Electricity Consumption Data Research Articles

Electricity consumption in campus environments varies based on building functions, occupancy patterns, and time-of-day usage. Understanding these variations is essential for efficient energy management. Uncontrolled electricity use often results in high operational costs, highlighting the need for accurate methods to uncover consumption patterns. This study analyzes electricity consumption data from multiple campus buildings at a polytechnic in Jakarta during 2023 and 2024. Each dataset consists of six columns and 365 rows in a year. Since the data is unlabeled, three clustering algorithms: K-Means, Hierarchical Clustering, and DBSCAN are applied to identify usage patterns across campus areas. Pre-processing included imputation and normalization, followed by clustering. Cluster quality was evaluated using the Silhouette Score. A key novelty of this study is the year-to-year comparative analysis, showing that clustering performance can vary significantly depending on data structure and noise. The 2023 dataset (dataset 1) achieved the highest Silhouette Score of 0.48 using DBSCAN, while the 2024 dataset (dataset 2) produced the best result with Hierarchical Clustering at 0.53. These results emphasize the importance of selecting clustering methods based on data characteristics and temporal context. The findings contribute to developing adaptive, data-driven strategies for managing energy use in non-residential settings, particularly in educational institutions like campuses.

Trends in electrical energy efficiency are key factors influencing production costs in food industry plants, as all production equipment relies on electricity. Accurate forecasting is essential for predicting future consumption and enabling effective energy management. This study aims to analyze and forecast trends in electrical energy efficiency in the food industry. Production and electricity consumption data from January 2022 to December 2023 were used to calculate the difference in electrical energy (DIFF) and the cumulative sum of electrical energy differences (CUSUM), which served as the basis for forecasting. The Long Short-Term Memory (LSTM) model, based on the deep learning approach, was employed to simulate the algorithmic patterns of electrical energy data in the food industry. Its forecasting performance was then compared with two alternative models, namely decomposition and logistic regression, using evaluation data from January to December 2024. Model accuracy was assessed using the Mean Absolute Percentage Error (MAPE) criterion. The results revealed that the decomposition model achieved lower MAPE values for both DIFF (14.47%) and CUSUM (24.13%), while the logistic regression model yielded higher MAPE values of 73.70% and 66.85%, respectively. Therefore, the decomposition model was identified as the most suitable method for forecasting electrical energy consumption trends in the food industry, providing higher accuracy and reliability than logistic regression. Forecasting energy consumption trends using the decomposition model can support strategic energy planning to enhance efficiency, reduce costs, and promote the sustainable development of the food industry in the future.

BackgroundVarious digital biomarkers have been explored to detect cognitive impairment in community-dwelling older individuals, among which electricity consumption (EC) data obtained from smart meters are novel and promising because they pose no burden to the individuals.ObjectiveThe study aimed to explore the potential of EC as a digital biomarker to screen older individuals with cognitive impairment living alone.MethodsWe recruited 40 older individuals living alone and recorded their 1-year daily household EC data. We used the Japanese version of the Montreal Cognitive Assessment to categorize participants into 2 groups: those with and without cognitive impairment. As the pattern of daily household EC is different between lower and higher temperature ranges because of the use of heating and cooling equipment, we divided the daily household EC into 3 temperature ranges. Using a linear mixed model, we evaluated the association between daily household EC, daily outside temperature, and the groups.ResultsAfter excluding 12 participants, they were categorized into 2 groups: those with (10/28, 36%) and without cognitive impairment (18/28, 64%). The daily household EC data consisting of 9391 points showed two characteristics: (1) daily household EC was significantly lower in the group with cognitive impairment than in the group without cognitive impairment in the high temperature range (2.158 kWh at 25 °C, P=.02; 3.712 kWh at 30 °C, P<.001). The increase in EC with rising temperature from 25 °C to 30 °C was less in the group with cognitive impairment (2.387 kWh, P<.001) than in the group without cognitive impairment (3.940 kWh, P<.001); and (2) a tendency for lower daily household EC in the group with cognitive impairment was observed in the moderate temperature range (1.795 kWh at 15 °C, P=.06; 1.582 kWh at 20 °C, P=.08).ConclusionsThe group with cognitive impairment may use less cooling equipment in the high temperature range and fewer home appliances in the moderate temperature range. Daily household EC might be useful in screening cognitive impairment in older individuals living alone.

Non-technical losses (NTL) in power distribution, such as illegal meter tapping, cause significant financial losses for utilities, amounting to billions annually. This study evaluates various machine learning methods for NTL detection, addressing the challenge of imbalanced electricity consumption data. Seven techniques for data balancing were employed: Adaptive Synthetic Sampling (ADASYN), Random Over Sampling, Random Under Sampling, Near Miss Under Sampling, and several variations of Synthetic Minority Over Sampling (SMOTE), including Borderline-SMOTE, SMOTE-ENN, and SMOTE-Tomek links. The model comprises two stages: first, seven classification algorithms (Decision Tree, Logistic Regression, XGBoost, Random Forest, SVM, Naïve Bayes, and KNN) were tested across diverse training-testing ratios to identify optimal performance. The second stage applied the comprehensive consumption dataset along with data balancing techniques to improve algorithm efficacy. Performance metrics—accuracy, precision, recall, F1 score, and Matthews Correlation Coefficient (MCC)—were utilized for evaluation. Results revealed that the Random Forest algorithm, when paired with Random Over Sampling at a 70 − 30% training-testing ratio, yielded the highest metrics: 98.03% accuracy, 99.02% precision, surpassing existing literature. The model achieved exceptional precision (0.990) and the highest overall performance, with rigorous statistical testing confirming all improvements were significant at the 95% confidence level.Supplementary InformationThe online version contains supplementary material available at 10.1038/s41598-025-20048-z.

This paper utilizes unique high-frequency, daily electricity consumption data across economic sectors to examine the impact of monetary policy shocks on economic output, with a particular focus on the network spillover effects and sectoral heterogeneity introduced by inter-sector linkages. The study finds that quantity-based monetary policy (e.g., M2) generates significant positive and cascading spillover effects within the production network. However, the total effects of monetary policy shocks are broadly similar across upstream, midstream, and downstream sectors, exhibiting only minor differences. Notably, the proportion of network (indirect) effects increases systematically from upstream to downstream sectors and displays marked sectoral heterogeneity. In contrast, interest-rate-based monetary policy displays insufficient spatial spillover through production networks. These findings offer important insights for policymakers to optimize structural policy design and promote coordinated sectoral chain development, which can guide the pursuit of sustainable economic strategies that balance growth, resource utilization and sectoral interdependencies.

The increasing energy demand and rising electricity costs have intensified the need for efficient energy management in residential buildings. Load imbalances in power grids and cost surges during peak demand periods are pushing consumers toward more strategic and conscious consumption models. This study focuses on optimizing household electricity consumption through load shifting strategies. To achieve this, a low-cost, Internet of Things (IoT)-based Smart Energy Management System (SEMS) was developed and implemented in a real household. Its performance was then compared with a commercial reference device, revealing an impressive accuracy rate of 99.98%. Electricity consumption data recorded over a one-year period using SEMS was analyzed to assess voltage fluctuations, frequency variations, and energy usage patterns. Daily, weekly, and seasonal consumption trends were identified. Moreover, classifying shiftable and non-shiftable loads enabled a comprehensive evaluation of the load-shifting potential. Scenario-based analyses demonstrated that shifting 25%, 50%, and 75% of shiftable loads to lower-cost tariff periods could result in 9.8%, 17.6%, and 26.1% cost savings, respectively. These findings indicate that SEMS enhances energy efficiency and reduces electricity costs. With its user-friendly interface and low installation cost, SEMS is well-suited for widespread adoption and presents an effective solution for time-based load shifting. Additionally, by encouraging users to adopt more efficient consumption habits, SEMS is expected to contribute to sustainable energy management.

High-resolution smart meter load dataset collected from multiple cities in Morocco

Norwegian energy community dataset: An electricity-hydrogen system with renewables, battery storage & hydrogen demand

SocioDiff: A Socio-Aware Diffusion Model for Residential Electricity Consumption Data Generation

Understanding electricity consumption at a fine-grained spatial level is vital for equitable infrastructure planning in cities. This study analyzes electricity usage patterns across New York City using multiple Machine Learning models, including time series forecasting with Prophet, classification with Random Forest, and regression with ensemble models. This study examine 20212024 monthly electricity consumption data at the borough and neighborhood level to identify high-demand zones, assess prediction accuracy, and evaluate spatial disparities in energy allocation. Using a combination of Gini coefficients, model residuals, and geospatial visualization, the study reveals significant inequalities in model performance and projected load trends. These findings underscore the importance of integrating fairness diagnostics into urban energy modeling, even when using standard public datasets and minimal input features.

Intensive groundwater extraction and a severe 2021 drought have worsened land subsidence in Taiwan's Choshui Delta, highlighting the need for effective predictive modeling to guide mitigation. In this study, we develop a machine learning framework for subsidence analysis using electricity consumption data from pumping wells as a proxy for groundwater extraction. A long short-term memory (LSTM) neural network is trained to reconstruct missing subsidence records and forecast subsidence trends, while an artificial neural network links well electricity usage to groundwater level fluctuations. Using these tools, we identify groundwater-level decline from pumping as a key driver of subsidence. The LSTM model achieves high accuracy in reproducing historical subsidence and provides reliable predictions of subsidence behavior. Scenario simulations indicate that reducing groundwater pumping, simulated by lowering well electricity use, allows groundwater levels to recover and significantly slows the rate of land subsidence. To assess the effectiveness of pumping reduction strategies, two artificial scenarios were simulated. The average subsidence rate at the Xiutan Elementary School multi-layer compression monitoring well (MLCW) decreased from 2.23 cm/year (observed) to 1.94 cm/year in first scenario and 1.34 cm/year in second scenario, demonstrating the potential of groundwater control in mitigating land subsidence. These findings underscore the importance of integrating groundwater-use indicators into subsidence models and demonstrate that curtailing groundwater extraction can effectively mitigate land subsidence in vulnerable deltaic regions.

Smart grids, in their international history, are recognised to be the interface technology that facilitate the sustainable energy transition. There is a great but not fully addressed innovation potential in Brazil in respects to the grid digitalisation within the energy transition domain. Innovation in the Brazilian energy sector is propelled by public policies and government agencies, therefore a comprehensive analysis and diagnosis of smart grid projects and public policies is vital to understand the policy’s issues and gaps in order to promote the energy transition. There are ongoing initiatives to better track the energy transition, such as the Energy Big Push, but they also lack information in regards to smart grid technologies. This research findings identifies that the actual R&amp;D program funds scheme does not address aspects related to the environment and Brazilian social fragility. The regional concentration of smart grid investment predominantly motivated to optimise the system, reduce cost and increase stability in the nearby electrical system is an indication that the R&amp;D Policy should be revised towards a common energy transition that is fair and sustainable. In response to the identified gap in strategic positioning for energy transition in Brazil, this paper suggests a public policy to establish national guidelines for transparency of distributed generation and electricity consumption data. Currently, there is no national framework that integrates these data in a standardised and accessible manner, preventing the holistic view necessary for an equitable energy transition. Key elements of this policy should include requirements for energy utilities to collect and publicly share data on distributed energy resources and consumption patterns through standardised dashboards.

Rural Alaskan communities face many housing challenges. Additionally, heating oil and electricity prices are significantly higher than the U.S. average. Identifying systematic opportunities for housing improvements in these highly energy-burdened areas is essential. Building energy simulation can help estimate energy consumption, however, publicly available data on rural Alaskan housing characteristics is limited. This study uses field-collected data to develop residential building archetype models based on clusters defined by key housing characteristics, such as home area and age, as well as infiltration and insulation levels. Three representative archetypes were created to reflect the diversity of the housing stock in the community. Energy models were developed and validated using measured electricity consumption data, with modelled results showing overall agreement with actual usage (NMBE >5%). The findings can support overall evaluation of the state of housing energy performance in several small rural Alaskan communities as well as the potential impact of housing improvements.

An in-depth investigation into the evolutionary characteristics, transmission mechanisms, and optimization pathways of electricity consumption linkages across China’s industrial sectors highlights their substantial theoretical and practical significance in achieving the “dual carbon” goals and advancing high-quality economic development. This study investigates the structural characteristics and developmental trends of electricity consumption linkages across China’s industrial sectors using an enhanced hypothetical extraction method. The analysis draws on national input–output tables and sector-specific electricity consumption data during the period from 2002 to 2020. Key transmission routes between industrial sectors are identified through path analysis and average path length calculations. The findings reveal that China’s industrial electricity consumption structure is marked by notable scale expansion and differentiation. The magnitude of inter-sectoral electricity flows continues to grow steadily. The evolution of these linkages exhibits clear phase-specific patterns, while the intensity of electricity consumption connections across sectors shows pronounced heterogeneity. Furthermore, the transmission path analysis revealed differentiated characteristics of electricity influence transmission, with generally shorter internal paths within sectors, significant cross-sectoral transmission differences, and manufacturing demonstrating good transmission accessibility with moderate path distances to major sectors. These insights provide a robust foundation for designing differentiated energy conservation policies, as well as for optimizing the overall structure of industrial electricity consumption.

Electricity has emerged as an essential requirement in modern life. As demand escalates, electricity costs rise, making wastefulness a drain on financial resources. Consequently, forecasting electricity usage can enhance our management of consumption. This study presents an IoT-based monitoring and forecasting system for electricity consumption. The system comprises two NodeMCU micro-controllers, a PZEM-004T sensor for collecting real-time power data, and three relays that regulate the current flow to three distinct electrical appliances. The data gathered is transmitted to a web application utilizing the k-Nearest Neighbor (k-NN) algorithm to forecast future electricity usage based on historical patterns. We evaluated the system's performance using four weeks of electricity consumption data. The results indicated that predictions were most accurate when the user’s daily consumption pattern remained stable, achieving a Mean Absolute Error (MAE) of approximately 1 watt and a Mean Absolute Percentage Error (MAPE) ranging from 1% to 1.7%. Additionally, predictions were notably precise during the early morning hours (3:00 AM to 8:00 AM) when k=6 was employed. This study demonstrates the effectiveness of integrating IoT-based systems with machine learning for real-time energy monitoring and forecasting. Furthermore, it emphasizes the application of data mining techniques within embedded IoT environments, providing valuable insights into the implementation of lightweight machine learning for smart energy systems.

The uneven distribution of electricity demand across Indonesia necessitates the development of Renewable Energy Sources, particularly wind energy. This study evaluates the performance efficiency of horizontal-axis wind turbines equipped with two blade types: taper and taperless, both using the NACA 0012 airfoil. Aerodynamic simulations were conducted using QBlade software. Wind speed data from 2017 to 2022 were sourced from the European Centre for Medium-Range Weather Forecasts (ECMWF), while electricity consumption data were obtained from the Statistics Bureau of Pesisir Barat Regency. A quantitative approach using descriptive graphical analysis was employed to compare the performance metrics of the two blade designs. The results show that the taperless blade achieves higher power coefficient (Cp) and torque coefficient (Ct) values compared to the taper blade, although the taper blade produces greater torque (T). The energy conversion of the taperless blade reached 347.6 kWh, representing an increase of approximately 4.83% over the 331.6 kWh generated by the taper blade. Further analysis indicates that approximately 19 taperless-blade turbines are required to meet the daily electricity demand of 6,545 kWh in Pesisir Barat Regency. These findings support the recommendation to adopt taperless blades for improved wind energy utilization in the region.

In order to solve the problem that the existing methods of electricity theft detection in dedicated user photovoltaic systems are difficult to capture subtle anomalies in non-stationary electricity consumption data, this paper introduces a method combining wavelet transform and support vector machine (WT-SVM). The Daubechies wavelet basis function is used to perform multi-scale decomposition of photovoltaic electricity consumption data, extract time-frequency features, and capture transient anomalies in electricity theft behavior. The extracted features are input into the SVM classification model, and the model is trained through the RBF kernel function. Grid search and cross-validation are used to optimize hyperparameters to improve the generalization ability of the model.The results show that under the same photovoltaic power theft detection dataset and test environment, the WT-SVM in this paper extracts time-frequency features through multi-scale wavelet decomposition and combines RBF (Radial Basis Function) and SVM classification, achieving an F1 score of 94.5%, a low latency of 35ms and a noise resistance of 91.2%, and outperforms the comparison model (Time-Freq Transformer: 62.4MB; MobileNetst: 5.7MB) with a lightweight of 2.1MB. The method in this paper has a good recognition effect on electricity theft behaviors such as current bypass, inverter tampering, and data injection, verifies the effectiveness of the fusion of wavelet time-frequency analysis and machine learning, and provides a high-precision and high-practicality solution for electricity theft detection in photovoltaic systems.

Relevance. The increasing electricity consumption in the private residential sector, driven in part by the growing use of electric heating, is leading to higher loads on 0.4 kV power transmission lines. Traditional standardized load profiles do not always reflect modern consumption patterns and conditions, which creates risks of inaccurate assessments of the electrical grid’s capacity and necessitates more precise modeling of grid operating conditions.Purpose. To develop approaches for classifying consumers and identifying statistically significant patterns in electricity consumption in private residential areas for subsequent calculation of grid operating conditions.Methods. The analysis was based on half-hourly electricity consumption data from 42 private houses, collected via an Automated Meter Reading and Management System (AMRMS). The data was cleaned using the three-sigma rule to remove gaps and outliers, and heat maps were used to identify non-representative consumers. The statistical significance of differences was determined using analysis of variance (ANOVA) and Tukey’s test. Based on median consumption values, consumer groups were formed (low and high electricity consumption). Data processing and visualization were performed using MS Excel, Python (Pandas, NumPy, SciPy libraries), and the Statistica software package.Results. The analysis confirmed statistically significant differences in electricity consumption between most of the houses (F = 2065.4, p &lt; 0.001). Tukey’s test showed that within each group, homes exhibited relatively stable energy consumption values, while intergroup comparisons revealed substantial variations in electricity usage. As a result of the study, two consumer types were identified: "low" and "high" consumption groups. The high-consumption group exhibited distinct evening peaks (18:00–22:00), whereas the low-consumption group had a more evenly distributed load profile.Conclusion. The application of statistical analysis methods to electricity consumption data enabled the simplification of household classification into two main groups and the development of typical consumption profiles. These results were integrated into the LineCapacity software, facilitating grid operation calculations and reducing the risk of misjudging the available power transmission capacity. A promising research direction is planned, focusing on expanding the dataset on residential electricity consumption. This will allow for the consideration of seasonal factors and the development of simulation modeling mechanisms for various consumer groups.

Accurately identifying the sources of fine particulate matter (PM2.5) pollution is crucial for pollution control and public health protection. Taking the PM2.5 pollution event that occurred in Suzhou in June 2023 as a typical case, this study analyzed the characteristics and components of PM2.5, and quantified the contributions of meteorological conditions, regional transport, and local emissions to the summertime PM2.5 surge in a typical Yangtze River Delta (YRD) city. Chemical composition analysis highlighted a sharp increase in nitrate ions (NO3−, contributing up to 49% during peak pollution), with calcium ion (Ca2+) and sulfate ion (SO42−) concentrations rising to 2 times and 7.5 times those of clean periods, respectively. Results from the random forest model demonstrated that emission sources (74%) dominated this pollution episode, significantly surpassing the meteorological contribution (26%). The Weather Research and Forecasting model combined with the Community Multiscale Air Quality model (WRF–CMAQ) further revealed that local emissions contributed the most to PM2.5 concentrations in Suzhou (46.3%), while external transport primarily originated from upwind cities such as Shanghai and Jiaxing. The findings indicate synergistic effects from dust sources, industrial emissions, and mobile sources. Validation using electricity consumption and key enterprise emission data confirmed that intensive local industrial activities exacerbated PM2.5 accumulation. Recommendations include strengthening regulations on local industrial and mobile source emissions, and enhancing regional joint prevention and control mechanisms to mitigate cross-boundary transport impacts.

This study examines the impact of the Beijing–Tianjin–Hebei (BTH) coordinated development policy on the regional industrial network structure, with a focus on the significance of electricity consumption data in social network analysis (SNA). Utilizing a gravity model integrated with electricity consumption data, this research employs centrality analysis and Lambda analysis to compare changes in the steel industry network before and after policy implementation. The findings reveal that traditional models relying solely on indicators such as population and Gross Domestic Product (GDP) fail to comprehensively capture regional economic linkages, whereas incorporating electricity consumption data enhances the model’s accuracy in identifying core nodes and latent connections. Post policy implementation, the centrality of Beijing and Tianjin increased significantly, reflecting their transition from production hubs to centers for research and development (R&amp;D) and management, while Shijiazhuang’s pivotal role diminished. This study also uncovers a “core–periphery” structure in the BTH urban network, where core cities (Beijing, Tianjin, and Shijiazhuang) dominate resource allocation and information flow, while peripheral cities exhibit uneven development. These results provide a scientific basis for optimizing regional coordinated development policies and underscore the critical role of electricity consumption data in refining regional economic analysis. Incorporating electricity consumption data into the gravity model significantly enhances its explanatory power by capturing hidden economic ties and improving policy evaluation, offering a more accurate and dynamic assessment of regional industrial linkages.