smart grid control center (CC), by utilizing various communication infrastructures and embedded devices. To extract valuable information from users’ power consumption data efficiently, multi-dimensional data of users are required to be analyzed deeply. To protect users’ privacy, power consumption data are usually encrypted before transmission, which simultaneously makes it difficult to conduct statistical analysis. In this paper, we propose a scheme which enables privacy-preserving statistical analysis over multi-dimensional aggregated data (SA-MAD) in smart grid systems equipped with edge computing. We modify Boneh–Goh–Nissim (BGN) public key cryptosystem to a dual-message encryption mode, combining with two special superincreasing sequences to deal with multi-dimensional encrypted data aggregation. Besides, we design an identity-based aggregate signature to ensure encrypted data integrity in smart grid systems, and employ shamir secret sharing technique to support transmission fault-tolerance mechanism from smart meters to corresponding edge servers. SA-MAD enables CC to flexibly conduct privacy-preserving statistical analysis (e.g., sum, average, and variance) over aggregated data, and it could be easily extended to support covariance and linear regression computation. The performance evaluation demonstrates the feasibility of SA-MAD in edge computing-based smart grid systems.

Synthetic Theft Attacks and Long Short Term Memory-Based Preprocessing for Electricity Theft Detection Using Gated Recurrent Unit

Electricity theft is one of the challenging problems in smart grids. The power utilities around the globe face huge economic loss due to ET. The traditional electricity theft detection (ETD) models confront several challenges, such as highly imbalance distribution of electricity consumption data, curse of dimensionality and inevitable effects of non-malicious factors. To cope with the aforementioned concerns, this paper presents a novel ETD strategy for smart grids based on theft attacks, long short-term memory (LSTM) and gated recurrent unit (GRU) called TLGRU. It includes three subunits: (1) synthetic theft attacks based data balancing, (2) LSTM based feature extraction, and (3) GRU based theft classification. GRU is used for drift identification. It stores and extracts the long-term dependency in the power consumption data. It is beneficial for drift identification. In this way, a minimum false positive rate (FPR) is obtained. Moreover, dropout regularization and Adam optimizer are added in GRU for tackling overfitting and trapping model in the local minima, respectively. The proposed TLGRU model uses the realistic EC profiles of the Chinese power utility state grid corporation of China for analysis and to solve the ETD problem. From the simulation results, it is exhibited that 1% FPR, 97.96% precision, 91.56% accuracy, and 91.68% area under curve for ETD are obtained by the proposed model. The proposed model outperforms the existing models in terms of ETD.

Energy supply based on\xa0wind-solar power in Germany

Wind-solar power has an intrinsic huge volatility and the obvious question arises, is it possible to marginalize it to an extent that the power generation can sufficiently be synchronized with the electric power consumption being volatile as well. We present a novel function describing the volatile system as a whole. The new function, in turn, depends on three characteristic numbers, which means that the volatility of this system is characterized by those numbers. Using the data of the total electric power consumption and the total wind-solar power generation in Germany for the last seven years (2015–2021) taken every 15 minutes we determine the characteristic numbers from these data and get the result that marginalizing the volatility is possible with a minimum of required storage capacity, provided (i) a surplus of wind-solar power is supplied about doubling the number of devices, (ii) smart meters are installed, (iii) a different kind of wind turbines and solar panels is partially used. Our results suggest that all the present electric energy required in Germany can be obtained from wind-solar power if (i), (ii) and possibly (iii) are fulfilled. And our results indicate that, because of the minimal necessary storage capacity, controlled wind-solar power can in addition produce the energy for transportation, warm water, space heating and in part for process heating, requiring an increase of the electric energy production in total by a factor of 5. Then, however, a huge number of wind turbines and solar panels is required changing the appearance of German landscapes fundamentally. Our method can be applied to the wind-solar power problem of any country provided a reliable basis of power data exists over a sufficiently long period.

Review Paper on Energy Management for Home Automation Using AI

Abstract: The smart energy management system was developed with the ability to record, store, and process power consumption data for all major home and industrial devices. Artificial intelligence technologies such as decision making and XG Boost have made advances in power electronics and energy engineering. These technologies provide powerful tools for designing, simulating, controlling, estimating, and fault diagnostic control of modern smart grids and renewable energy systems. AI technology has evolved rapidly over the past few decades, and its applications in modern industrial systems are growing rapidly. Power consumption data can be accessed from the web portal and handheld devices. Homeowners and industry companies can track power consumption by appliance, device, facility, or device. This allows you to better adjust your power consumption. Using the weather forecast, the system decides to switch between photovoltaics or grids using a machine learning concept-based deterministic algorithm. Keywords: Control of smart grid, Energy management system, Artificial Intelligence, Machine Learning, Decision making

Urban building energy and microclimate modeling – From 3D city generation to dynamic simulations

Dynamic urban simulations often face three main challenges: 3D digital city generations, building archetype creations, and inclusions of urban microclimate impacts due to limited data and computing resources available. This study introduces a new approach for the 3D city generation by integrating publicly available data sets (OpenStreetMap and Microsoft footprints) and a free program (Google Earth). These data sets provide 2D building footprints, whereas Google Earth provides digital surface models of terrains and buildings. The building archetype library of non-geometrical properties was created based on building types and years of constructions in the form of shapefiles joined with the 3D city data through QGIS. The proposed workflow also includes the dynamic integration of urban microclimate (CityFFD) and building thermal/energy models (CityBEM). The dynamic simulations were achieved using weather station data as boundary conditions, including air temperature, solar radiation, and wind speed and direction, instead of typical meteorological year data. The transient microclimate results were validated using local weather station data, and dynamic energy simulation results were validated using measured power consumption data. The study provides a solution to dynamic urban building energy and microclimate modeling by publicly available data sets and tools.

A distributed privacy-preserving data aggregation scheme for smart grid with fine-grained access control

Smart grid integrates smart meters and modern communication technologies with the traditional electricity grid. It not only improves efficiency in power resource management, but also enhances reliability of the grid. However, the power consumption data may reveal users’ privacy, e.g. their living habits, and its authenticity is also important for accurate billing. Although a number of privacy preserving data aggregation schemes for smart grid have been proposed in the literature, most of them still suffer some limitations. For example, a single party is normally required to decrypt the aggregated data and this party could be a single point of failure in the system. Moreover, once the aggregated data is decrypted, no access control is imposed and it is available to the public. In order to address the above problems, we introduce a distributed privacy-preserving data aggregation scheme for smart grid with fine-grained access control. In the proposed scheme, homomorphic encryption is employed to ensure user privacy, digital signature is used to ensure data authenticity, distributed proxy re-encryption is used to achieve fine-grained access control of the aggregated data, and zero-knowledge proof is used to ensure that the proxy servers perform their tasks properly. Security analyses prove that the proposed scheme achieves the desirable security properties. In particular, it does not suffer single point of failure and the aggregated data can only be accessed by the designated recipient. Efficiency analyses also demonstrate that it is practical for real-world applications.

Energy Consumption in Commercial Buildings in a Post-COVID-19 World

The ripple effects of the pandemic have resulted in an unprecedented shift in sectoral energy consumption as the workforce predominantly stays and works from home. Quantifying the impact of these restrictions on energy consumption offers a new direction toward intelligent energy services in a post-coronavirus (post-COVID-19) world, especially for commercial buildings. Thus, utilizing actual power consumption data, the study evaluates how energy usage in commercial buildings can change in a post-COVID-19 world, while examining the impact of digitalization to identify potential new opportunities. The article analyzes the changes in energy demand with occupancy rate based on data from 126 commercial businesses with varied classes across Manchester, U.K. The results show that the reduction in energy demand is not proportionate to the occupancy level, resulting in high energy costs. For instance, an average footfall for February 2021 is 10% of 2020, while the costs of electricity only fall to 80% of 2020. Although most of the energy demand is from appliances, the absence of energy efficiency increases energy consumption, highlighting the urgent need for optimized energy efficiency measures to include the time of use and scheduled use of energy across people and processes.

Comparison and application potential analysis of autoencoder-based electricity pattern mining algorithms for large-scale demand response

Studies of electricity consumption behavior patterns (ECBPs) are very important for demand-side management and emission reduction. Most of the existing ECBPs studies have limitations in data volume, algorithm performance and application potential in large-scale data scenario. Based on various autoencoders, this study proposes an ECBPs mining method with better performance and wider application potential. Two indices are constructed for model evaluations. The empirical research results based on the high-frequency power consumption data of residents show that the representation learning of ECBPs through autoencoders can not only effectively reduce the data dimension (reduced by 90%) for pattern mining but also achieve an effect no less than that of pattern mining from the original data, with the difference in pattern aggregation degree between them being only 0.003. Different autoencoders have characteristics in the representation mapping of the original data space. The results also show that the curves decoded by different autoencoders reflect different characteristics suitable for different scenarios. This study solves the dimension disaster problem of ECBPs mining in the context of large-scale data, and provides a better tool for more complex ECBPs based tasks such as multi-energy prosumers modeling and energy system optimization.

Changes in hourly electricity consumption under COVID mandates: A glance to future hourly residential power consumption pattern with remote work in Arizona

The transition to remote work brings uncertainty to the future power consumption pattern. The COVID mandates in 2020 have accelerated the transition to remote work, generating major uncertainty regarding how residential power consumption patterns will shift. Understanding these shifts is vital for regional operators who will need to implement long-term planning strategies if companies continue to adopt remote work practices. Additionally, if new COVID variants prompt extended stay-at-home mandates, the resulting behavior shifts will decide the optimal combination of power generation in a region. Our study examines changes in hourly residential power consumption patterns resulting from COVID mandates in Arizona. We estimate how the COVID mandates and subsequent remote work practices could change the power consumption patterns using individual-consumer-level hourly power consumption data for 6,309 consumers and a machine learning framework. We also simulate how the hourly power consumption pattern will change with increasing penetration of remote work under winter and summer temperature settings. We then use our simulations to test the policy effectiveness of changing time-of-use (TOU) rates. Our results show that COVID mandates likely increase the power consumption in the afternoon by 13%, and can change the power consumption pattern in winter from a two-peaked shape to a one-peaked shape. Furthermore, we show that the residents' income, race, and house size are significantly correlated with the changes in power consumption, and the correlation is not linear. We find that, by increasing the peak hour prices and decreasing the off-peak hour prices by 10% of the TOU pricing, the peak electricity demand could be reduced by 10%. Our results show under the new remote work era: (1) the need for modifying previous energy generation combination planning due to changing peak demand hours; (2) equity concerns regarding TOU pricing and the inability of vulnerable groups to shift electricity consumption; (3) the ability of governments and utilities to lower the maximum load of power consumption by modifying the TOU rates.

Detection of False-Reading Attacks in Smart Grid Net-Metering System

In the smart grid, malicious customers may compromise their smart meters (SMs) to report false readings to achieve financial gains illegally. This causes hefty financial losses to the utility and may degrade the grid performance because the reported readings are used for energy management. This article is the first work that investigates this problem in the net-metering system, in which one SM is used to report the difference between the power consumed and the power generated. First, we prepare a benign data set for the net-metering system by processing a real power consumption and generation data set. Then, we propose a new set of attacks tailored for the net-metering system to create a malicious data set. After that, we analyzed the data and found time correlations between the net meter readings and correlations between the readings and relevant data obtained from trustworthy sources, such as solar irradiance and temperature. Based on the data analysis, we propose a general multidata-source deep hybrid learning-based detector to identify the false-reading attacks. Our detector is trained on net meter readings of all customers besides data from trustworthy sources to enhance the detector performance by learning the correlations between them. The rationale here is that although an attacker can report false readings, he cannot manipulate the solar irradiance and temperature values because they are beyond his control. Extensive experiments have been conducted, and the results indicate that our detector can identify the false-reading attacks with a high detection rate of 98.59% and a low false alarm of 2.92%.

Data-Analytic Assessment for Flexumers Under Demand Diversification in a Power System

Under the carbon-neutral environment, the number of renewable power sources needs to be drastically increased. To respond to the large variability derived from renewable power sources, potential flexible resources have been established and researched. Among these, securing flexibility by using demand is achieved through demand response. For this purpose, it is helpful to identify flexumers—consumers with flexibility—for each player involved in the demand response. To identify the characteristics of flexumers among the demand consumers, we propose a method to classify the characteristics of flexumers into four groups based on power consumption data: price responsivity score, consistency score, flexible amount, and response time score. To verify the effectiveness of the proposed classification, the test system was evaluated with the power-consumption data from 19 companies in 11 industries. One company in the steel industry scored remarkably high in terms of a flexible amount. Overall, companies in the energy, chemical, material, filter and cement industries relatively showed characteristics suitable to flexumers. The suitability for flexumer application was quantitatively compared between industries, and other implications included the scope of criteria application and the direction of formula improvement. With the electrification of other industries, sector coupling, and the digitization of the power industry, the identification of flexumers in demand will significantly alter the plans for securing power-system flexibility. Therefore, the proposed flexumer characteristic formulas can contribute to the advancement of empirical data-based power-industry modeling by classifying resources with flexumer characteristics among the demand agents in the power system model.

Mitigating consumer privacy breach in smart grid using obfuscation-based generative adversarial network.

Smart meters allow real-time monitoring and collection of power consumption data of a consumer's premise. With the worldwide integration of smart meters, there has been a substantial rise in concerns regarding threats to consumer privacy. The exposed fine-grained power consumption data results in behaviour leakage by revealing the end-user's home appliance usage information. Previously, researchers have proposed approaches to alter data using perturbation, aggregation or hide identifiers using anonymization. Unfortunately, these techniques suffer from various limitations. In this paper, we propose a privacy preserving architecture for fine-grained power data in a smart grid. The proposed architecture uses generative adversarial network (GAN) and an obfuscator to generate a synthetic timeseries. The proposed architecture enables to replace the existing appliance signature with appliances that are not active during that period while ensuring minimum energy difference between the ground truth and the synthetic timeseries. We use real-world dataset containing power consumption readings for our experiment and use non-intrusive load monitoring (NILM) algorithms to show that our approach is more effective in preserving the privacy level of a consumer's power consumption data.

Research on Power Consumption Anomaly Detection Based on Fuzzy Clustering and Trend Judgment

Among the end-users of the power grid, especially in the rural power grid, there are a large number of users and the situation is complex. In this complex situation, there are more leakage caused by insulation damage and a small number of users stealing electricity. Maintenance staff will take a long time to determine the location of the abnormal user meter box. In view of this situation, the method of subjective fuzzy clustering and quartile difference is adopted to determine the partition threshold. The power consumption data of end-users are divided into three regions: high, normal and low, which can be used to screen users in the area of abnormal power consumption. Then the trend judgment method is used to further accurately screen to improve the accuracy and reduce the number of users in the abnormal range. Finally according to abnormal power consumption auxiliary locate abnormal electricity users list box. Then the simulation environment is set to verify the application of membership fuzzy clustering and trend judgment in power consumption data partition.

Design of Intelligent Fusion Terminal System with Fog Computing Capability in Distribution Area based on Large Capacity CPU

The intelligent fusion terminal in the distribution area usually adopts the mode of cooperation between the cloud and the edge, and the workload of manual operation and maintenance is large. Therefore, an intelligent fusion terminal system in the distribution area with fog computing capability based on a high-capacity CPU is proposed. Follow the “cloud pipe edge end” construction framework of smart IOT system, and take this framework as the edge computing node of distribution station area and power consumption side. Mt7622b chip in Linux operating system with openwrt firmware is used as the main control chip of edge agent gateway equipment, and the recursive least square method is used to realize the data fusion of power acquisition service in distribution station area and power distribution demand terminal. The test results show that the designed system can realize real-time monitoring of power consumption and distribution data and power quality management in the distribution station area, and the data processing delay is less than 100ms, which provides a reference for the intelligent fusion terminal system in the distribution station area.

The consistency measure of hunan’s electric power industry prosperity index

In view of the problem that the traditional electric power prosperity index lacks the support of the mixed frequency and multi-dimension data, a new consistency measure method is constructed, which uses time difference correlation analysis and principal component and consider the linkage of electric power and economy at the same time. Take the Hunan province for example, we set the pool of kinds of sectional electricity power consumption and other relatives data, use the method of principal component analysis to capture main character of electricity’s change. The results show that the proposed consistency measurement model can describe the fluctuation characteristics of Hunan’s Power Prosperity Index well. The model can be used for monitor the changes in the power industry status and promoting the policy-making about the adjustment of the energy-saving and environment-friendly structure.