Search

Over time, several relationships have been defined between electricity consumption and a region's social and economic variables, with income as the main factor. This paper uses multiple correspondence analysis to identify the categories of dwellings and, from a graphical point of view (positioning maps), the effects of the different characteristics that influence the electricity consumption of households in rural areas of Cundinamarca, Colombia. In this analysis, the consumption of residential users responded mainly to what they can afford or acquire based on their income, consumption habits, and the characteristics of the technology. Furthermore, this study highlights the implications of these findings for policymakers and energy providers, providing valuable insights for developing targeted strategies to promote energy efficiency and sustainability in rural areas. This research contributes to a deeper understanding of the dynamics of electricity consumption and highlights the importance of tailoring energy-related interventions to the specific socio-economic context of rural communities, in this case in Cundinamarca. [ABSTRACT FROM AUTHOR]

Smart home technology (SHT) is increasingly entering homes to provide services such as energy management, security, comfort, and convenience. However, research shows that adoption varies across social groups and that SHT might affect energy demand. Denmark is considered a frontrunner in the uptake of SHT and offers a unique opportunity to combine administrative household information with energy consumption data and survey responses on SHT uptake. This paper studies a representative sample of 1,468 Danish households to investigate SHT diffusion, social differences in SHT adoption, and correlations between SHT and energy consumption, divided into appliance use and heating. The results indicate that entertainment and home security are the most popular SHT services in Denmark and that SHT is more widespread among younger households, especially for entertainment and robotic help. In contrast, smart heating systems are more widespread among older households. Living in a detached house seems to increase the likelihood of having SHT, while the highest income group appears more likely to have security systems, and technical education seems associated with the adoption of SHT for heating management. Finally, smart security systems were associated with higher electricity consumption, and SHT for electricity management was associated with higher heating consumption and to a lesser extent higher electricity consumption, but there was no significant correlation between having smart heating control and heating consumption. [ABSTRACT FROM AUTHOR]

Global energy consumption is growing rapidly, with the frequency and intensity of extreme events constantly increasing, posing a long-term threat to power supply and consumption. Therefore, analyzing the spatiotemporal characteristics of electricity consumption and quantitatively assessing the impact of extreme events on electricity consumption are of great significance. Based on fine-grained electricity consumption data from Europe for the years 2019–2022, this paper employs a data mining perspective and four methods including Z-score, Isolation Forest, Local Outlier Factor, and Autoencoder to detect abnormal electricity consumption during extreme events. Additionally, it combines indicators such as elastic loss, vulnerability, and duration to measure the impact of extreme events on electricity consumption. It is found that low temperatures could lead to abrupt changes in electricity consumption, with Northern Europe being more significantly affected by low temperatures. The COVID-19 pandemic had the most significant impact on electricity consumption in Europe, with the middle part of Europe being the hardest hit during the first wave of the pandemic. Electricity anomalies during the pandemic period were related to national pandemic control policies and exhibited some lag. High temperatures persisted for a longer duration in the middle part of Europe. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to examine the impact of remittance inflows (remittances) on electricity consumption and electric power losses in Jamaica. Design/methodology/approach: The authors use annual data from 1976 to 2014 and apply vector error correction modelling, Granger causality testing and impulse response analysis. Findings: First, the authors find that there is co-integration between remittances and the energy variables, namely electricity consumption and electric power losses. Second, short-run Granger causality exists between the energy variables and remittances. This causality is bidirectional between the energy variables and positive changes in remittances, but it is unidirectional running from the energy variables to negative movements in remittances. Third, the authors find that in the long-run remittances have a negative relationship with electric power losses and a positive relationship with the consumption of electricity. Practical implications: Findings from this paper will help to elucidate the relationship between electricity consumption, and electric power losses, and remittances. Social implications: The problem of electric power losses is acute in Jamaica and it is mostly due to theft. At the same time, Jamaica receives significant remittances. Social policy could have a role to encourage the use of remittances to help stem the theft of electricity. Originality/value: This is the first study that examines the relationships between remittances, electricity consumption and electric power losses. [ABSTRACT FROM AUTHOR]

Night‐time light (NTL) satellite imagery can provide unique insights into the energy sector. Nevertheless, there are limited studies that have systematically reviewed the literature on the relationship between electricity consumption and NTL. Therefore, this paper aims to provide a systematic review of studies that have explored this relationship. The review identified over 200 regression models estimating electricity consumption using NTL satellite images. The key finding of the review was that there was a large variability in regression performance for model prediction of electricity consumption from NTL imagery, indicating a need for further work to refine the techniques and approaches in this emerging field of remote sensing research. The level of spatial aggregation had an important influence on model performance with larger geographical areas, such as countries or states, providing better estimations. [ABSTRACT FROM AUTHOR]

Over the past years, the economies of the Gulf Cooperation Countries (GCC) countries, which hold a large of the world in oil and gas exports, have suffered from dramatic declines in oil prices. This has put pressure on their policymakers to seek relief from their heavy dependence on natural resources and diversify their exports. At the same time, the GCC countries have high electricity consumption due to their severe climatic conditions. This has prompted their policymakers to consider the inevitable shift to environmentally friendly resources for electricity generation. Foreign direct investment, facilitated by the financial systems of these countries, may play an important role in achieving the above objectives. Therefore, the objectives of our paper are to investigate the relationship between foreign direct investment, electricity consumption, and financial development in GCC countries using a novel GMM-Panel VAR approach. Data are observed from 1990 to 2019. We find bidirectional causality between foreign direct investment and financial development and two unidirectional paths: one from electricity consumption to foreign direct investment and from financial development to electricity consumption. In addition, we observe negative and significant responses of financial development to shocks in electricity consumption. Our results can have a double interpretation. First, they provide an overview of the interactions between the variables studied, whose evolution may be prognosticated with the analysis of shocks resulting from the methodology adopted in our paper. This is serviceable given the recurrent turbulence in the international financial markets and the incessant perturbations in the prices of energy commodities, visually examined especially in recent years. Second, our empirical findings are useful for policymakers willing to have earlier diagnoses for policies strengthening renewable energy use in these countries. Our results can be seen on the side of this objective. The quite developed financial system in these countries may play, indeed, an important role in encouraging the FDI installation in the field of renewable energy. [ABSTRACT FROM AUTHOR]

This paper uses data from the 2015 Residential Energy Consumption Survey to explore the extent to which renters' electricity use in the United States exceeds that of otherwise similar non-renters. Renting households are found to use approximately 9% more electricity than non-renters when controlling for location, socioeconomic, and many appliance-quantity controls. There are multiple factors that explain this extra electricity use, including inferior energy efficiency of appliances, behavioral factors, differences in bill payment responsibilities, and additional reliance by renters on electric space and water heaters. The paper finds that none of these factors are dominant. The phenomenon of renters' (conditionally) higher electricity use is thus best understood as one that emerges from multiple sources. [ABSTRACT FROM AUTHOR]

In this paper, a vector data net solver is proposed, which can reduce bivariate discrete-time dynamic programming (DP) computation time by 98.0% without losing accuracy. Therefore, for the first time, bivariate discrete-time DP can operate under model predictive control rolling optimization to calculate future optimum vehicle velocity in real time considering future road altitude and instant traffic information. Simulation results indicate that with the solution presented in this paper, front vehicles and the proper windows to pass through front intersections can be constantly considered. Meanwhile, the calculated optimum vehicle velocity almost remains the same as the global optimum solutions. Simulation results are validated by real-car tests, and the test new energy vehicle (NEV) electricity consumption is reduced by up to 48.6%. A comparison experiment is performed between the solution presented in this paper and commonly used adaptive dynamic programming (ADP), and the results indicate that the former has better performance and stability. This paper describes a novel solution for online optimum velocity calculation under vehicle to everything (V2X) environment and can be used by all smart NEVs with autonomous driving or active cruise control functions for lower electricity consumption and better riding comfort. [ABSTRACT FROM AUTHOR]

Using energy more efficiently is one of the easiest ways to save money, reduce greenhouse gas emissions, and meet growing energy demands. Electricity consumption control is an emergent topic worldwide. The passive house idea is not new, but it is still actual and is discussed by researchers. This paper brings to the reader's attention the combined use of fuzzy and fractional control methods to increase the performance of electricity consumption control, taking into account the current challenges in the energy field, together with a method for the automatic definition of fuzzy rules. In comparison with the no-control case, a 20% reduction in consumption is achieved with the present proposal. In the case of another control method, a 15% reduction was possible using Shakeri's team's method. The simulation of the proposed passive house control proves that it could ensure efficient electricity consumption that can be translated into electricity cost savings between 10 and 50 percent. [ABSTRACT FROM AUTHOR]

Since the government implemented the supply-side structural reform, the growth of electricity consumption in energy-intensive manufacturing industries has been contained in an all-round way, which poses greater challenges to overcapacity in the power sector. It is still a mystery that how to restrain the electricity consumption of energy-intensive manufacturing industry affects the installed capacity of power generation. Thereupon, this paper empirically studies the relationship between electricity consumption of the six energy-intensive manufacturing subsectors and provincial power generation capacity. The empirical results with line loss rate as instrumental variables indicate that the electricity consumption of the six energy-intensive manufacturing subsectors will increase or decrease the installed capacity of power generation by a one-to-one elastic coefficient. In terms of manufacturing subsectors, the power sector's own electricity consumption has the highest capacity enhancement effect, followed by non-metallic minerals and chemical raw materials manufacturing subsectors. The resolution of overcapacity for power generation is fundamentally to reduce the electricity consumption intensity of the six high-energy-consuming manufacturing subsectors. [ABSTRACT FROM AUTHOR]

Electricity Consumption is one among widely studied section of computer architecture for more than decades. Electricity Adoption is one of the parameter in Machine Learning. It is one of the emerging field in the research. It keeps an eye on high accuracy without any kind of computation constraint. The paper has the objectivity to analyze Machine Learning algorithms effectiveness, after being applied to the electricity consumption prediction. Load management and demand response, high dimensional data sets are much effective variable selection, accurate prediction for electricity market pricing. It retains economic mechanisms to the largest. Our goal is about important guidelines offering to the Machine Learning community and provide basic knowledge of building specific electricity consumption estimation methods for machine learning algorithms. This Paper reviews about the Conventional Machine Learning Models as well as the recent models, allowing predicting electricity consumption. A number of research works are concerned with the set of structural models and its corresponding applicabilities are introduced. The predictions are proposed for the research reference, depending upon previous work analogy. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic has begun in early 2020 and still continues to strongly affect the entire world delivering a significant global, shock, but varying across countries and commodity sectors. The Government of the Republic of Serbia has been adopting different measures to slow down the dissemination of the coronavirus, specifically nationwide lockdown in March and April 2020. Business activities have been reduced. The pandemic situation has changed the lifestyle as people are mostly staying home and working from home. This paper provides a review of unprecedented impacts of COVID-19 pandemic, with restrictions and lockdown in Serbia, on electricity sector at this stage of the crisis. The outcomes offer a contribution to the body of literature because limited research has been conducted on these relationships in case of Serbia. Sets of statistical indicators are used to analyze changes the electricity sector has been facing. Data visualization is used to compare developments during the pandemic with those of previous years. Our research and data-driven analysis of these impacts should improve the understanding of the techno-economic effects of unforeseen events, such as a pandemic, on the power system, scrutinizing if effects could be relatively short-lived or longer-lasting. [ABSTRACT FROM AUTHOR]

This paper addresses electricity consumption management in manufacturing enterprises. The research aims to provide manufacturing enterprises with an effective tool to control electricity costs. Recently, some factors have been observed to affect the rapid changes in the operating conditions of enterprises. These include the transformation of the power sector toward renewable energy, the disruption of supply chains resulting from a coronavirus pandemic, political crises, and process automation. A method for the analysis and management of electricity consumption in enterprises based on simulation modeling is proposed. The simulation model contains predefined objects representing physical system elements and the data processing algorithm. The production order execution time, energy consumption, employee overtime, and machine load are included in the model. The results show that it is possible to determine the level of power available for the process completion and its influence on the production volume and realization time. In the studied case, when the available power was reduced by half, there was an increase in order execution time of nearly 25 percent and an increase in energy consumption of nearly 15 percent. The method can be used in the operational activities of enterprises as well as extended to different types of production processes. [ABSTRACT FROM AUTHOR]

Large quantities of post-use glass packages are produced globally, that so need to be treated as waste: this is cause of a global environmental concern. Therefore, efforts are required for optimisation and promotion of re-use and recycling practices with a waste valorisation-oriented approach in a circular economy context. In this context, the study was aimed at documenting environmental damages and improvements related to recycling glass cullet into sodium silicate in water solution on a lab-scale chemical process. Life Cycle Assessment was applied for this purpose according to the specialised International Standards. The study highlighted that the environmental hotspots of the process stay in the production of electricity and of sodium hydroxide as both required for the chemical reaction development. Those two input items contribute 81.94% and 14.33% of the total damage associated with the whole lab process, that is equal to nearly 36.5 μpt. A 64% environmental damage reduction could be obtained by sourcing the process electricity requirements by means of a photovoltaic plant. Furthermore, through a sensitivity analysis, the authors proved that the investigated sodium silicate is appreciably more environmentally sustainable than the virgin-origin counterpart, whose environmental profile was measured in nearly 43 μpt. The study can be considered as a proof that, already in the design phase on a lab-scale dimension, it is possible to identify recycling paths that may contribute to implementing sustainable circular models of the economy. [Display omitted] • The paper investigates the recycling of post-use glass containers into sodium silicate. • Life Cycle Assessment was applied to a chemical process on the laboratory scale. • The functional unit was 41g sodium silicate. • Electricity consumption and sodium hydroxide production were the environmental hotspots. • Recycled sodium silicate was environmentally proven than the virgin counterpart. [ABSTRACT FROM AUTHOR]

In recent decades, the Nonlinear Grey Bernoulli Model "NGBM (1, 1)" has been applied in various fields and achieved positive results. However, its prediction results may be inaccurate in different scenarios. In order to expand the field of application and to improve the predictive quality of the NGBM (1, 1) model, this paper proposes an effective model (named Fourier-NGBM (1, 1)). This model includes two main stages; first, we get the error values based on the actual data and predicted value of NGBM (1, 1). Then, we use a Fourier series to filter out and to select the low-frequency error values. To test the superior ability of the proposed model, two numerical data sets were used. One is the historical data of annual water consumption in Wuhan from 2005 to 2012 in He et al. 's paper, and the other is example data from Wang et al. 's paper. The forecasted results prove that the performance of the Fourier-NGBM (1, 1) model is better than three other forecasting models, namely GM (1, 1), NGBM (1, 1) and the improved Grey Regression model. Furthermore, this study also applied the proposed model to forecast the electricity consumption in Vietnam up to the year 2020. The empirical results can offer valuable insights and provide basic information for model building to develop future policies regarding electrical industry management. In subsequent research, more methodologies can be used to reduce the residual error of the NGBM (1, 1) model, such as Markov chain or different kinds of Fourier functions. Additionally, the proposed model can be applied in different industries with fluctuating data and uncertain information. [ABSTRACT FROM AUTHOR]

Short-term load forecasting (STLF) usually begins by grouping data according to various criteria, most often by days of the week. Then, based on the obtained segments, independent models are created. Each model’s prediction uses only one segment of the data. This paper proposes a new approach to model formation based on the correlation between the forecasted day and previous days. The proposed approach is compared with the usual approach where data segments are obtained by grouping according to days of the week. The models were created using fuzzy logic and ANFIS. The mean absolute percentage errors of the new approach and the usual approach using ANFIS in terms of prediction accuracy are obtained as 2.89 and 4.15, respectively. The mean absolute percentage errors for the new approach and the usual approach are 3.39 and 4.78, respectively, when fuzzy logic is used. The results showed that when the proposed method is used, forecasts for the day ahead are much more accurate in both cases. [ABSTRACT FROM AUTHOR]

In the past 20 years, China has undergone a rapid process of electrification, which has contributed to the modernization of people's lives. This paper associated household electricity consumption, appliance service function, total cost of electricity consumption to life well-being for the first time, and explained the structural characteristics of these changes. The welfare index from appliance services is defined as the result of the interaction between electricity consumption and appliance operation, and is used as an indicator to assess the improvement of household well-being. We sorted out 9 types of service functions of appliances, estimated the structure of household electricity consumption, total electricity cost and welfares received, and analyzed the factors that enhance welfare and their contributions. The results show that the electricity consumed by 12 main household appliances per household per year increased from 358 kWh in 2000 to 1419.5 kWh in 2020, and the total household electricity cost increases from 1315.74 yuan (RMB) to 6772.68 yuan. The quantity and structure of both have changed greatly. The service functions provided by appliances are increasingly diversified, have expanded from the basic services such as lighting, watching TV, refrigerated food to nine aspects including communication and transportation. The quality of life of residents continues to be improved, and the welfare index has increased from 2.48 to 7.82. There is a good linear relationship between the index and the three independent variables. The unit contributions of household disposable income, total electricity cost and household population size to the welfare index were 0.0836, 0.1195 and −1.6161, respectively. To accelerate electrification and enhance people's well-being, China needs to further improve the power and communication infrastructure, promote the application of intelligent technology, and implement precise encouragement policies. • Electricity consumption and appliance services cloud be linked to residential welfare. • The changes of household electricity structure and cost are quantitatively measured. • The welfare index from home appliance services are estimated for the first time. • The well-being is influenced by ability to pay, willingness to pay and family size. • The domestic electrification has greatly improved people's quality of life. [ABSTRACT FROM AUTHOR]

Knowing the demand for electrical consumption beforehand is important for efficient energy programming policies that can help with climate change, life cycle-costs, and optimal primary resource extraction. In this paper, we propose a framework to improve forecasting performance of high frequency electrical consumption data. We use different models for each day of the week, and then compose them to obtain the total forecast. We apply both machine learning (Long-Short Term Memory network) and econometric models (AutoRegressive Integrated Moving Average and Holtz-Winters) that consider time dependence in the data comparing model performance. We find that a classical ARIMA model outperforms other models; however, in applying the proposed framework, LSTM manages to outperform all other models. The results are statistically significant as indicated by the Model Confidence Set test constructed for Mean Absolute Percentage Error and Mean Square Error. [ABSTRACT FROM AUTHOR]

• Econometric panel data techniques that address cross-country heterogeneity and cross-sectional dependence are adopted over 1971–2015. • A significant and positive long-term relationship exists between per capita economic growth and per capita renewable electricity consumption. • Granger causality does not emerge between per capita economic growth and per capita renewable electricity consumption. • Per capita economic growth appears to be a causal factor for total electricity consumption. Renewable electricity is a pillar of the sustainability transition being pursued through climate and energy policy strategies, and the European Green Deal represents a potential investment plan for this new phase of development. Economic growth can be influenced by the expansion of renewable electricity consumption, but the nature of their relationship is ambiguous and depends on various economic and policy factors. This paper investigates the long-run relationship between renewable electricity consumption and economic growth in selected countries over the period 1971–2015 using econometric panel data techniques that specifically address cross-country heterogeneity and cross-sectional dependence. Our findings suggest that, on average, there is a significant positive long-term relationship between renewable electricity consumption and economic growth, although Granger causality is not detected. Regarding causality, we do find per capita economic growth to be a causal factor for total electricity consumption and fossil-fuel based electricity consumption. [ABSTRACT FROM AUTHOR]

Fractional order grey model is effective in describing the uncertainty of the system. In this paper, we propose a novel variable-order fractional discrete grey model (short for VOFDGM(1,1)) by combining the discrete grey model and variable-order fractional accumulation, which is a more general form of the DGM(1,1). The detailed modeling procedure of the presented model is first systematically studied, in particular, matrix perturbation theory is used to prove the validity in terms of the stability of the model, and then, the model parameters are optimized by the whale optimization algorithm. The accuracy of the proposed model is verified by comparing it with classical models on six data sequences with different forms. Finally, the model is applied to predict the electricity consumption of Beijing and Liaoning Province of China, and the results show that the model has a better prediction performance compared with the other four commonly-used grey models. To the best of our knowledge, this is the first time that the variable-order fractional accumulation is introduced into the discrete grey model, which greatly increases the prediction accuracy of the DGM(1,1) and extends the application range of grey models. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to model electricity consumption using Artificial Neural Networks (ANN). Total electricity consumption and consumption generated by households (HH) were modeled. The input variables of the ANN were based on nighttime light images from VIIRS DNB. Studies conducted thus far have covered mainly linear models. Most of case studies focused on single countries or groups of countries with only few focusing on the sub-national scale. This paper is pioneering in covering an area of Poland (Central Europe) at NUTS-2 level. The use of ANN enabled the modeling of the non-linear relations associated with the complex structure of electricity demand. Satellite data were collected for the period 2013–2016, and included images with improved quality (inter alia higher resolution), compared to the DMSP/OLS program. As images are available from April 2012 onwards, it is only recently that their number has become sufficient for ANN learning. The images were used to create models of multilayer perceptrons. The results achieved by ANN were compared with the results obtained using linear regressions. Studies have confirmed that electricity consumption can be determined with higher precision by the ANN method. • Innovative modeling of electricity consumption by artificial neural networks based on nighttime light images from VIIRS DNB. • A new way of preparing the input data of the model. • Total electricity consumption and electricity consumed by households were modeled. • The first electricity consumption analysis covered regions of Poland (Central Europe) at NUTS-2 level. [ABSTRACT FROM AUTHOR]

Households are the major energy consumer and contributor to the emission of greenhouse gases. The Algerian policy of mastering energy has improved building energy efficiency since 1994 by introducing thermal regulation (DTR). However, energy consumption is still increasing instead of decreasing, which is mainly due to occupants' behaviour which is difficult to estimate and predict. This paper explores the impact of households and housing characteristics on residential gas and electricity consumption in the 36 municipalities of the department of Djelfa (Algeria) which is located in an arid and semi-arid climate zone. This paper is based on GIS and statistical techniques. It considers the yearly gas and electricity energy consumption (2013) of the municipalities of the department of Djelfa. The method is organised in four steps: (a) a multiple linear regression is used to construct two estimative models of gas and electricity. The models have more than 93% of accuracy for both gas and electricity models; (b) estimating gas and electricity consumption for 2008 according to the developed models; (c) organisation of the census data of 2008 in five dimensions: the population distribution, household characteristics, housing type and occupancy, and finally household appliance ownership; (d) a set of sensitivity analysis is performed based on Principal Component Analysis (PCA) and Pearson's bivariate correlation and finally a path analysis is performed based on Structural Equation Model (SEM) to assess the importance of each variable. The overall impact of all these variables indicates that increasing the household size is the first factor reducing the electricity and gas consumption followed by the housing surface, density, room occupancy, and older households, while increasing the education level and appliance ownership boosts both per-capita gas and electricity consumption. [ABSTRACT FROM AUTHOR]

The Information and Communication Technology (ICT) sector has gained much attention in the discussions on climate change, as it could impact global emissions both positively and negatively. The objective of the present study is to provide estimates for the 2020 use stage electricity consumption and ICT sector's total lifecycle greenhouse gas (GHG) emissions divided in three main parts: user devices including internet-of-things, networks and data centers. The study builds on a high number of data sources including measured and reported data from 150 companies that is estimated to cover about 80% of network subscriptions, about 55% of data center electricity, and about 35% of upstream GHG emissions. To understand the development, the results are put into the perspective of earlier studies. In conclusion, the ICT sector used about 4% of the global electricity in the use stage and represented about 1.4% of the global GHG emissions in 2020. The use stage electricity consumption and the total GHG emissions have increased since 2015, but the impact per subscription has decreased. The user devices accounted for over half of all GHG emissions, with equal parts relating to use stage and other lifecycle stages. For networks and data centers, the use stage GHG emissions are dominating. The electricity consumption and GHG emissions are also estimated for the closely related areas Entertainment and Media (including e.g., TVs), paper media, and cryptocurrencies. • ICT sector represents ∼4% of global electricity consumption in 2020. • ICT sector represents 1.4% of global GHG emissions in 2020. • User devices represents a majority of GHG emissions (∼57%). • Embodied emissions represent 36% of total emissions. • The ICT sector has increased its emissions by about 5% from 2015. [ABSTRACT FROM AUTHOR]

In the context of a resilient energy system, accurate residential load forecasting has become a non-trivial requirement for ensuring effective management and planning strategy/policy development. Due to the highly stochastic nature of energy load profiles, it is difficult to predict accurately, and usually, predictions are error-prone. This paper explores the potential of Empirical Mode Decomposition (EMD) in simplifying the dynamics of complex demand profiles. The simplified components are then embedded within a deep learning model, specifically Convolution Neural Network (CNN) and Long Short-Term Memory (LSTM), to forecast short-term residential loads. The novel modelling framework integrates Bayesian optimisation strategy, feature decomposition technique, feature engineering phase, and percentile-based bias correction algorithm to enhance model accuracy. The model is developed using a case-study residential dwelling located in Fintry (Scotland), and the model performance is assessed over four forecast horizons. The overall efficiency of framework is also investigated for three algorithms: random forest, gradient boosting decision trees (GBDT), and an LSTM network. While EMD and feature engineering were found to greatly improve prediction accuracy, the number of IMFs used was shown to significantly impact the model's performance and computational complexity. The model was tested on two further case studies from Fintry. • A novel forecasting framework is proposed for short-term energy demand prediction. • Multi-domain features are extracted to increase the accuracy. • Utilising empirical mode decomposition to enhance framework performance. • Exhibit strong forecasting capability without the additional computational cost. • Excellent forecasting accuracy and model robustness are validated using three households. [ABSTRACT FROM AUTHOR]

Flexibility has increasingly gained attention within the field of electrification and energy transition where a common objective is to reduce the electricity consumption peaks. However, flexibility can increase the risk of grid congestion depending on where and when and it is used, thus an overall system perspective needs to be considered to ensure an effective energy transition. This paper presents a framework to assess electricity users' contributions to grid load peaks by splitting electricity consumption data into subsets based on time and temperature. The data in each subset is separately correlated with the grid load using three correlation measures to assess how the user's consumption changes at the same time as typical grid peak loads occur. The framework is implemented on four different types of business activities at Uppsala municipality in Sweden, which is a large public entity, to explore their behaviors and assess their grid peak load contributions. The results of this study conclude that all four activities generally contribute to the grid peak loads, but that differences exist. These differences are not visible without splitting the data, and not doing so can lead to unrepresentative conclusions. The presented framework can identify activities that contribute the most to unfavorable grid peaks, providing a tool for decision-makers to enable an accelerated energy transition. • Assess electricity consumer's contributions to grid peak loads using correlation. • Data is split to reveal different and opposite behaviors that otherwise are not visible. • The suggested framework includes important features without complex modeling. • Four different types of consumers are tested, showing different results. • Results can be used to decision-making about smart grid services, e.g. user flexibility. [ABSTRACT FROM AUTHOR]

In recent years, the grey-based models with fractional accumulation have received extensive attention by scholars and have been widely used in various fields. However, the existing rough construction of the background value in the fractional grey model impairs its predictive performance to some extent. To address this problem, this paper reconstructs a dynamic background value for the fractional grey model by the composite integral median theorem, as a result, a novel fractional grey model-based variable background value (denoted as OFAGM(1,1) for short) is proposed. In particular, the Particle Swarm Optimization algorithm (PSO) is then employed to determine the optimum for the fractional order and the background value coefficients. Based on electricity consumption of two regions of China (i.e. Beijing, Inner Mongolia), the superiority of the proposed model has been verified in comparison with other benchmark models, the electricity consumption of Beijing is predicted to reach 1 3 8 5. 3 5 × 1 0 8 Kwh in 2022 and that of Inner Mongolia will reach 5 0 6 3. 3 9 × 1 0 8 Kwh in 2023. This study also takes the relative growth rate and the doubling time into account for these two regions that facilities comparison of the regions' performance. [ABSTRACT FROM AUTHOR]

Electricity consumption and material wastage of manufacturing industries have directly or indirectly influenced the environment. Many manufacturing enterprises are committed to improving energy and material efficiencies. To achieve this goal, one of the high-efficiency ways is to optimize the scheduling. In this study, a multi-object optimization model is constructed for a particular kind of batch processing scheduling problem existed in flexible flow shops, where the objects include makespan, electricity consumption and material wastage. First, the models for electricity consumption and material wastage are built, based on which a mathematic model for scheduling problem is built afterwards. Finally, a hybrid non-dominated sorting genetic algorithm II (NSGA-II) method is employed to solve the multi-object optimization scheduling model. A case study based on a real-world paper mill industry is presented to demonstrate the effectiveness of the method and its application in practice. Moreover, a real-life scheduling problem is investigated, and the result shows that the proposed method is more efficient than manual scheduling in energy and material saving. In fact, many tissue paper mills or other manufacturing industries schedule by manual labor in China, indicating that the proposed method has a significant potential in improving energy and material efficiencies in the studied flexible flow shop, and in energy and material saving in similar industries. [ABSTRACT FROM AUTHOR]

The paper uses qualitative data from Norway and the United Kingdom to understand the new technology of In Home Display monitors as a material object loaded with meaning and norms that may affect social practices and relations. The displays are designed to encourage householders to reduce electricity consumption. In contrast to technologies associated with 'smart meters', the monitors under study cannot be used for controlling or automatising various types of electricity consumption, but these devises nonetheless often form part of 'smart grid solutions'. A large part of the research in this area has attempted to quantify the impact of displays, and qualitative research focusing on the users has also mainly sought to explain why - or why not - the introduction of displays has resulted in reduced household consumption. This paper follows a more open approach to the introduction and impact of displays by paying attention to the existing routines and social practices into which the display enters and potentially becomes integrated and domesticated. We examine to what extent ideas and norms inscribed in the display continue to have a bearing on the household moral economy and internal dynamics as the objects are negotiated and taken in use in British and Norwegian homes. Drawing on earlier studies that have sought to combine practice and domestication theory for understanding displays, the study's novelty lies in its focus on the materiality of displays and social implications thereof, and its analysis of the social status of this object in two different contexts. [ABSTRACT FROM AUTHOR]

Student residence halls occupy 26% of the total area of a typical university campus in the UK and are directly responsible for 24% of university’s annual CO2emissions. Based on five years measured data, this paper aims to investigate the energy-related environmental and economic performance of electrically heated residence halls in which space heating is provided by two different types of electric heaters, that is, panel heater (PHT) and storage heater (SHT). Secondly, using statistical and machine learning methods, the paper attempts to investigate the relationship between daily electricity consumption and five factors (ambient temperature, solar radiation, relative humidity, wind speed and type of day). Data analysis revealed that electricity consumption of both halls is mainly driven by ambient temperature only, whereas SHT residence has 39% higher annual electricity bill and emits 70% higher CO2emissions on a per square metre basis compared to the PHT residence hall. [ABSTRACT FROM AUTHOR]

Some scholars have addressed the relationship between the Human Development Index (HDI) and energy consumption in terms of the semi-logarithmic or hyperbolic function. One of the results from this relationship is to divide the world countries into two categories, developed and developing countries. This classification considers pre-developing countries and developing countries into one category (developing) while the proportion of people with fundamental energy needs in the former is far higher than in the latter. The objective of this paper is to allocate a separate class for pre-developing which their fundamental energy needs have not completely satisfied. The methodology of the study is divided into two parts. Initially, based on the longitudinal data (112 country’s data during the period of 2005–2013), a linear Quality of Life (QoL) indicator is proposed in terms of six variables. Then an S-shape (sigmoid) curve is fitted to the QoL indicator data against energy consumption (total primary energy supply as a proxy) per capita (ECpc) and electricity consumption per capita (Elcpc) data. Three types of countries, developed, developing, and pre-developing are identified based on the sigmoid function. The results of the proposed model demonstrate that the “pre-developing” category has different QoL and ECpc as compared to developing and developed classes. Another result of the paper shows the entry of new technologies has influenced the QoL and Elcpc to a greater extent in developing countries than in developed countries. One-way analysis of variance is a method to shed light on the latter consequence. In the case of pre-developing countries, the pertinent analysis shows an insignificant impact. This paper concludes the new classification of countries appropriately addresses variation of QoL against ECpc in each class. [ABSTRACT FROM AUTHOR]

Electricity is a key energy source in each country and an important condition for economic development. It is necessary to use modern methods and tools to predict energy consumption for different types of systems and weather conditions. In every industrial plant, electricity consumption presents one of the greatest operating costs. Monitoring and forecasting of this parameter provide the opportunity to rationalize the use of electricity and thus significantly reduce the costs. The paper proposes the prediction of energy consumption by a new time-series model. This involves time series models using a set of previously collected data to predict the future load. The most commonly used linear time series models are the AR (Autoregressive Model), MA (Moving Average) and ARMA (Autoregressive Moving Average Model). The AR model is used in this paper. Using the AR (Autoregressive Model) model, the Monte Carlo simulation method is utilized for predicting and analyzing the energy consumption change in the considered tobacco industrial plant. One of the main parts of the AR model is a seasonal pattern that takes into account the climatic conditions for a given geographical area. This part of the model was delineated by the Fourier transform and was used with the aim of avoiding the model complexity. As an example, the numerical results were performed for tobacco production in one industrial plant. A probabilistic range of input values is used to determine the future probabilistic level of energy consumption. [ABSTRACT FROM AUTHOR]

Electricity consumption in cities is steadily increasing. Using a life cycle approach and fuel mix data from power companies’ sustainability reports, this paper analyzes greenhouse gas (GHG) emissions from electricity consumption in Hong Kong. The results show that coal contributed on an average 74.3 percent, liquefied natural gas 25.1 percent, and oil 0.6 percent of the thermal energy consumed for generating electricity in Hong Kong between 2002 and 2015. Besides, Hong Kong imported an average of 7.96 billion kWh per year net electricity from a nuclear power plant in Shenzhen. During this period, GHG emissions from annual electricity consumption ranged between 27.0 and 34.1 million tons (MT) and the emission factor ranged between 702 and 792 g CO 2 -eq/kWh. Hong Kong’s gross domestic product (GDP) increased steadily from USD 176 billion in 2002 to USD 297 billion by 2015. As a result, Hong Kong’s electricity productivity increased from 4.62 to 6.75 USD/kWh while GHG emission from electricity consumption per GDP decreased from 0.153 to 0.104 MT CO 2 -eq/USD billion. Hong Kong’s annual electricity consumption was predicted over the short-term period (2016–2020) and medium term (up to year 2030). Electricity consumption is likely to increase to 44.63 billion kWh by 2030 while GHG emissions from electricity consumption would increase to 33.92 MT of CO 2 -eq. The implications are discussed at the end of the paper. [ABSTRACT FROM AUTHOR]

This paper examines the stationary properties of the electricity consumption of five main sectors (residential, public services, industrial, agricultural, and street lighting) in Iran over the period 1967–2017. To analyze the data, we apply the Lagrange Multiplier (LM) and GARCH-based unit root tests with structural breaks. The results of our study provide strong evidence that electricity consumption is stationary in the industrial, residential and street lighting sectors; thus, sharp shocks have transitory effects on electricity consumption, implying that consumption trends in these sectors will ultimately return to their long-run equilibrium. However, the time series of electricity consumption for the agricultural and public services sectors contain a unit root, and thus shocks to their electricity consumption are permanent. The foregoing findings can help policymakers in each sector to design efficient electricity management policies. [ABSTRACT FROM AUTHOR]

This paper reports on a study of electricity consumption, for achieving thermal comfort, and possible relation to respective plan layouts, in apartments of tropical Dhaka, the capital of Bangladesh, which is one of the most densely populated cities in the world. As approximately 45% of the total population of Dhaka constitutes the middle income and upper-middle income groups, electricity consumption by this group is a critical factor in the national energy balance. According to recent reports, the electricity consumption in the residential sector has almost doubled in 6 years. During the warm months (March–October), ventilation and air movement are vital for thermal comfort in the tropics, and electrical cooling appliances are commonly used for the purpose. The target middle income group resides in apartments of floor area between 93 and 149 m2 (1000–1600 ft2). A field survey was conducted, whereby scaled drawings of plan layout of the apartments were obtained, to understand the spatial arrangement of the existing apartments, i.e., to assess the arrangement of spaces in the apartment units in terms of their potential to allow air movement. Two basic types of layouts were found mostly used in Dhaka; defined in the study as "open type" and "cellular type" layouts. A questionnaire survey was conducted on sample units, to determine the specifications of electrical appliances being used for cooling and to assess the comfort situation of the inhabitants. It was the contention of this study that there could be a critical analysis of plan layouts in mid-rise apartment buildings, to determine whether there is a relationship between the energy consumption and layout of these plans. Analysis of the findings from the survey and the questionnaire responses reveal that plan layout does, indeed, have a significant impact on electricity consumption needed for thermal comfort. [ABSTRACT FROM AUTHOR]

Managing household electricity consumption plays an important role in the overall energy management spectrum. This paper presents an analysis of the main factors that contribute to household electricity consumption. Emphasis is given on consumer behaviour in relation to household characteristics. For this purpose, primary data is collected via a survey study from a representative sample of households. The data were analysed using correlational as well as regression analysis methods. It was found that electricity consumption is a social phenomenon, with economic and technological dimensions. Further, it was verified that energy-saving techniques such as insulation, modern building materials and renewable energy make a significant difference in the electricity cost. Moreover, specific types of electrical appliances are highly correlated with electricity consumption. [ABSTRACT FROM AUTHOR]

• The matrix algorithm of a dynamic background value for the interval sequence is proposed. • The multi-variable grey model in matrix form can directly predict the interval sequence. • New model essentially combines two bounds of the interval to predict one of them. • New model well fits the extreme points of electricity consumption in different seasons. The multi-variable grey model based on dynamic background algorithm improves the forecasting performance of the multi-variable grey model on the precise number sequence. In order to make this model suitable for the interval sequence, the matrix form of the multi-variable grey model based on dynamic background algorithm is proposed in the paper. In the modeling process, the interval is treated as a two-dimensional column vector, the parameters of the multi-variable grey model are replaced by matrices, and the dynamic background algorithm for interval sequences is proposed. The analysis results of the matrix algorithm for the dynamic background value and the prediction formula show that the new model is essentially a way to predict one of the two bounds of an interval by combining them, reflecting the integrity and interaction between the lower and upper bounds. The interval predictions of industrial electricity consumption of Zhejiang Province, China national electricity consumption and consumer price index show that the new model can well predict the minimum and maximum values of the interval sequence and has better prediction performance compared with the method of predicting each boundary sequence separately. [ABSTRACT FROM AUTHOR]

• There is spatial correlation of electricity consumption of China. • Analyze impact of technology and industrial structure on electricity consumption. • Industrial structure contributes more to reduce electricity consumption. • Region heterogeneity is obvious among different regions and grid service zones. The increase of electricity consumption not only leads to economic growth, but also pollutes environment due to the heavy dependence on fossil fuels. How to reduce the electricity consumption without affecting the economic development is a challenging and pivotal issue. Relevant empirical evidence is scarce, so this paper deepens the understanding of two paths to decrease electricity consumption: technological progress and upgrading of industrial structure based on spatial and heterogeneity analyses. By constructing two spatial panel models, results show that electricity consumption among provinces in China is positively spatial-related and has certain path-dependent characteristics. To promote the technological progress and optimize the industrial structure are two effective solutions to reduce electricity consumption, and the latter channel plays a more important role. Heterogeneity among different regions and grid service zones exists obviously. [ABSTRACT FROM AUTHOR]

Time lag effect exists widely in the course of economic operation. Some economic variables are affected not only by various factors in the current period but also by various factors in the past and even their own past values. As a class of dynamical models, autoregressive distributed lag (ARDL) models are frequently used to conduct dynamic regression analysis. In this paper, we are interested in the quantile regression (QR) modeling of the ARDL model in a dynamic framework. By combining the working likelihood of asymmetric Laplace distribution (ALD) with the expectation–maximization (EM) algorithm into the considered ARDL model, the iterative weighted least square estimators (IWLSE) are derived. Some Monte Carlo simulations are implemented to evaluate the performance of the proposed estimation method. A dataset of the consumption of electricity by residential customers is analyzed to illustrate the application. [ABSTRACT FROM AUTHOR]

Today, electrical energy plays a major role in production and consumption and is of special importance in economic decision-making process. Being aware of electrical energy demand for each period is necessary to correct planning. Therefore, the forecasting of electricity consumption is important among several economic sections. Besides the traditional models, in this paper, we offer a hybrid forecast approach that combines the adaptive wavelet neural network with the ARIMA-GARCH family models and uses the effective exogenous variables on electricity consumption. Based on this approach, two hybrid models are proposed. To assess the ability of the proposed models, we forecasted the daily electricity consumption by the hybrid and benchmark models for 60 days ahead in two separate seasons (summer and winter). The empirical results showed that the proposed models have more prediction accuracy compared with the other benchmark forecast models including neural network, adaptive wavelet neural network, and ARIMAX-GARCH family models. [ABSTRACT FROM AUTHOR]

Forecasting of electricity energy consumption (EEC) has been always playing a vital role in China's power system management, and requires promising prediction techniques. This paper proposed an optimized hybrid GM(1,1) model to improve prediction accuracy of EEC in short term. GM(1,1) model, in spite of successful employing in various fields, sometimes gives rise to inaccurate solution in practical applications. Time response function (TRF) is an important factor deeply influencing modeling precision. Aiming to enhance forecasting performance, this paper proposed a novel grey model with optimal time response function, referred to as IRGM(1,1) model. As of unknown variables in TRF, a nonlinear optimization method, based on particle swarm algorithm, is constructed to obtain optimal values, for shrinking simulation errors and improving adaptability to characteristics of raw data. The forecasting performance has been confirmed by electricity consumption data of China, comparing with three alternative grey models. Application demonstrates that the proposed method can significantly promote modeling accuracy. [ABSTRACT FROM AUTHOR]

This paper empirically examines electricity consumption–economic growth nexus in Uganda from 1981 to 2013. Autoregressive distributed lag-bounds testing and Granger causality tests are employed for analysis. The results confirm the existence of long-run relationship between electricity consumption and economic growth and vice versa. In addition, the Granger causality test results confirm conservation hypothesis in the short run and feedback hypothesis in the long run. Therefore, the paper recommends Ugandan authorities not only to develop energy policies geared toward promoting efficient energy use but also to expand electricity infrastructure to address increased electricity demand to support economic growth. [ABSTRACT FROM PUBLISHER]

Until recently, the price of electricity in Ethiopia was among the lowest in the world. Such low prices have contributed to a substantial financial deficit for the government-owned electric utility and led to a degradation in the quality of electricity services delivered to customers. In December 2018, the utility increased the electricity tariff to help to finance improvements in the quality of electricity services. This paper studies the effect of the revised tariff on urban household electricity consumption and alternative fuel expenditure. The study relied on two rounds of household survey data and six years of electricity consumption data from the utility company. The study finds that prepaid customers reduced their electricity consumption by about 22 kWh per month in the post-tariff-adjustment periods, equivalent to about 10% of electricity expenditure and 14% of daily consumption. In the overall sample, however, consumption slightly increased over time. These results imply that the price elasticity of demand for electricity in urban Ethiopia is highly inelastic. Moreover, households did not shift substantially toward the use of alternative fuels. The findings indicate that governments and utilities in settings where electricity is priced well below cost-covering levels may be able to increase revenues and improve their balance sheets with relatively modest effects on households' electricity consumption, though effects from more substantial tariff hikes should be examined. • The price of electricity in Ethiopia was until recently among the lowest in the world. • The utility company increased the electricity tariff with the aim of improving the quality of electricity services. • This paper studies the effect of the revised tariff on urban households' electricity consumption. • The study result shows a highly inelastic demand. • The study has policy implications in settings where electricity price is well below cost-covering level. [ABSTRACT FROM AUTHOR]

Energy efficiency standards for household appliances have been adopted in many countries to mitigate negative externalities, reduce emissions, and save energy. Using Chinese provincial-level panel data from 2008 to 2018, this paper builds a difference-in-difference model to examine the mechanism by which energy-efficiency upgrades in China's air conditioners affect urban household electricity usage. The results show that the upgrades have brought about an obvious reverse effect, with urban household electricity usage increasing rather than decreasing. Reducing the unit costs of energy service has enhanced residents' sensitivity to cooling demand. Driven by the substitution and income effects, urban residents may increase the intensity and frequency of their AC use. Additionally, this reverse effect is heterogeneously dependent on the family size and urban residents' age structure rather than their educational level. When families are larger and have more children, the reverse effect is more pronounced. This paper's findings provide useful recommendations for policy-makers to formulate policies that are synergistic with energy efficiency standards for household appliances. [ABSTRACT FROM AUTHOR]

Future smart infrastructure development, in both developing and developed countries, is hinged on demand management and response strategies with consumers actively involved in time-shifting electricity consumption for improved efficiency. This paper presents a qualitative, interview-based, comparative study of how homeowners adapt their practices to the changing systems of electricity provision in two countries, Pakistan and Denmark. It reveals that household practices like laundering are flexible, highly contextualised and embedded in the wider socio-material and cultural context. In Denmark, time-shifting of laundering in households with photovoltaics is done voluntarily and closely interwoven with the temporal rhythms of the common dual-income household, as well as the natural cycles of the sun and weather, and is in most cases based on some degree of automation. In Pakistan, blackout schedules dictate time-shifting of most practices. Large family sizes and nuanced clothing make laundering more complex, socially bound and time-consuming; however, joint family systems, provision of house-staff and outsourcing make it more time-flexible and less dependent on automation and electricity-use. Using theories on temporalities of practices in a cross-cultural analysis highlights the significance of local socio-material and cultural context in the performance, bundling and synchronisation of practices. While practice theories prove useful in cross-cultural comparison of temporalities of household practices and demand, further theory development is needed to conceptualise practices as shared or socially differentiated entities in varying cultural contexts. This has implications for demand management policies proposed in smart-grid transitions as well as in the possible cross-cultural transfer of smart technology and demand response strategies. [ABSTRACT FROM AUTHOR]

China has the largest electricity system in the world, which is undergoing a critical market reform. Based on the panel data in 2000 to 2016 of China, this paper tries to explain theinconsistency between electricity consumption and economic growth. For example, in 2015, GDP growth rate was close to 6.9% but with only 2.9% growth in electricity consumption. However, in 2018, a 6.6% growth in GDP required an 8.5% electricity growth. The results explain the reasons for inconsistency and identify the key factors. We find that the increase in inventory, fixed capital and industrial electricity consumption will narrow the gap when economy grows faster than electricity consumption, and widen the gap on the contrary. Heterogeneity exists among regions, the model and variables seem most convincing in explaining the situation in the western region, which is most similar to the full sample of China. Feedback effect is also observed between electricity consumption and economic growth in most parts of China by Granger test. The findings provides suggestions for the policy makers in making power planning, in an effort to avoid large power shortage or surplus. • Inventory, fixed capital and industrial electricity consumption will impact the deviation. • Impacts on deviation in western region are most similar to the full sample, and eastern region goes opposite. • Feedback effect is observed between electricity consumption and economic growth in most parts of China. [ABSTRACT FROM AUTHOR]

Building orientation is one of the driving factors that impacts building energy consumption, which deserves to be studied. The Sizhai traditional dwellings located in Zhejiang province were chosen as the study buildings in this paper. The geometric model was rotated at 20° increments clockwise to create a total of 18 test scenarios. Integration of virtual simulation in software, the thermal and daylighting performances in 18 test scenarios were simulated to assess their indoor comfort levels in terms of the indoor temperature, air velocity and illuminance. Furthermore, the indoor comfort level has an impact on the energy consumption of building. To this end, the electricity consumption of air conditioner (AC), electrical ventilation and artificial lighting, as well as the total annual electricity consumption including AC, electrical ventilation and artificial lighting were computed by software to explore the optimum Building Azimuth (BA). The results show that a total annual electricity cost difference of approximately 150 kW h throughout a year between the best (S) and worst (N-W80) BA of the building was achieved. By performing BA measurement for all dwellings in Sizhai village, the conclusion is that this village has a high energy saving potential. • Building model was rotated at 20° increments clockwise to create 18 test scenarios. • Three evaluation parameters were adopted to assess indoor comfort level. • Electricity use difference of 150 kW h between the best and worst BAs was achieved. • Energy saving potential was evaluated for Sizhai integrated with Google Earth. [ABSTRACT FROM AUTHOR]

This paper empirically evaluates the extent of energy resilience achieved in a socially-deprived community in Oxford, through deployment of solar photovoltaic (PV) systems and smart batteries (internet enabled and controllable) across a cluster of 82 dwellings (households). The methodological approach comprised dwelling and household surveys, along with high frequency monitoring of household electricity consumption, solar PV generation, battery charge and discharge data. In the monitored households, average daily electricity consumption was found to be positively related with dwelling size, number of occupants and number of appliances used. Although 117 MWh of PV electricity was generated within a year across 74 dwellings, peak generation did not match peak consumption, demonstrating the need for battery storage. Home batteries were found to increase self-consumption of PV electricity and offset grid demand through discharge of stored PV electricity marginally at an average of 6%, depending on the size of the PV system, surplus PV electricity available and size of the battery. Aggregating solar generation and storage at a community level showed that peak grid electricity demand between 17:00 and 19:00 was reduced by 8% through the use of smart batteries across 74 dwellings. In future, a local energy sharing scheme could be developed, wherein not all dwellings would need to have solar PV systems, but rather have internet enabled batteries that could be monitored and controlled virtually. [ABSTRACT FROM AUTHOR]

The energy use prediction of building systems is crucial to design a high-efficiency building and maintain low energy consumption operation, which is also important in optimizing building system control and retrofitting. This paper demonstrates a comparative study of four data-driven methods used in online building energy predictions involving large-scale data extracted from several types of buildings. The characteristics of building electricity use and data reliability were addressed through the data pre-treatment process including visualization, cleaning, parsing and filtering. Mathematical algorithms and their applications in previous studies were summarized and compared, and evaluation methods were developed. The performance and suitable application scenarios of the proposed algorithms were conducted via the comparison of monitoring data and predicted results. The study indicates that the most complex method which requires the highest computation ability, i.e., the Artificial Neural Network (ANN), does not lead to the highest accuracy, while as the fastest computation method, Gaussian Process Regression (GPR) usually has the results with the lowest accuracy. Support Vector Machine (SVM) and Multivariate Linear Regression (MLR) methods usually perform better in the case scenarios studied. All the prediction accuracies can meet the requirements of RMSE <30% and NMBE <10% proposed by ASHRAE, and the computation time varies from less than 1 s to 22 s per prediction. All these methods/algorithms worked well for buildings with stable energy use patterns. For buildings with complex and unstable occupancy schedules and energy use patterns, MLR and SVM methods have the ability to achieve a high accuracy with fast computation speed. [ABSTRACT FROM AUTHOR]

Abstract A full understand of the influential mechanism concerning electricity consumption has a crucial political reference significance for the implementation of energy conservation and consumption reduction policies. To solve the lack of correlation between the empirical results of the research regions in present researches, this paper takes China's electricity consumption from 1995 to 2016 as the research subject, uses Multi-period ST-LMDI model by setting a unified reference province as a benchmark for different regions in China to completely decompose the changes in China's electricity consumption, and further analyzes the influence mechanism of China's electricity consumption changes by combining the characteristics of the departments and regions. As the result, it's found that the economic growth has a strong impetus for power consumption while the technological progress can effectively curb it. Meanwhile, results of studying electricity consumption from the perspective of industry and region show that the economic structure and consumption intensity have obviously different influences in the eastern, central and western regions. So when it comes to formulate the policy for electricity development and reform, the characteristics of industrial structure as well as the regional differences must be taken into consideration. Highlights • We apply Multi-period ST-LMDI to decompose China's electricity consumption. • The expansion of the economy is the main factor for the growth of electricity consumption. • Decline in electricity consumption intensity restrain the growth of power consumption. • All industrial sectors basically had positive effects on electricity consumption. [ABSTRACT FROM AUTHOR]

Highlights • A big dataset of electricity load time series of residential customers is modelled. • Small sets of modelled parameters are used to summarise the lengthy load time series. • The customers are clustered by the similarity of their time series' model parameters. • The 12 clusters show 61% distinction and 6.75% improved coincidence factor on average. • The clustering method is reasonably robust against a limited form of mixed noise. Abstract Clustering of electricity customers supports effective market segmentation and management. The literature suggests the clustering of residential customers by their load characteristics. The key challenge is the application of appropriate processes to reduce the extreme dimensionality of load time series to facilitate unique clusters. Time feature extraction is a potential remedy, however, it is limited by the type of noisy, patchy, and unequal time-series common in residential datasets. In this paper we propose a strategy to alleviate these limitations by converting any types of load time series into map models that can be readily clustered. This also results in higher cluster distinction and robustness against noise compared to a baseline feature-based approach. A large dataset of residential electricity customers is used to confirm the outcomes as measured by a number of analytical and industrial metrics. The experiment with 12 clusters results in around 61% distinction, improved coincidence factor by around 6.75% relative to a random grouping, and robustness of around 59% against the applied noise. [ABSTRACT FROM AUTHOR]