Electric Big Data Research Articles

Algorithm for detecting abnormal electricity usage by customers based on electricity big data and deep learning

Abstract In order to optimize the effect of individuals’ aberrant power utilization detection and reinforce the recognition rate and accuracy of abnormal power consumption detection of electricity use, an aberrant power utilization identification algorithm based on electric power big data and deep learning is proposed. Taking the two-way dialogue between power users and the power company as the basic perspective, real-time monitoring and collection of power consumption dynamics of users is carried out, and the power big data collection framework is designed. The retrieval of aberrant power utilization detection indexes is completed. Based on the deep learning algorithm, the artificial neural network base operation medium is combined to quantitatively solve the aberrant power utilization indexes, completing the design of a user aberrant power utilization detection algorithm. Experimental results show that the accuracy of the designed algorithm is 0.963, the F1 value is 0.985, and the AUC value is 0.942, which can effectively identify the aberrant power utilization and has a better performance of abnormal power consumption identification and detection.

An electricity big data application to reveal the chronological linkages between industries

ABSTRACT Effective integration and compromise between theories and empirical data are essential for an operational economic model. However, existing economic models often neglect the intricate fluctuations and transitions that occur in weeks and days. This research proposes an Input–Output-based algorithm to introduce the time domain into economic modelling. Using daily electricity consumption big data in Chongqing as a proxy for economic activities, we quantitatively analyse the chronological interactions among industrial sectors and reveal that a longer duration is required by the heavy industry sector to signal an intermediate production in the service sector than any other sectors in this municipality. With the proposed model, we forecast the economic impact induced by demand changes for consumer goods under three growth scenarios. The model not only serves as a methodological bridge between theoretical and data-driven approaches but also offers new insights into the dynamic interplay of sectoral activities over time.

A Big Data-Driven Approach for Early Warning of Enterprise Emissions Alignment with Carbon Neutrality Targets: A Case Study of Guangxi Province

Achieving the target of carbon neutrality has been an important approach for China to mitigate global climate change. Enterprises are major carbon emitters, and a well-designed early warning system is needed to ensure that their emissions align with carbon neutrality goals. Therefore, this study utilized electricity big data to construct an early warning model for enterprise carbon emissions based on carbon quota allocation. Taking key carbon-emitting enterprises in Guangxi as a case study, we aim to provide insights to support China’s dual carbon goals. Firstly, we established the Carbon Quota Allocation System, enabling carbon quota allocation at the enterprise levels. Secondly, we developed the Enterprise Carbon Neutrality Index, facilitating dynamic warnings for carbon emissions among enterprises. The main conclusions are as follows: (1) In 2020, Guangdong received the highest carbon quota of 606 million tons, representing 5.72% of the national total, while Guangxi only received 2.63 billion tons. (2) Only 39.34% of enterprises in Guangxi are able to meet the carbon neutrality target, indicating significant emission reduction pressure faced by enterprises in the region. (3) Over 90% of enterprises in Guangxi receive Commendation and Encouragement warning levels, suggesting that enterprises in Guangxi are demonstrating a promising trend in emission reduction efforts.

Rapid carbon emission measurement during the building operation phase based on PSO–SVM: electric big data perspective

With the rapid development of urbanization in China, urban energy consumption increases rapidly, leading to energy shortages and environmental pollution, of which building operational energy consumption carbon emissions (BECCE) account for a large proportion. It has a vital impact on global warming and urban green and sustainable development. Chengdu city in Sichuan Province is taken as the research area in this paper. First, basic information and power data on four types of single buildings, including large-sized buildings, small- and medium-sized buildings, government agencies, and residential buildings, are collected. Second, the characteristics of the four types of buildings are extracted, and the calculation model of BECCE (“electricity-carbon” model) based on particle swarm optimization algorithm–support vector machine (PSO–SVM) is constructed, and the model is trained and verified using the method of five-fold cross-validation. Then, according to the mean absolute error (MAE), root mean square error (RMSE), and R2 evaluation indicators, the constructed “electricity-carbon” model is compared and evaluated. Finally, the generalization ability of the “electricity-carbon” model is verified. The research results show that (1) the “electricity-carbon” model constructed in this paper has a high accuracy rate, and the fitting ability of the PSO–SVM model is significantly better than that of the support vector regression (SVR) model; (2) in the testing stage, the fitting situation of large buildings is the best, and MAE, RMSE, and R2 are 858.7, 1108.6, and 0.91, respectively; and (3) the spatial distribution map of regional BECCE can be quickly obtained using the “electricity-carbon” model constructed in this paper. The “electricity-carbon” model constructed in this paper can provide a scientific reference for building emission reduction.

Predicting air pollutant emissions of the foundry industry: Based on the electricity big data

Industrial enterprises are one of the largest sources of air pollution. However, the existing means of monitoring air pollutant emissions are narrow in coverage, high in cost, and low in accuracy. To bridge these gaps, this study explored a predicting model for air pollutant emissions from foundry industries based on high-accuracy electricity consumption data and continuous emission monitoring system (CEMS). The model has then been applied to the calculation of air pollutant emissions from foundries without CEMS and the optimization of air pollutant emission temporal allocation factors. The results reveal that electricity consumption and PM emissions during the 2022 Beijing Winter Olympics have the same ascending and descending relationship. Furthermore, a cubic polynomial model between electricity consumption and flue gas flow is established based on the whole year data of 2021 (R2 = 0.85). The relative errors between the PM emissions calculated by the model and the emission factor method are small (−17.09–24.12 %), and the results from the two methods revealed a strong correlation (r = 0.93, p < 0.01). In addition, the monthly PM emissions from foundries are mainly concentrated in spring and winter, and the daily emissions on weekends are significantly lower than those on workdays. These results can be useful for environmental regulation and optimization of air pollutant emission inventories of foundry industry.

Real-Time Carbon Emissions Monitoring of High-Energy-Consumption Enterprises in Guangxi Based on Electricity Big Data

Real-time carbon emissions monitoring at the enterprise level is a crucial tool in shifting macrolevel carbon peak and carbon neutrality plans toward micro-level implementations. This study extends the existing CO2 emissions accounting framework to enterprise emissions monitoring. We analyze the correlation mechanism between electricity consumption and CO2 emissions by industries, calculate the electricity–CO2 coefficients, and finally model an enterprise-level real-time carbon emissions monitoring method based on electricity big data. Taking Guangxi region as a sample, the results show that (1) the proportion of electricity-related emissions is on the rising stage in Guangxi, with 441 g CO2/KWh emitted from electricity consumption in 2020, (2) the carbon emissions from the energy-intensive industries account for over 70% of the whole society, and they all have high electricity–CO2 coefficients, far exceeding the industry average of 1129 g/kWh, and (3) the monitoring method is applied to 1338 enterprises from over 40 industries. The emission characteristics reflect the regional and industrial heterogeneity. This enterprise-level monitoring method aims to optimize the carbon emissions calculation method toward higher temporal and spatial resolutions, so as to provide an important numerical basis for promoting carbon emission reduction and sustainable development.

Challenges in Assessing the Behaviour of Nodal Electricity Prices in Insular Electricity Markets: The Case of New Zealand

In this new era of energy transition, access to reliable and correctly functioning electricity markets is a huge concern for all economies. The restructuring path taken by most electricity markets involves the movement towards green generation structures and the increasing integration of wind and solar photovoltaic energy sources. Furthermore, it involves the electrification of energy systems, which implies a substantial increase in electricity demand levels. It is also important to add that electricity use has been pivotal in achieving efficient productivity levels in many sectors and is thus crucial to boosting economic activity. Nevertheless, this shift in generation structures has raised several challenges in electricity markets, mainly because the electricity produced from wind and solar photovoltaics is intermittent. In turn, adopting green power sources has been claimed to increase electricity price volatility and thus increase pricing risks. Therefore, to ensure that the right market signals are being sent to investors, the behaviour of electricity prices should be carefully assessed. There are three main types of pricing mechanisms commonly used in electricity markets: zonal, uniform and nodal. This study provides a short literature survey on these three pricing mechanisms. Our analysis has revealed that the assessment of the behaviour of nodal electricity price volatility is rarely studied in the literature. This fact has motivated the exploration of this topic and the consideration of the New Zealand electricity market case. The New Zealand electricity market is an energy-only system with no interconnections with other electricity markets. Furthermore, it has plenty of electricity produced from hydropower, which has a high potential to reduce price volatility through its backup role. The nodal pricing mechanism is complex, and data on it are hard to process. This paper elucidates the main challenges in processing electricity big data. Three different procedures to make this data more useable are described in detail. The main conclusions of this paper highlight the need to access easy-to-manage data and identify certain variables that significantly affect nodal prices for data which are unavailable.

Monitoring the enterprise carbon emissions using electricity big data: A case study of Beijing

Enterprises are major sources of anthropogenic carbon emissions, and high-quality data on enterprise carbon emissions are prerequisites for climate abatement policies and actions. However, most of the existing data are more than one-year lagging, easily manipulated, and concentrated at the industrial or regional level. To bridge these gaps, this study develops a monitoring approach for enterprise carbon emissions by combining electricity big data, bottom-up emission accounting model, and network model. The proposed approach has then been applied to monitor the real-time carbon emissions of 0.81 million enterprises in Beijing. Our major findings are that: (1) Owing to a large amount of embodied carbon emissions from electricity inflow, Beijing's electricity-related CO2 emissions are 73.57 million tonnes in 2020, constituting 55% of its total. (2) The CO2 emissions per kWh of electricity consumed in Beijing is 645.26 g, whose top three traceable contributors are Hebei (206.71 g), Shanxi (142.21 g), and Beijing itself (133.07 g). (3) The average monitoring error of enterprise carbon emissions is less than 7%, proving the effectiveness of the proposed approach using electricity big data.

Report on the Current Situation and Innovation Research of Data Development in New Power Systems

The article discusses the emergence of big data in the electricity industry with the introduction of smart grids. The construction of smart grids globally has led to an increase in monitoring data that traditional power data processing systems cannot handle, presenting both opportunities and challenges for the industry. Enterprises must establish new strategic management directions, collaborate with other entities for innovation, improve data systems, and protect data security. The article predicts the future trends of data centers and analyzes carbon emissions calculations. It also explores how the application of electricity big data can assist the industry in creating a comprehensive ”energy ecosystem” to revolutionize the production and consumption of electricity enterprises.

Complaint electricity customer clustering method based on electricity big data

In the fierce domestic market competition, the improvement of service quality is an important goal of electricity companies. This paper proposes the k-means algorithm based on the improved wolf pack algorithm, which is suitable for the power company complains, there are many factors that affect user complaints. Firstly, the PCA method is used to reduce the dimension of the complaint user’s behavior influencing factors, so as to improve the accuracy of clustering. Secondly, due to the shortcomings of falling into local optimal solution and low clustering accuracy, this paper proposes an improved wolf pack algorithm, which proposes the interactive strategy of walking behavior, calling behavior and an adaptive siege strategy for behavior, the clustering accuracy and convergence speed are improved.This algorithm overcomes the shortcomings of the original algorithm. Moreover, it improves the efficiency and clustering quality of the algorithm and it can realize the accurate classification of users.

Privacy Protection Method of Electric Power Network Based on Blockchain

In order to ensure the integrity and confidentiality of power data in the era of big data, it is very important to protect the privacy of smart grid data information. Analyzing electricity big data can obtain electricity consumption habits of electricity users to guide the formulation of power supply plans. This experiment uses an asymmetric encryption algorithm. The encryption and decryption of the asymmetric encryption algorithm use two different keys to fully guarantee the security of the blockchain system. The experiment is based on the blockchain technology in photovoltaic microgrid electricity trading, which belongs to the current type of trading, which is divided into five stages. The service provider is a node of the blockchain system. All smart contracts are encrypted by the private key of both parties in the transaction and the public key of the service provider, which fully guarantees the privacy of users. The experimental data shows that the smart contract is decrypted by the private key and the public key of both parties, so as to obtain the relevant information of the transaction and make the corresponding power dispatch work during the transaction period.The blockchain system solves the security and privacy issues of both parties in the absence of a third-party intermediary. Therefore, the use of blockchain technology can achieve a higher degree of automation for point-to-point power transactions.

A Study on Acer Mono Sap Integration Management System Based on Energy Harvesting Electric Device and Sap Big Data Analysis Model

This study set out to invent an Information and Communication Technologies (ICT)-based smart Acer mono sap collection electric device to make efficient use of the labor force by reducing inefficient activities of old manual work to record sap exudation and state information. Based on the assumption that environmental information would have close connections with Acer mono sap exudation to reinforce the competitive edge of production in forest products, the study analyzed correlations between Acer mono sap exudation and environmental information and predicted Acer mono exudation. A smart collection of electric devices would gather data about Acer mono sap exudation per hour on outdoor temperature, humidity, conductivity, and wind direction and velocity, and was installed in four areas in the Republic of Korea, including Sancheong, Gwangyang, Geoje, and Inje. Collected data were used to analyze correlations between environmental information and Acer mono sap exudation using four different algorithms, including linear regression, Support Vector Machine (SVM), Artificial Neural Network (ANN), and random forest, to predict Acer mono sap exudation. Remarkable outcomes were obtained across all the algorithms except for linear regression, demonstrating close connections between environmental information and Acer mono sap exudation. The random forest model, which showed the most outstanding performance, was used to make a mobile app capable of providing predicted Acer mono sap exudation and collected environmental information.

A Smart and Safe Electricity Consumption Model for Integrated Energy System Based on Electric Big Data

A Smart and Safe Electricity Consumption Model for Integrated Energy System Based on Electric Big Data

Spark-based Parallel OS-ELM Algorithm Application for Short-term Load Forecasting for Massive User Data

The data type and quantity of user load data show an exponential growth, so that the traditional load forecasting methods can hardly meet the load forecasting requirements of massive users. Aiming at this problem, a parallel OS-ELM short-term load forecasting model based on Spark is proposed in this article. By analyzing the characteristics of the Spark framework and the MapReduce framework, the Spark big data processing framework is determined as the basic framework for processing massive user load data, and a parallel K-means load clustering model based on Spark is designed. The on-line sequential learning machine OS-ELM makes the hidden layer data of computing each incremental training dataset mutually independent, therefore, a Spark-based parallel OS-ELM (SBPOS-ELM) algorithm is put forward. The proposed model is applied under the smart electricity big data environment and the training samples are selected using the incremental training dataset to make a short-term prediction of the millions of users’ smart meter electricity load, which verifies the feasibility and effectiveness of the proposed model. At last, comparing with other commonly used short-term load forecasting algorithms, the experimental results show that SBPOS-ELM algorithm has higher accuracy and operation efficiency.

Unified Searching Service for Electric Big Data

For Electric Management Information System (EMIS), different types of data are continuously generated from many sub-systems. It is essential to integrate these different data resources to perform better analysis and more accurate calculation about the Power Grid system. However, existing EMIS is combined with separate platforms, and the data formats are various. In this paper, we propose a unified searching service for EMIS based on the integration of electric big data. In the system, different sources are firstly configured to export their data into the Hadoop Distributed File System (HDFS). Then indexing is generated and the keywords of different data are generated by word2vec. Finally, a Mapreduce based processing, searching and recommending the system is developed. The microservice technology and Hadoop framework is applied to implement the proposed framework and the experimental results indicate the proposed method can effectively create a unified search service for the electric company.

Adaptive Optimized Pattern Extracting Algorithm for Forecasting Maximum Electrical Load Duration Using Random Sampling and Cumulative Slope Index

Load forecasting techniques can be an essential method to save energy and shave peak loads in order to improve energy efficiency and maintain the stability of a power grid. To achieve this goal, machine learning-based approaches have been proposed recently. Before moving toward the long-term and ultimate solution such as machine learning, we propose a simple and efficient method to forecast electricity usage patterns and the duration of maximum electrical load using a small data set. The proposed algorithm can forecast maximum electrical load duration using random sampling and a cumulative slope index. To verify the algorithm, we utilized electricity data (from 2015.11 to 2016.12) obtained from a building with a constant lifestyle and electricity pattern. The performance of the algorithm was evaluated using electricity bills, the discharging condition of an energy storage system, and the cumulative slope index. It was found that the proposed algorithm could provide electricity cost savings of 0.62–2.28% compared with other, conventional electricity prediction techniques, such as the moving average method and exponential smoothing. In near future research, it is expected that this algorithm could be applied to electrical big data to handle real-time data processing.

The Selection and Placement Method of Materialized Views on Big Data Platform of Equipment Condition Assessment

With the formation of electric big data environment, more and more big data analyses emerge. In the complicated data analysis on equipment condition assessment, there exist many join operations, which are time-consuming. In order to save time, the approach of materialized view is usually used. It places part of common and critical join results on external storage and avoids the frequent join operation. In the paper we propose the methods of selecting and placing materialized views to reduce the query time of electric transmission and transformation equipment, and make the profits of service providers maximal. In selection method we design a computation way for the value of non-leaf node based on MVPP structure chart. In placement method we use relevance weights to place the selected materialized views, which help reduce the network transmission time. Our experiments show that the proposed selection and placement methods have a high throughput and good optimization ability of query time for electric transmission and transformation equipment.

Data Mining Analysis and High-dimensional Visualization Based on Electric Big Data

with the popularization of intelligent ammeter, collection of users’ power utility information can be more accurate and smart. Every other 15 minutes, backstage of power supply companies can read power utility data automatically. By collecting data based on optimized scatter diagram in non-linear polynomial form, power supply companies can accurately analyze and display users’ power utility habits in more dimensions and angles through parallel coordinate system based on convex hull optimization. They are also able to synthesize multiple users’ power utility information and geographical information of communities, so as to establish improved comprehensive assessment system for residential quarters. In addition, power supply companies can synthesize visualized analysis on the relation between power utility of various industries in urban areas and GDP data, so as to further explore the interactive function of industry power utility and regional development; thus can also provide significant reference value for regional development strategies.

Study on the User-Side Risk of Smart Grid System in Big Data Age

With the coming of big data age, Internet, finance and other industries have launched in-depth studies on big data technology. They hope to grasp the opportunities that big data brings to enterprises. Smart gird construction generated massive and heterogeneous data in the process of electricity generation, electricity transmission and electricity consumption, thus electricity big data took shape. Based on the analysis of Big Data characteristics of Smart gird user-side, this paper describes the risks that big data reduces on smart gird user-side from the perspectives of demand forecasting, customer complaint and operation risk that grid peak valley load brings. Meanwhile, it also expounds the risks that big data brings to Smart gird user-side from the perspectives of technology and user information security. Hope to provide some relevant materials of the Smart gird user-side risk management for our country.