Electricity Consumption Patterns Research Articles

Electricity user behavior analysis and marketing strategy based on internet of things and big data

This paper examines power user behavior and the design of marketing strategies, using a case study of Smart Community A. We explore how advanced analytical models are used to enhance energy efficiency and user services. First, we apply spectral clustering to refine user segmentation and identify distinct electricity consumption patterns among different groups. Then, the Hidden Markov Model (HMM) analyzes user behavior, uncovering shifts in consumption habits and enabling personalized service offerings. Next, the ARIMA model predicts electricity consumption trends, guiding grid scheduling and resource allocation. Based on these analyses, we develop targeted marketing strategies, such as dynamic pricing and energy-saving incentives, which boost user engagement and reduce energy usage. Through an IoT and big data-driven interactive marketing platform, we enhance user experience and foster a culture of energy conservation. Finally, a feedback mechanism ensures continuous improvement and maximizes the effectiveness of the marketing strategies.

Sky-Scanning for Energy: Unveiling Rural Electricity Consumption Patterns through Satellite Imagery’s Convolutional Features

The pursuit of the Sustainable Development Goals has highlighted rural electricity consumption patterns, necessitating innovative analytical approaches. This paper introduces a novel method for predicting rural electricity consumption by leveraging deep convolutional features extracted from satellite imagery. The study employs a pretrained remote sensing interpretation model for feature extraction, streamlining the training process and enhancing the prediction efficiency. A random forest model is then used for electricity consumption prediction, while the SHapley Additive exPlanations (SHAP) model assesses the feature importance. To explain the human geography implications of feature maps, this research develops a feature visualization method grounded in expert knowledge. By selecting feature maps with higher interpretability, the “black-box” model based on remote sensing images is further analyzed and reveals the geographical features that affect electricity consumption. The methodology is applied to villages in Xinxing County, Guangdong Province, China, achieving high prediction accuracy with a correlation coefficient of 0.797. The study reveals a significant positive correlations between the characteristics and spatial distribution of houses and roads in the rural built environment and electricity demand. Conversely, natural landscape elements, such as farmland and forests, exhibit significant negative correlations with electricity demand predictions. These findings offer new insights into rural electricity consumption patterns and provide theoretical support for electricity planning and decision making in line with the Sustainable Development Goals.

The Practical Impact of Price-Based Demand-Side Management for Occupants of an Office Building Connected to a Renewable Energy Microgrid

This paper examined the practical impact of price-based demand-side management (DSM) for occupants of an office building connected to a renewable energy microgrid. There has been an absence of studies that have analyzed occupant reactions, in terms of perceived practicality, regarding the implementation of DSM in conjunction with factors including renewable energy generation, load shifting and energy costs. An increased understanding of the practicality of DSM will support future improvements in building energy efficiency and sustainability. Ten occupants of the National Build Energy Retrofit Test-bed (NBERT) were selected as a case study. The electricity consumption pattern of the NBERT occupants was derived over a period of two years. Five unique DSM schedules were developed for each of the NBERT occupants, and a survey was carried out to investigate the practicality of these DSM schedules. A real-time electricity pricing tariff, electricity CO2 intensity, three feed-in tariffs and two microgrid control methods were evaluated to assess the practicality of each DSM schedule on the ten NBERT occupants. The results showed that the incorporation of onsite renewable energy generation with price-based DSM had a positive impact (r = 0.69–0.75) on occupant practicality. Onsite renewable energy generation was able to offset the demand for expensive electricity from the grid during peak hours, which aligned with the occupants’ typical work schedules. However, the introduction of a feed-in tariff with a renewable energy microgrid made price-based DSM less practical (r = 0.15–0.64).

Impact of variable electricity price on heat pump operated buildings

Background Residential buildings with heat pumps show promising possibilities for demand-side management. The operation optimization of such heating systems can lead to cost reduction and, at the same time, change electricity consumption patterns, which is especially prevalent in the case of a variable price signal. In this work, we deal with the following question: How does the volatility of a variable retail electricity price change the energy consumption of buildings with a smart energy management system? Methods In this context, we take Austria as an example and aggregate the findings of individual households to the national stock of single-family houses. This is done by simulating and optimzing heating operation in single representative buildings. The aggregation is done based on national building information statistics. Results This part of the Austrian building stock could shift 19.7 GWh of electricity per year through thermal inertia using a real-time electricity price from 2021. We show the future potential under the assumption of three electricity price trends for 2030, representing different decarbonisation ambition levels. The trends show that higher decarbonisation levels which lead to higher electricity prices increase the incentive to shift electric loads. Conclusions Real time pricing turns out to be an effective incentive for buildings to shift electric loads by pre-heating the building mass. However, cost savings for individuals are relatively low which is why additional monetary incentives are needed to tap into that potential. Increased daily peak-to-peak demand from these buildings has to put into perspective to the overall grid load.

Predicting Industrial Electricity Consumption Using Industry–Geography Relationships: A Graph-Based Machine Learning Approach

Accurately predicting industrial electricity consumption is of paramount importance for optimizing energy management and operational efficiency. Traditional forecasting approaches face significant challenges in capturing the complex factors influencing industrial electricity consumption, often due to the inadequate representation of correlations, thus limiting their predictive capabilities. To overcome these limitations, we propose a novel graph-based forecasting model termed Industry–Geography Time Series Forecasting Model (IG-TFM). Our approach leverages historical electricity consumption data and geographical information relevant to similar industries to construct an industry–geography relationship graph. This graph serves as the foundation of a comprehensive network that encompasses all industries of interest, allowing us to identify sectors closely associated with the target industry. The structured graph data are then processed within a graph convolutional neural network framework, which effectively captures the impact of geographical location, industry similarities, and inter-industry relationships on electricity consumption patterns. Utilizing this enriched representation, we develop our IG-TFM for accurate time series forecasting of industrial electricity consumption. Experiments conducted on real-world data, including 31 industries across 9 cities in a southern province of China, demonstrate the significant advantages of our proposed method across key performance indicators such as the Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). These findings underscore the importance and efficacy of employing complex networks to encode sequence-related information, thereby substantially improving prediction accuracy in industrial electricity consumption forecasting.

Who engages in electricity conservation and to what effect after real-world, high-resolution feedback? An empirical analysis of Korean households with smart meters

Engagement with households to fully realize the potential of demand-side solutions has attracted policy attention. The potential of feedback has been understudied, especially regarding who engages more in electricity conservation. Furthermore, most studies have been limited to the Western context, with only a few that explore Asia. This study fills these gaps by investigating changes in household hourly electricity consumption patterns after its members receive high-resolution feedback. After data balancing, we partitioned 63 households into distinct groups using K-means clustering and investigated consumption changes after the provision of high-resolution electricity feedback through a mobile application. The results indicate mixed effectiveness of feedback: some households reduced consumption by about 13 %, while others increased it between 7 % and 20 %. In addition, statistical analysis using survey responses revealed that households with greater awareness of electricity costs and a stronger interest in climate change were more receptive to feedback. Demographic and housing attributes such as age, building type, and floor count also influenced the feedback effect. The findings recommend enhancing awareness of electricity costs and climate change and developing a better understanding of individuals’ challenges with changing conservation behaviors based on their demographic and housing characteristics.

Review on Temporal Convolutional Networks for Electricity Theft Detection with Limited Data

Electricity theft detection using artificial intelligence (AI) and machine learning techniques have shown significant promise in recent research. However, practical implementation and widespread adoption of these advanced methods face several persistent challenges, particularly when dealing with limited data. This review delves into the computational complexity, data requirements, overfitting issues, and scalability and generalizability concerns associated with popular techniques such as Temporal Convolutional Networks (TCN), Long Short-Term Memory (LSTM), Deep Convolutional Neural Networks (DCNN), Multi-Layer Perceptron (MLP), Gated Recurrent Unit (GRU), and Artificial Neural Networks (ANN). Computational complexity and resource constraints affect the training times and convergence of TCN, LSTM, and DCNN, while high data needs and parameter tuning hinder MLP and GRU. The ANN-based method utilized by the Electricity Company of Ghana underscores overfitting and data duplication, further exacerbated by limited data availability. Moreover, the scalability and generalizability of TCN, LSTM, and DCNN across different regions and larger datasets are limited, with effectiveness varying based on electricity consumption patterns and theft tactics. Addressing these challenges through optimizing computational efficiency, improving data quality and utilization, and enhancing scalability and generalizability is crucial, especially in data-constrained environments. Continued research and development in these areas will be essential for realizing the full potential of AI-based electricity theft detection systems with limited data.

Information flow dynamics between cryptocurrency returns and electricity consumption: A comparative analysis of Bitcoin and Ethereum

Understanding energy consumption associated with cryptocurrency mining gained increasing attention, with the literature focusing mainly on Bitcoin. This study uses data from the two energy consumption indices, to estimate static and dynamic transfer entropies. The results provide a nuanced understanding of the bidirectional relationships and their implications. The dominant direction of information flow for Bitcoin is from electricity consumption to returns, while for Ethereum, it is from returns to electricity consumption, suggesting that Ethereum's returns significantly impact electricity consumption patterns. Results highlight the need for policies that integrate energy forecasting and environmental sustainability considerations and has significant implications for policymaking.

Monthly electricity consumption data at 1 km × 1 km grid for 280 cities in China from 2012 to 2019

High spatio-temporal resolution estimates of electricity consumption are essential for formulating effective energy transition strategies. However, the data availability is limited by complex spatio-temporal heterogeneity and insufficient multi-source feature fusion. To address these issues, this study introduces an innovative downscaling method that combines multi-source data with machine learning and spatial interpolation techniques. The method’s accuracy showed significant improvements, with determination coefficients (R2) increasing by 30.1% and 33.4% over the baseline model in two evaluation datasets. With this advanced model, we estimated monthly electricity consumption across 1 km x 1 km grid for 280 Chinese cities from 2012 to 2019. Our dataset is highly consistent with officially released electricity consumption of different industries (Pearson correlation coefficients within 0.83 - 0.91). Moreover, our data can reflect the electricity consumption patterns of different urban land uses compared to other datasets. This study bridges a significant gap in fine-grained electricity consumption data, providing a robust foundation for the development of sustainable energy policies.

Solar surge and cost shifts: Heterogenous effects of redistribution in the electricity bills in Japan

This study investigates the impact of daily intermittency in solar energy on retail electricity bills, focusing on the “Duck Curve” and “Peak Shifting” phenomena and their varying effects on different consumer groups. Notably, commercial and industrial users exhibit higher demand around midday, while residential users peak during morning and evening hours. This prompts a crucial question: do peak shifting and redistribution effects differ among consumer groups due to their distinct electricity consumption patterns? Our analysis centers on Japan's power system, which has witnessed significant solar energy penetration, with solar capacity growing from 42 GW in 2016 to 83 GW in 2022. Utilizing monthly electricity consumption data and employing robustness checks through instrumental variable methods, we empirically demonstrate that increased solar penetration leads to higher electricity prices for residential consumers but reduced costs for commercial-industrial users. Additionally, we uncover the mediating role of pumped hydro storage (PHS) stations in stabilizing prices during peak and off-peak periods by managing energy demand variability, thereby mitigating economic impacts across consumer groups. This study highlights the issue of cross-class subsidization, where certain groups bear disproportionately higher electricity costs due to increased renewable energy penetration. It underscores the necessity for carefully crafted policy interventions to uphold market fairness and sustainability alongside large-scale renewable penetration, ensuring a balanced and equitable energy transition.

Rainy and dry seasons impact on electricity demand in Indonesia

Electricity consumption has become an integral part of daily life and is pivotal in supporting various aspects of human life. North Aceh Regency, a tropical region in Indonesia, experiences significant seasonal fluctuations between the rainy and dry seasons. This research aims to investigate and analyze the impact of these seasonal differences on electricity consumption patterns by consumers in the region using the IBM SPSS statistical method. Monthly electricity consumption data from consumers in North Aceh Regency over a specific period were collected and analyzed using IBM SPSS software. Descriptive statistical analysis, hypothesis testing, and regression models were employed to identify significant differences in electricity consumption between the rainy and dry seasons and to understand the factors influencing consumption patterns. The results of the analysis indicate a significant difference in electricity consumption between the rainy and dry seasons in North Aceh Regency. The dry season shows an increase in electricity consumption, possibly related to factors such as the use of air conditioning and additional lighting.

Ownership, Patterns of Use and Electricity Consumption of Domestic Appliances in Urban Households of the West African Monetary and Economic Union: A Case Study of Ouagadougou in Burkina Faso

Ownership, Patterns of Use and Electricity Consumption of Domestic Appliances in Urban Households of the West African Monetary and Economic Union: A Case Study of Ouagadougou in Burkina Faso

An Improved Parallel Clustering Method Based on K-Means for Electricity Consumption Patterns

An Improved Parallel Clustering Method Based on <i>K</i>-Means for Electricity Consumption Patterns

Modern developments and analysis of household electricity utilization by applying smart meter and its findings

The efficient utilization of household electricity is pivotal in the context of rising energy demands and environmental concerns. This study addresses the critical issue of electricity wastage in Chinese households by applying advanced smart meter technology. Aiming to analyze and optimize electricity consumption patterns, the research utilizes the Smart Energy Utilization Model (SEUM) over a period from January 2020 to December 2022, incorporating methodologies such as Artificial Neural Networks (ANN), Support Vector Regression (SVR), Least Squares Support Vector Regression (LS-SVR), and deep learning. The findings reveal that households equipped with smart meters demonstrated a 15 % reduction in overall energy consumption, a 10 % decrease in peak-hour usage, and a notable improvement in energy-saving behaviors among users. Additionally, the integration of smart meters facilitated better load management and contributed to reducing the carbon footprint. The study also found that smart meter data analytics helped in identifying and rectifying inefficient appliances, resulting in a 12 % reduction in energy waste. Moreover, the increased awareness and real-time feedback provided by smart meters led to a 20 % increase in user engagement with energy-saving initiatives. These findings underscore the potential of smart meter technology, enhanced by advanced analytical methods, to enhance energy efficiency and support sustainable development policies.

Modeling Residential Energy Consumption Patterns with Machine Learning Methods Based on a Case Study in Brazil

Developing efficient energy conservation and strategies is relevant in the context of climate change and rising energy demands. The objective of this study is to model and predict the electrical power consumption patterns in Brazilian households, considering the thresholds for energy use. Our methodology utilizes advanced machine learning methods, such as agglomerative hierarchical clustering, k-means clustering, and self-organizing maps, to identify such patterns. Gradient boosting, chosen for its robustness and accuracy, is used as a benchmark to evaluate the performance of these methods. Our methodology reveals consumption patterns from the perspectives of both users and energy providers, assessing the corresponding effectiveness according to stakeholder needs. Consequently, the methodology provides a comprehensive empirical framework that supports strategic decision making in the management of energy consumption. Our findings demonstrate that k-means clustering outperforms other methods, offering a more precise classification of consumption patterns. This finding aids in the development of targeted energy policies and enhances resource management strategies. The present research shows the applicability of advanced analytical methods in specific contexts, showing their potential to shape future energy policies and practices.

Optimizing local electricity markets: A bi-level primal-dual approach for integrating price-based demand response and distribution locational marginal pricing

This paper addresses the conundrum of optimizing electricity consumption patterns in response to fluctuations in demand and price, a task managed by both load aggregators and the distribution system operator (DSO). The conventional approaches in the literature to integrate demand response (DR) into optimal power flow (OPF) problems typically overlook the price responsiveness of consumers or simplify power flow equations to account for price-elastic demand.In this paper, we strive to close this gap by introducing a bi-level primal-dual optimization framework that incorporates aggregators' objectives into the market-clearing process while preserving the precision of the OPF equations. At the upper level, the model seeks to minimize both the total payment and peak load. The lower level, structured as a second-order conic (SOC) problem, aims to reduce overall generation costs subject to constraints of the second-order conic (SOC) branch flow model (BFM). The two levels interact through the optimal demand response and distribution locational marginal prices (DLMPs). The principles of convex duality principles together with the strong duality constraint are leveraged to transform the market-clearing problem into a single primal-dual problem. We also circumvent the non-linearity that stems from the DR payment term by incorporating discretizing loads and the big-M method, thus converting the problem into a mixed-integer SOC (MI-SOC) formulation. The merits of the proposed MI-SOC framework are validated through case studies conducted on the IEEE 33-bus test system, showcasing its potential to enforce price-elasticity demand response in distribution system's electricity markets.

Investigating Electricity Usage Profile for Residential Consumers in India

Electricity has become one of the essential needs in modern society. The demand and necessity for electricity have increased with population, trade, and industry, which has resulted in increased stress on the grid. As the development of an electricity storage system is costly, utilities are working on customer segmentation to classify the consumers according to their usage patterns to understand their demand and further develop resources accordingly. In this work, the K-Means clustering algorithm has been applied to a two-year monthly consumption data set (January 2019 to December 2020) of 100 residential consumers from Kutheda village Hamirpur (Himachal Pradesh, India) to visualize the diverse consumption behaviour. It resulted in four different clusters of consumers. It also showed that there is a group having a large number of consumers whose consumption is low and consumption pattern is very less flexible in different seasons. Another group of consumers with high consumption also shows high flexibility in consumption patterns, but their number is less. Also, the winter season shows the highest consumption of electricity and the monsoon season shows the lowest consumption of electricity in this particular region. This analysis will certainly help the electricity provider to make production planning for a different group of consumers in a specific season based on electricity consumption patterns.

Anomaly Detection in Smart Electric Meters for Detecting Faults and Misuse of Electric Energy Consumption

The emergence of Smart Electric Meters (SEMs) has revolutionized energy management, providing real-time data collection and monitoring capabilities. However, ensuring the accuracy and security of this data presents challenges. Anomaly detection in electric energy consumption patterns is crucial for identifying issues like technical faults, erroneous billing, and misuse of electricity. Our project offers an Anomaly Detection System that leverages data analytics and machine learning to scrutinize SEM data. By analyzing historical patterns, the system distinguishes anomalies from routine fluctuations, triggering alerts when irregularities are detected. This system enhances the reliability and security of electric energy consumption data, fostering a more efficient and sustainable energy sector. Key Words: Anomaly Detection, Smart electric Meters, Fault Detection, Energy Misuse.

Improving Electricity Theft Detection Using Electricity Information Collection System and Customers’ Consumption Patterns

Electricity theft detection (ETD) techniques employed to identify fraudulent consumers often fail to accurately pinpoint electricity thieves in real time. The patterns associated with electricity use are leveraged to identify anomalies indicative of electricity theft. However, challenges in the benchmark ETD include overfitting and a high incidence of false positives (FPs) resulting from incorrect usage patterns formed by considering only electricity consumption patterns without accounting for external factors that contribute to variations in normal consumption patterns. Further investigation is required to precisely detect instances of electricity theft, thereby minimizing nontechnical losses and forecasting future electricity demand to maintain a stable supply. This study employs a master energy meter located on the transformer side to monitor the amount of energy distributed to the region. Zones with a high likelihood of energy theft are detected by comparing the sum of readings from all the smart meters with the readings from the master energy meter installed on the HV of the substation transformer within the same electric feeder. Ensemble XGBoost machine-learning algorithm and K-Means algorithm are used for the classification of malicious and nonmalicious samples and grouping similar types of consumers together, respectively. This makes the proposed model resistant to false-positive rates caused by changes in usage patterns that aren’t done on purpose. Furthermore, energy thieves are identified by detecting anomalies in consumption behavior while maintaining constant internal and external environmental variables. This novel model proposed here mitigates the FP rate found in the present research of electricity usage data. Our approach outperforms support vector machines, convolution neural network, and logistic regression in simulations. Precision, F1-score, recall, Matthews Correlation Coefficient, Receiver Operating Characteristics (ROC)-Area Under The Curve (AUC), and Precision Recal (PR)-Area Under The Curve (AUC) validate our model. The simulation results show that the proposed K-Means-LSTM-XGBoost model improved the classifier’s F1-score, precision, and recall to 93.75%, 95.16%, and 92.38%, respectively. Our model classifies huge time series data with high precision and can be utilized by the utility for real time electricity theft detection.

Quantum support vector machine for forecasting house energy consumption: a comparative study with deep learning models

The Smart Grid operates autonomously, facilitating the smooth integration of diverse power generation sources into the grid, thereby ensuring a continuous, reliable, and high-quality supply of electricity to end users. One key focus within the realm of smart grid applications is the Home Energy Management System (HEMS), which holds significant importance given the fluctuating availability of generation and the dynamic nature of loading conditions. This paper presents an overview of HEMS and the methodologies utilized for load forecasting. It introduces a novel approach employing Quantum Support Vector Machine (QSVM) for predicting periodic power consumption, leveraging the AMPD2 dataset. In the establishment of a microgrid, various factors such as energy consumption patterns of household appliances, solar irradiance, and overall load are taken into account in dataset creation. In the realm of load forecasting in Home Energy Management Systems (HEMS), the Quantum Support Vector Machine (QSVM) stands out from other methods due to its unique approach and capabilities. Unlike traditional forecasting methods, QSVM leverages quantum computing principles to handle complex and nonlinear electricity consumption patterns. QSVM demonstrates superior accuracy by effectively capturing intricate relationships within the data, leading to more precise predictions. Its ability to adapt to diverse datasets and produce significantly low error values, such as RMSE and MAE, showcases its efficiency in forecasting electricity load consumption in smart grids. Moreover, the QSVM model’s exceptional flexibility and performance, as evidenced by achieving an accuracy of 97.3% on challenging datasets like AMpds2, highlight its distinctive edge over conventional forecasting techniques, making it a promising solution for enhancing forecasting accuracy in HEMS.The article provides a brief summary of HEMS and load forecasting techniques, demonstrating and comparing them with deep learning models to showcase the efficacy of the proposed algorithms.