Individual Electricity Consumption Research Articles

Combining an improved Apriori algorithm and Social Network analysis to identify the unique sequential features of individual household electricity consumption behaviours

ABSTRACT The household’s electricity consumption behaviour follows a unique sequential pattern and can be identified by analyzing the electricity consumption data with fine granularity in a smart home context. This particular sequence is concretely embodied in a series of electrical activities with temporal association relationships, thus forming a unique household electrical appliance activity-based chain (EAAC). In this study, we propose a method that combines an improved Apriori algorithm and Social Network to construct a household EAACs. First, we improved the Apriori algorithm (Apriori (1,1)) by combining the temporal and transactional sequences and used it to mine the time-series activity associations among different household appliances. After that, we used the Sliding Window concept to splice the time-series associations and obtain the unique EAACs for each household. Next, we visualized the EAACs using the Social Network analysis to reflect the unique sequential features of household electricity consumption behaviours. Finally, the model was validated by analyzing two families’ actual household electricity consumption data, and future research directions were given.

Enhancing Energy Efficiency in Retail within Smart Cities through Demand-Side Management Models

The energy discourse is multifaceted, encompassing energy creation, storage, and conservation. Beyond the imperative of conserving energy consumption, effective energy management is a critical aspect of achieving overall energy efficiency. Despite being traditionally regarded as low electricity consumers, retailers play a pivotal role in economic activity. While categorized as non-productive energy users, the retail industry operates numerous establishments, facing substantial energy costs that make energy management integral to its operations. Historically, smaller retail stores have lacked awareness of energy saving. However, by connecting these stores, even modest reductions in individual electricity consumption can yield significant overall energy savings. This study aims to investigate the feasibility of implementing the demand-side management (DSM) aggregator model in the retail industry. Through surveys on awareness of energy saving and the application of deep learning techniques to analyze the effectiveness of the Aggregator model, the results reveal that the mean squared prediction error (MSPE) of this research is below 2.05%. This indicates substantial accuracy and offers meaningful reference value for Energy Service Company (ESCO) providers. The findings contribute practical recommendations for the sustainable and competitive implementation of DSM energy management practices in smart cities.

Efficient Demand Side Management Using a Novel Decentralized Building Automation Algorithm

Given its adaptable and efficient energy consuming devices during peak hours, the residential building sector is urged to take part in demand response (DR) initiatives with the use of a building energy management system (BMS). The residents of buildings with BMS enjoy secure, pleasant, and fully managed lifestyles. Although the BMS helps the building consume less energy and encourages occupant engagement in energy-saving initiatives, unwelcome interruptions and harsh instructions from the system are inconvenient for the inhabitants, which further discourages their participation in DR initiatives. Building automation control is a crucial factor for improving buildings’ energy efficiency and management, as well as improving the electricity grid’s reliability indices. Smart houses that use the right sizing procedure and energy-management techniques can help lower the demand on the entire grid and potentially sell clean energy to the utility. Recently, smart houses have been presented as an alternative to traditional power-system issues including thermal plant emissions and the risk of blackouts brought on by malfunctioning bulk plants or transmission lines. This paper describes the necessary technology requirements and presents the methodology and the decentralized building automation novel algorithm for efficient demand side management in a building management system. Human comfort aspects including thermal comfort and visual comfort were taken into consideration when selecting heating and lighting controls. The suggested BMS relies primarily on a load-shifting technique, which moves controllable loads to low-cost periods to avoid high loading during peak hours. The model aims to minimize the individual household electricity consumption cost while considering customers’ comfort and lifestyle. All these are applied in an experimental university microgrid, and the results are presented in terms of energy saving in kWh, money in €, and working hours. The results demonstrated that the proposed approach might successfully lower energy use during the DR period and enhance occupant comfort.

The effect of customized information feedback on individual electricity saving behavior: Evidence from a field experiment in China

Electricity savings from information interventions will play a key role in meeting future carbon reductions. Surprisingly, this subject is still poorly studied and understood in China, where residential electricity consumption is second only to manufacturing in terms of carbon emissions. Despite some studies evaluating the impact of information feedback strategies on individual electricity consumption, these studies ignore individual diversity. This study conducted the field experiment in Nanjing, China, with eight treatment and control groups. The aim was to find out whether: i) general and customized information feedback, ii) single and mixed information strategies, and iii) online and offline information delivery methods have an impact on individual electricity savings. Results demonstrated that customized information feedback was the most effective strategy for reducing electricity consumption in single strategies. Energy-saving knowledge, social comparisons, and customized information feedback, except for environmental education-based information, significantly enhanced individual electricity saving behavior. Mixed strategies are superior to single strategies for influencing individual electricity saving behavior. Notably, customized environmental education-based information had a significant electricity saving effect. Furthermore, the offline information delivery method has a stronger effect on reducing individual electricity consumption. These findings can provide a reference for policymakers to implement effective electricity saving policies.

Individual household demand response potential evaluation and identification based on machine learning algorithms

Modern power systems are facing an increase in the penetration of renewables to achieve carbon neutrality targets in the future. Individual household demand response (DR) is a potential resource to address the fluctuation caused by renewable energy generation. However, the DR potential of residential customers is more challenging to evaluate and identify than the DR at the aggregated level due to the uncertainty in individual customers' electricity consumption behavior. In this study, to address this issue, a DR potential evaluation and identification framework based on machine learning algorithms is proposed. Firstly, the customer's DR capacity under dynamic time-of-use electricity tariffs is carefully calculated. Then several novel indicators are proposed to depict customer's electricity consumption characteristics. Next, some prevalent machine learning methods are leveraged to learn the mapping between the developed indicators and DR capacity. Besides, to further improve the classification accuracy and analyze the performance of the unlabeled samples, the self-training method is applied by using customers' data who are issued normal flat electricity prices. Finally, the proposed framework was applied to a publicly available dataset and the results indicated that the proposed approach reached prospective classification accuracy and proved the validity of the proposed indicators and identification framework.

An optimal charging scheduling model and algorithm for electric buses

Electrification poses a promising low-carbon or even zero-carbon transportation solution, serving as a strategic approach to reducing carbon emissions and promoting carbon neutrality in the transportation sector. Along the transportation electrification pathway, the goal of carbon neutrality can be further accelerated with an increasing amount of electricity being generated from renewable energies. The past decade observed the rapid development of battery technologies and deployment of electricity infrastructure worldwide, fostering transportation electrification to expand from railways to light and then heavy vehicles on roadways. In China, a massive number of electric buses have been employed and operated in dozens of metropolises. An important daily operations issue with these urban electric buses is how to coordinate their charging activities in a cost-effective manner, considering various physical, financial, institutional, and managerial constraints.This paper addresses a general charging scheduling problem for an electric bus fleet operated across multiple bus lines and charging depots and terminals, aiming at finding an optimal set of charging location and time decisions given the available charging windows. The charging windows for each bus are predetermined in terms of its layovers at depots and terminals and each of them is discretized into a number of charging slots with the same time duration. A mixed linear integer programming model with binary charging slot choice and continuous state-of-charge (SOC) variables is constructed for minimizing the total charging cost of the bus fleet subject to individual electricity consumption rates, electricity charging rates, time-based charging windows, battery SOC bounds, time-of-use (TOU) charging tariffs, and station-specific electricity load capacities. A Lagrangian relaxation framework is employed to decouple the joint charging schedule of a bus fleet into a number of independent single-bus charging schedules, which can be efficiently addressed by a bi-criterion dynamic programming algorithm. A real-world regional electric bus fleet of 122 buses in Shanghai, China is selected for validating the effectiveness and practicability of the proposed charging scheduling model and algorithm. The optimization results numerically reveal the impacts of TOU tariffs, station load capacities, charging infrastructure configurations, and battery capacities on the bus system performance as well as individual recharging behaviors, and justify the superior solution efficiency of our algorithm against a state-of-the-art commercial solver.

Benchmark of Electricity Consumption Forecasting Methodologies Applied to Industrial Kitchens

Even though Industrial Kitchens (IKs) are among the highest energy intensity spaces, very little work has been done to forecast their consumption. This work explores the possibility of increasing the accuracy of the consumption forecast in an IK by forecasting disaggregated appliance consumption and comparing these results with the forecast of the total consumption of these appliances (Virtual Aggregate—VA). To do so, three different methods are used: the statistical method (Prophet), classic Machine Learning (ML) method such as random forest (RF), and deep learning (DL) method, namely long short-term memory (LSTM). This work uses individual appliance electricity consumption data collected from a Portuguese restaurant over a period of four consecutive weeks. The obtained results suggest that Prophet and RF are the more viable options. The former achieved the best performance in aggregated data, whereas the latter showed better forecasting results for most of the individual loads. Regarding the performance of the VA against the sum of individual appliance forecasts, all models perform better in the former. However, the very small difference across the results shows that this is a viable alternative to forecast aggregated consumption when only individual appliance consumption data are available.

APPLICATION OF SIMULATION RESEARCH TO ANALYSE THE PRODUCTION PROCESS IN TERMS OF SUSTAINABLE DEVELOPMENT

Sustainable development is an very important idea nowadays and it influences on many factors. It is very important to focus on the goals of sustainable development and implement them both in industry and in everyday life. The aim of the article is to analyse the impact of implementing an automatic conveyor belt transport system between the stands of an exemplary assembly line on sustainable development in economic and environmental terms. The analyzed production process consists of one production line with six assembly stations. The efficiency of individual design solutions and electricity consumption were adopted as the evaluation criteria. To compare the two processes, a simulation analysis was performed in the Plant Simulation program. First chapter is the introduction to the article. The second chapter describes the current applications of simulation tests. The third chapter describes the production system that is improved by adding conveyors. The next chapter compares the processes with and without the use of conveyors and presents how much energy must be used additionally by implementing conveyor belts, but also what energy savings can be obtained by installing additional stop sensors. The fifth chapter presents the conclusions: the conducted research allowed concluding that the implementation of conveyor belts affects a higher number of finished products at the same time as the transport of components is manual. However, the best solution is to use conveyors with stop sensors, and the power consumption is then low and more profitable for the enterprise.

Synthetic demand data generation for individual electricity consumers : Generative Adversarial Networks (GANs)

Load modeling is one of the crucial tasks for improving smart grids’ energy efficiency. Among many alternatives, machine learning-based load models have become popular in applications and have shown outstanding performance in recent years. The performance of these models highly relies on data quality and quantity available for training. However, gathering a sufficient amount of high-quality data is time-consuming and extremely expensive. In the last decade, Generative Adversarial Networks (GANs) have demonstrated their potential to solve the data shortage problem by generating synthetic data by learning from recorded/empirical data. Educated synthetic datasets can reduce prediction error of electricity consumption when combined with empirical data. Further, they can be used to enhance risk management calculations. Therefore, we propose RCGAN, TimeGAN, CWGAN, and RCWGAN which take individual electricity consumption data as input to provide synthetic data in this study. Our work focuses on one dimensional times series, and numerical experiments on an empirical dataset show that GANs are indeed able to generate synthetic data with realistic appearance.

Electricity consumption in the digital era: Micro evidence from Chinese households

This paper studies the impact of internet access on household electricity consumption, using three waves (six years) of China Family Panel Study survey data. We separately explore short-, medium-, and long-term effects. The panel fixed regression results indicate that after gaining access to the internet, individual electricity consumption declines about 1.2% as the short-run effect (around two years). Difference-in-differences (DID) estimation shows that after using the internet for four years, individual electricity demand declines on average a total of 12.5% as the medium-term effect. For all internet users during the entire survey period, propensity score matching (PSM) shows that electricity consumption decreases 16.3% on average compared to nonusers, which can be seen as the long-term effect. Substitution and optimization of household appliances and individual pro-environmental behaviors and green lifestyles promoted by digitalization may explain the results. Our findings suggest that policies to enhance access to high-speed, affordable, and reliable internet services contribute to reducing household electricity consumption, thereby helping cut CO2 (carbon dioxide) emissions from fossil fuel-based power plants while also alleviating problems of insufficient electricity production capacity.

Forecasting of individual electricity consumption using Optimized Gradient Boosting Regression with Modified Particle Swarm Optimization

The task of forecasting consumers’ energy consumption is currently a trend in energy supply companies. An accurate prediction of energy consumption is a powerful tool to check for inconsistencies between what is recorded and the actual amount consumed. In practice, Brazilian energy companies verify inconsistencies in the manual reading of consumption, using a consumption range based on the predicted consumption. This consumption forecast is currently realized by the average of previous consumptions and, therefore, can be improved by the use of machine learning techniques. For this purpose, an Optimized Gradient Boosting Regressor (OGBR) was proposed, which has been optimized by a modified version of the Particle Swarm Optimization (PSO) for fast parameter optimization. The OGBR prediction results on a dataset of over 2 million consumers were compared with its unmodified version and with the Seasonal and Trend decomposition using Loess (STL). In addition, the forecast stability of the OGBR over 12 months was evaluated. Therefore, the energy consumption forecasting performance was improved by using the OGBR and this performance was better than its unmodified version, in all validation metrics, and better than STL, in most classes of consumption.

Electrical Energy Prediction in Residential Buildings for Short-Term Horizons Using Hybrid Deep Learning Strategy

Smart grid technology based on renewable energy and energy storage systems are attracting considerable attention towards energy crises. Accurate and reliable model for electricity prediction is considered a key factor for a suitable energy management policy. Currently, electricity consumption is rapidly increasing due to the rise in human population and technology development. Therefore, in this study, we established a two-step methodology for residential building load prediction, which comprises two stages: in the first stage, the raw data of electricity consumption are refined for effective training; and the second step includes a hybrid model with the integration of convolutional neural network (CNN) and multilayer bidirectional gated recurrent unit (MB-GRU). The CNN layers are incorporated into the model as a feature extractor, while MB-GRU learns the sequences between electricity consumption data. The proposed model is evaluated using the root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) metrics. Finally, our model is assessed over benchmark datasets that exhibited an extensive drop in the error rate in comparison to other techniques. The results indicated that the proposed model reduced errors over the individual household electricity consumption prediction (IHEPC) dataset (i.e., RMSE (5%), MSE (4%), and MAE (4%)), and for the appliances load prediction (AEP) dataset (i.e., RMSE (2%), and MAE (1%)).

Appliance-specific feedback and social comparisons: Evidence from a field experiment on energy conservation

The provision of feedback about individual electricity consumption is a widely used approach to promote pro-environmental behavior. This form of feedback typically invokes social comparisons by informing households about their aggregate electricity consumption relative to others. While previous research has shown that aggregate consumption feedback translates into significant energy savings, the potential for further reductions may remain untapped because households lack knowledge about their appliance energy consumption patterns. In this paper, we present evidence from a field experiment, where we provide residents with feedback about their electricity consumption, specific to a high-energy use appliance (i.e. air-conditioner). We provide the relevant social norm information by varying the reference group of each resident. We find that our appliance-specific feedback is a powerful tool to curb electricity consumption. Residents significantly reduce their average air-conditioning usage by 17% in our treatment groups. Notwithstanding, our effects are not driven by comparative feedback with respect to different reference groups. We interpret this as encouraging evidence to promote the use of appliance-specific feedback to realize energy savings.

Appliance Specific Feedback and Social Comparisons: Evidence From a Field Experiment on Electricity Saving

The provision of feedback about individual electricity consumption is a widely used approach to promote pro-environmental behavior. This form of feedback typically invokes social comparisons by informing households about their aggregate electricity consumption relative to others. While previous research has shown that aggregate consumption feedback translates into significant energy savings, the potential for further reductions may remain untapped because households lack knowledge about their appliance energy consumption patterns. In this paper, we present evidence from a field experiment, where we provide residents with feedback about their electricity consumption, specific to a high-energy use appliance (i.e. air-conditioner). We provide the relevant social norm information by varying the reference group of each resident. We find that our appliance-specific feedback is a powerful tool to curb electricity consumption. Residents significantly reduce their average air-conditioning usage by 17\% in our treatment groups. Notwithstanding, our effects are not driven by comparative feedback with respect to different reference groups. We interpret this as encouraging evidence to promote the use of appliance-specific feedback to realize energy savings.

Bayesian Deep Learning-Based Probabilistic Load Forecasting in Smart Grids

The extensive deployment of smart meters in millions of households provides a huge amount of individual electricity consumption data for demand side analysis at a fine granularity. Different from traditional aggregated system-level data, smart meter data is more irregular and unpredictable. As a result, probabilistic load forecasting (PLF), which can provide a better understanding of the uncertainty and volatility in future demand, is critical to constructing energy-efficient and reliable smart grids. In this article, a recently developed technique called Bayesian deep learning is employed to solve this challenging problem. In particular, a novel multitask PLF framework based on Bayesian deep learning is proposed to quantify the shared uncertainties across distinct customer groups while accounting for their differences. Further, a clustering-based pooling method is designed to increase the data diversity and volume for the framework. This not only addresses the problem of overfitting but also improves the predictive performance. Numerical results are presented which demonstrate that the proposed framework provides superior probabilistic forecasting accuracy over conventional methods.

Effect of energy information provision on occupant’s behavior and energy consumption in public spaces

‘Nudge’, which is a framework of altering people’s behaviour in a predictable way without large penalty or economic incentives, is applied to energy saving measures of buildings in several papers. However, most of them focus on energy saving in a private space such as home, and little research has been done for energy saving in a public space. In this research, field experiments were conducted with the aim of energy saving in a public space by offering information. Focusing on individual behavior in a public space, we provided information directly to an individual, not to a public. By using power taps and thermal sensors, the individual equipment electricity consumption during absence, which is considered as the amount of energy wasted, is calculated. The subjects were divided into three groups. Through the information provision, some people changed their behavior and reduced energy consumption by approximately 70%. Furthermore, it was founded that those who originally consumed much energy even when absent might tend not to change behavior by receiving information. The results from this experiment will provide fresh insight into information provision such as data visualization for energy saving of a public space and be useful for life management of occupants.

The effect of group size on energy consumption by communal electricity users

A communal electricity metering, where several consumers split their bill equally without being able to distinguish between their individual electricity consumption (EC), may create a social dilemma. Using this concept as a frame of reference, we hypothesized that increasing the group size of the consumers would increase EC. We increased the perceived group size of communal electricity users and monitored EC before, during and after the intervention. We also studied interpersonal trust, collectivism, self- and collective efficacy, ECrelated attitudes, pro-environmental self-identity and self-reported EC. We found that during the intervention phase, mean EC increased by 28.9% - an increase that disappeared right after the intervention was terminated. The only significant predictors of EC were efficacy and trust. Selfreported EC was not correlated to actual EC. The implications for conservation of electricity in a communal metering setting and the caution needed when using self-reports of environmental behavior are discussed.

Self-consumption with PV + Battery systems: A market diffusion model considering individual consumer behaviour and preferences

The market diffusion of self-consumption technologies, such as photovoltaic and battery systems, is an important aspect in the transition towards a sustainable energy system. Most studies, which address this issue, focus solely on economic aspects and neglect the influence of individual electricity consumption behaviour and consumer preferences on the individual benefit of a self-consumption system. Yet, preferences and behaviour have a significant impact in the market uptake of new technologies, as can be seen in the current sales figures of batteries for the purpose of self-consumption enhancement. The technology is purchased, even though it is still far from economically viable. In this study, a market diffusion model is proposed that is based on 415 individual electricity load profiles, which define the homeowners’ consumption behaviour. Additionally, the results of a market survey are included to explicitly model different user groups and map their varying willingness to pay. The results show that homeowners who are likely to adopt a self-consumption technology are on average characterised by higher annual electricity consumption. The consumption behaviour, and therefore the load profiles are heterogeneous within each user group and therefore, also the individual utility of a battery for self-consumption enhancement differs significantly. The results show that the suggested modelling approach is able to explain the past development of battery installations in private households in Germany. Up until 2030, the model simulations suggest a moderate development of battery enhanced self-consumption, resulting in a battery of 2GWh in private households in 2030.

The effect of individual and communal electricity generation, consumption and storage on urban Community Renewable Energy Networks (CREN): an Australian case study

Community Renewable Energy Networks (CREN), in which households and businesses in a local community share energy resources, are an attractive platform for optimising renewable energy use and reducing dependence on the wider electricity grid. However, the optimal use local power generation and energy storage is critically dependent on the load characteristics and location of the community. In this work we compare the simulated energy generation, consumption and independence of two model developments in Melbourne and Sydney. The analysis looked at 6 basic scenarios, from the default grid dependence through to a community approach with both individual and communal PV generation and battery energy storage. The results showed that a combination of household and community owned PV and storage can reduce grid electricity import by up to 93% for Melbourne and 96% for Sydney, but that neither development could independently meet all its power requirements without shortfall. The shortfall arises during the winter months when PV generation is at its lowest, and no practical amount of energy storage can mitigate this. Interestingly, Melbourne, which is at a higher latitude than Sydney and receives less solar insolation, achieves more months of grid independence than Sydney

Forecasting Uncertainty in Electricity Smart Meter Data by Boosting Additive Quantile Regression

Smart electricity meters are currently deployed in millions of households to collect detailed individual electricity consumption data. Compared with traditional electricity data based on aggregated consumption, smart meter data are much more volatile and less predictable. There is a need within the energy industry for probabilistic forecasts of household electricity consumption to quantify the uncertainty of future electricity demand in order to undertake appropriate planning of generation and distribution. We propose to estimate an additive quantile regression model for a set of quantiles of the future distribution using a boosting procedure. By doing so, we can benefit from flexible and interpretable models, which include an automatic variable selection. We compare our approach with three benchmark methods on both aggregated and disaggregated scales using a smart meter data set collected from 3639 households in Ireland at 30-min intervals over a period of 1.5 years. The empirical results demonstrate that our approach based on quantile regression provides better forecast accuracy for disaggregated demand, while the traditional approach based on a normality assumption (possibly after an appropriate Box-Cox transformation) is a better approximation for aggregated demand. These results are particularly useful since more energy data will become available at the disaggregated level in the future.