Hourly Electricity Consumption Research Articles

Applying neural networks for short and long-term hourly electricity consumption forecasting in universities: A simultaneous approach for energy management

Predictive models for energy consumption are increasingly relevant for buildings with medium-high demands, such as public buildings. These models enable effective energy management, especially in contexts of budget constraints, maximizing resource efficiency. Thus, university buildings are interesting cases because they meet the above-mentioned conditions, they can be managed by the public or private sector and have high societal impact. This work aims to simultaneously develop two predictive models for hourly electricity demand in a university building: one for the short-term (next hour) and one for the long-term (all hours of the year). The methodology consists in: analyzing the data using descriptive statistics to identify relevant variables; building the neural network models in Python; and evaluating them with performance indicators. The short-term model, which includes the previous hour's energy as independent variable, achieved a relative error of 16.0 %, an R2 = 91.17, RMSE = 0.512 kWh, and MAE = 0.325 kWh. The long-term model, which omits this variable, showed a relative error of 31.7 %, R2 = 74.69, RMSE = 0.864 kWh, and MAE = 0.566 kWh. The study highlights the effectiveness of neural networks in energy forecasting. It also emphasizes the importance of using the previous hour's energy as a variable to obtain short-term accuracy; but also the possibility of building models without it, allowing for long-term approaches. The novelty lies in the simultaneous approach of two predictive horizons in a university building. This approach can contribute by providing accurate information to energy control algorithms that integrate renewable energy, storage, grid power, etc., to optimize the use of resources and improving environmental sustainability.

Changes in hourly electricity consumption profiles and price elasticities in Denmark 2019–2022

Changes in consumption profiles affect the need for investments in production and grid capacities. Extending a model with categorical variables for hours of the day, months and types of days to include short-term electricity prices, and applying Danish data for the hourly electricity consumption by aggregated categories of customers, consumption profiles for each of the years from 2019 to 2022 are estimated and it is tested if the profiles change significantly. Further, the short-term price elasticity of hourly electricity demand is estimated. During the first COVID-19 lockdown, residential electricity consumption increased and non-residential consumption decreased and the residential consumption profile on weekdays resembles the weekend profile. However, long-term effects are quite limited. For 2022, the residential consumption profile is significantly different from the profile in 2019. The profile has become flatter, increasing consumption during the night and reducing consumption during the daytime. An increasing number of electric vehicles and individual heat pumps contribute to this change. The short-term price elasticity for total electricity consumption increased in 2022. Especially, the price elasticity for residential customers increased and became significant in the second half of 2022 where electricity prices were high and volatile and customers were aware of prices.

Model-based analysis to identify the impact of factors affecting electricity gaps during COVID-19: A case study in Germany

The recent COVID-19 pandemic has precipitated drastic changes in economic and lifestyle conditions, significantly altering residual electricity demand behavior. This alteration has expanded the demand gap between actual and forecasted electricity usage based on pre-pandemic data, highlighting a critical global issue. Many studies in the pandemic have explored the features of this widening gap, which is impacted by major social events like fast virus spread and lockdowns. However, the influence of factors like economic shifts and lifestyle changes on this demand remains largely unexplored, primarily due to the pandemic's significant effects in these areas. Understanding the essential factors affecting the demand gap is crucial for stakeholders in the electricity sector to develop effective strategies. This study examines the hourly electricity consumption and related factors during the specified period. We present a method combining time-series forecasting and sparse modeling. This helps identify critical factors affecting the electricity demand gap during the pandemic, highlighting the most crucial variables. Utilizing this method, we identify the variables that have undergone significant changes during the pandemic and evaluate their effects on the electricity demand gap. The effectiveness is proven by applying it to the dataset collected in German.

An Overview of Electricity Consumption in Europe: Models for Prediction of the Electricity Usage for Heating and Cooling

Although aggregate electricity consumption provides valuable information for market analysis, demand composition, including industrial, residential, illumination, and other uses, and special days, such as national or religious holidays and annual industrial shutdowns, differ for each country. This paper analyzes the hourly electricity consumption of European countries in the European Transmission System Operation for Electricity (ENTSO-E) grid from 2006 to 2018. We propose an outlier detection method to identify special days and a modulated Fourier Series Expansion model to determine the breakdown of industrial versus household consumption and heating versus cooling consumption. The proposed outlier detection method uses the time series for each hour and checks whether a day has more than a threshold number of hours with exceptional electricity consumption levels. The proposed demand prediction model has a 3% average error when electricity usage for heating is not dominant. It also allows country classification based on consumption patterns to efficiently manage regional or country-based electricity markets.

Development and Verification of a Regional Residential Electricity Consumption Estimation Method

In pursuing Japan’s target of net zero greenhouse gas (GHG) emissions by 2050, decarbonization strategies at the regional level have been taking place nationally. Some successes have been achieved in the residential sector in achieving decarbonization at the regional level due to improvements in the advancement of energy-saving technologies. An important prerequisite to achieving further decarbonization in the residential sector is understanding household electricity consumption of power demand objects. This study constructed a method for predicting residential electricity consumption in a case study region. First, we set up six models of household composition for scenario exercises. Then, we used the residential energy estimation based on daily activities (REEDA) method to calculate the hourly electricity consumption of each household composition in the four seasons based on the duration of daily life activity. Finally, we separately explore the impact of housing performance (insulation, airtightness), air-conditioning patterns (intermittent operation method in a habitable room/continuous operation method in a habitable room/continuous operation method in all rooms), and geographical location on residential air conditional electricity consumption. The output is a regional residential energy estimate method that can consider multiple key variables. We verified the developed model by (1) comparing the estimated output with the Japan Energy Database and (2) testing the method for various residential areas in Japan. The results showed an accuracy level greater than 75% and nationwide applicability.

Electricity consumption simulation using random coefficient periodic autoregressive model

The concept of a continuous-time conditional linear random process involves a random kernel being integrated stochastically by a process with independent increments, which is often called a “generative process”. In cases where the “generative process” is Poisson, the resulting model represents an investigated signal as a sum of numerous stochastically dependent random impulses each of which occurs according to some inhomogeneous Poisson arrival process. This model can be applied to represent various processes related to energy consumption, such as electricity loads of electrical power systems, gas and water consumption, and other energy resources, while also considering the signals’ cyclostationarity, which is usually caused by the rhythmic nature of consumer behaviour. A member of the discretetime conditional linear cyclostationary random processes class is the random coefficient periodic autoregressive (RCPAR) model, which is appropriate for use in energy informatics, including estimation, forecasting, and computer simulation purposes. The primary objective of the paper is to establish a procedure for simulating the hourly electricity consumption of small and medium-sized enterprises using the RCPAR model, which has periodic parameters and creates cyclostationary properties while also accounting for the investigated process conditional heteroscedasticity. The statistical estimation step of the proposed procedure uses the general methodology for estimating the parameters of the RCPAR model and the methods of statistical analysis of cyclostationary signals. This step is used to identify the simulation characteristics. The simulation step is based on the methods of cyclostationary white noise generation and its transformation by a digital linear filter with random parameters. The last ones are obtained using the Gaussian random vectors computer simulation methods, taking into account the cyclostaionarity property.

Improving the accuracy of multi-step prediction of building energy consumption based on EEMD-PSO-Informer and long-time series

Accurate multi-step forecasting of building energy consumption is an essential tool for effective planning and plays a vital role in building energy management systems. With the advent of big data, many artificial intelligence techniques require long time series to predict multi-step energy consumption. However, energy consumption data of buildings are often nonlinear and non-stationary in the state as well as considerable period, making model prediction more difficult. In this research, we propose a hybrid algorithm that combines the ensemble empirical modal decomposition (EEMD) and informer, where the parameters of the informer are optimized by the particle swarm optimization algorithm (PSO). At the beginning of our improved method, we use EEMD to break down the raw data into several intrinsic mode functions(IMF) components. Informer is then used to make predictions, and PSO is used to tune hyper-parameters during prediction. In the final step, the final prediction result is obtained by combining the prediction results of all IMF components. The hourly electricity consumption of five buildings in the BDG2 dataset is used to evaluate the effectiveness of the proposed method. Five existing models are compared with this method and evaluated by different performance metrics. From the perspective of five cases, the accuracy rate has increased by up to 78.68% compared with the existing methods. Compared with the original model, the accuracy rate has increased by up to 56.11%.

Feature extraction and an interpretable hierarchical model for annual hourly electricity consumption profile of commercial buildings in China

Understanding and modeling building electricity consumption is paramount for demand-side decarbonization. Using a data-driven approach, this study proposes a hierarchical model to generate annual hourly electricity consumption profiles for commercial buildings, to facilitate energy system design and renewable energy integration. Electricity consumption profiles and the corresponding weather data from 55 commercial buildings across all five climate zones in China were collected to address the scarcity of relevant open datasets. Furthermore, periodicity and correlation analyses of the collected dataset indicate that the annual electricity consumption profiles can be decomposed into daily fluctuations primarily influenced by climate change and intra-day fluctuations, which are predominantly affected by building schedules. Based on these features, suitable algorithms were selected to address the issues independently in these two temporal paradigms, forming a hierarchical model. A regression tree was used to reveal the relationships between daily consumption and weather data as well as the climate zone label. Additionally, k-means clustering was employed to extract typical intra-day consumption patterns, followed by the deployment of a classification tree to predict intra-day pattern labels under specific conditions. In the cross-validation, the proposed hierarchical model achieved a high coefficient of determination (R2) of 0.941, which further improved to 0.949 after incorporating residual regression, demonstrating its high accuracy. Compared to the single-step gradient boosting decision tree (GBDT) model (R2 = 0.951), the proposed hierarchical model exhibited comparable accuracy and offered better interpretability and lower overall complexity, making it a favorable choice for engineering applications. This study provides insights into the development of a data-driven model for building electricity consumption profiles.

Energy and Economic Analysis of a Hydroelectric Power Plant: A Case Study

In this study, the electricity production and energy costs of hydroelectric power plant is analyzed by using actual power plants data. Using long term actual data, the capacity utilization rates of the hydroelectric power plant were estimated on an hourly basis. Economic analysis of the power plant and factors affecting the energy production costs (initial investment cost, operating-maintenance costs, etc.) were researched and the energy production costs of the power plant were assessed in detail. Additionally, for the first time in this study, a dimensionless number was defined to denote the variation of electricity consumption in the country on an hourly, monthly and yearly basis. This number was called the hourly electricity consumption coefficient (HECC). A detailed investigation of the electricity consumption in Turkey was analyzed.

Demand-Side Regulation Provision of Virtual Power Plants Consisting of Interconnected Microgrids Through Double-Stage Double-Layer Optimization

This study proposes a double-stage double-layer optimization model for a virtual power plant (VPP) consisting of interconnected microgrids (IMGs) with integrated renewable energy sources (RESs) and energy storage systems (ESSs) to realize demand-side ancillary service, considering intra energy sharing among the IMGs within the VPP. In particular, the first stage, day-ahead scheduling, is carried out to predict the hourly electricity consumption baseline and regulation capacity for the next day, the latter of which results in a reward from the market operator. In the second stage, real-time power consumption control is performed by following the dynamic regulation (or RegD) signal. The second stage is further divided into two layers: the upper layer distributes demand response (DR) signals from the main grid according to the electricity unit price of each microgrid (MG) and exchanges electricity among MGs based on a new energy sharing mechanism to reduce RegD-following violations. The lower layer performs real-time power consumption control for each MG to minimize operation costs. The overall goal is to maximize the reward in the day-ahead stage and minimize the RegD-following violation penalty in the real-time stage, so as to minimize the overall operation cost of the VPP. The optimization is written in five objective functions, which are solved using mixed integer linear programming (MILP) in Gurobisolvers. Extensive simulation and comparison studies are carried out, and numerical results show that compared with traditional MG operations, VPPs comprised of IMGs can reduce operation costs and provide better frequency support for the grid through superior RegD signal following performances.

Optimum hybrid renewable energy system design for on and off grid buildings: Hotel, education and animal hospital building case

Optimum design of hybrid renewable systems is essential for the efficient utilization of the renewable sources and uninterruptible energy supply. The size and backup capacity of the system are effected by the hourly energy demand profile of the building.In this study, optimal design of PV/wind/battery/diesel hybrid renewable energy system (HRES) for the electrification of a hotel building (HB), education building and animal hospital (AH) for on and off grid cases are evaluated to compare buildings with different demand profiles. The hourly electricity consumption of the buildings is measured during January 2023. Nonlinear swarm optimization algorithm was used to minimize the system cost of electricity (COE) and maximize the renewable fraction.Optimal off-grid HRES found to include PV and wind turbine together. AH represented the most stable and highest hourly demand which resulted in minimum COE (0.18 $/kWh and 0.321 $/kWh) for on and off grids.Then annual electricity consumptions of the buildings are equalized to compare buildings with the same annual but different hourly load. On-grid HB found to have minimum COE (0.177 $/kWh) due to the closer hourly demand profile on weekends and weekdays then other buildings. Therefore, on-grid HRES configurations are found to be more cost effective in buildings utilized seven days of the week. However, in off-grid case minimum COE (0.321 $/kWh) was obtained for AH and maximum was found for HB which was due to the peak demands. The result shows that buildings with sudden increases require high battery capacity which results in high COE.

Solar Self-Sufficient Households as a Driving Factor for Sustainability Transformation

We present a model to estimate the technical requirements, including the photovoltaic area and battery capacity, along with the costs, for a four-person household to be 100% electrically self-sufficient in Germany. We model the hourly electricity consumption of private households with quasi-Fourier series and an autoregressive statistical model based on data from Berlin in 2010. Combining the consumption model and remote-sensed hourly solar irradiance data from the ERA5 data set, we find the optimal photovoltaic area and battery capacity that would have been necessary to be self-sufficient in electricity from July 2002 to June 2022. We show that it is possible to build a self-sufficient household with today’s storage technology for private households and estimate the costs expected to do so.

Comparative study of continuous hourly energy consumption forecasting strategies with small data sets to support demand management decisions in buildings

AbstractBuildings are one of the largest consumers of electrical energy, making it important to develop different strategies to help to reduce electricity consumption. Building energy consumption forecasting strategies are widely used to support demand management decisions, but these strategies require large data sets to achieve an accurate electric consumption forecast, so they are not commonly used for buildings with a short history of record keeping. Based on this, the objective of this study is to determine, through continuous hourly electricity consumption forecasting strategies, the amount of data needed to achieve an accurate forecast. The proposed forecasting strategies were evaluated with Random Forest, eXtreme Gradient Boost, Convolutional Neural Network, and Temporal Convolutional Network algorithms using 4 years of electricity consumption data from two buildings located on the campus of the University of Valladolid. For performance evaluation, two scenarios were proposed for each of the proposed forecasting strategies. The results showed that for forecasting horizons of 1 week, it was possible to obtain a mean absolute percentage error (MAPE) below 7% for Building 1 and a MAPE below 10% for Building 2 with 6 months of data, while for a forecast horizon of 1 month, it was possible to obtain a MAPE below 10% for Building 1 and below 11% for Building 2 with 10 months of data. However, if the distribution of the data captured in the buildings does not undergo sudden changes, the decision tree algorithms obtain better results. However, if there are sudden changes, deep learning algorithms are a better choice.

A Novel Stochastic Model for Hourly Electricity Load Profile Analysis of Rural Districts in Fujian, China

Renewable energy is important for achieving carbon neutralization. However, power generation from renewable energy sources can be uncertain and uncontrollable. Therefore, understanding the features of energy demand is pivotal for integrating renewable energy sources and storage systems within the entire energy network. Traditional load profiles are depicted by fixed typical load curves, which cannot support detailed dynamic simulations of annual hourly electricity consumption. Here, a novel stochastic model for hourly electricity load profile analysis is proposed. A clustering-based model of hourly load was constructed to depict load profiles of typical days, while a non-linear regression method determined the temperature-related factors within annual daily load consumptions, based on which a stochastic simulation model was established for hourly electricity load profiles. The model’s performance was tested with electricity data of rural districts in Fujian Province, China. The proposed model achieved a coefficient of variation of the mean absolute error of 15.7%, which was significantly lower than that of the traditional model. Further, a simplified case was employed to analyze the application of the proposed stochastic model in the design of energy storage systems. The proposed method enables the optimal design of integrated energy networks with renewable energy sources and energy storage systems.

Forecasting of Electrical Energy Consumption in Slovakia

Prediction of electricity energy consumption plays a crucial role in the electric power industry. Accurate forecasting is essential for electricity supply policies. A characteristic feature of electrical energy is the need to ensure a constant balance between consumption and electricity production, whereas electricity cannot be stored in significant quantities, nor is it easy to transport. Electricity consumption generally has a stochastic behavior that makes it hard to predict. The main goal of this study is to propose the forecasting models to predict the maximum hourly electricity consumption per day that is more accurate than the official load prediction of the Slovak Distribution Company. Different models are proposed and compared. The first model group is based on the transverse set of Grey models and Nonlinear Grey Bernoulli models and the second approach is based on a multi-layer feed-forward back-propagation network. Moreover, a new potential hybrid model combining these different approaches is used to forecast the maximum hourly electricity consumption per day. Various performance metrics are adopted to evaluate the performance and effectiveness of models. All the proposed models achieved more accurate predictions than the official load prediction, while the hybrid model offered the best results according to performance metrics and supported the legitimacy of this research.

Data-driven assessment of room air conditioner efficiency for saving energy

Room air conditioners (RACs) are one of the high energy-consuming home appliances. Developing a smart solution to evaluate and track the efficiency of RACs is essentially useful for residents to make necessary maintenance or replacement decisions. While smart meters are increasingly installed to monitor electricity use, the application of smart meter data to evaluate the RAC efficiency remains inadequate. In this paper, we present a data-driven framework to identify non-inverter window RACs with low energy efficiency by analyzing smart meter data from the university student hall rooms. In this framework, we first applied the extreme gradient boosting (XGBoost) method to predict a RAC's hourly electricity consumption. Then we measured the effect of outdoor temperature on the XGBoost prediction of hourly RAC electricity consumption using the Shapley Additive Explanation method to interpret the RAC's efficiency. We conjectured that the RAC efficiency is normal if the predicted hourly electricity consumption is significantly correlated with the outdoor temperature. In contrast, the RAC efficiency is low if the outdoor temperature changes have little impact on the predicted electricity consumption. Finally, we applied the K-Means clustering algorithm to separate the RACs into the “low efficiency” and “normal efficiency” categories based on each's pattern of outdoor temperature's impact on electricity consumption. Our cross-validation result showed that the XGBoost model can achieve an average R2 score of 0.50 and an average root mean squared error of 0.20 kWh. We used RAC replacement records to validate our framework of interpreting the RAC's efficiency. On average, RACs having low efficiency consumed 25.69% more electricity per hour. Overall, our data-driven framework can contribute to extending the value of smart meters for RAC efficiency evaluation. Meanwhile, the smart meter data-driven framework can be improved, and more validation is needed in the future.

Исследование факторов, влияющих на потребление электроэнергии коммерческим предприятием

This work is devoted to an important issue that concerns the analysis of the behavior of an individual participant in the electric power system in order to further predict this behavior. To do this, we used data on the hourly electricity consumption of the shopping center. In addition to them, data sets of ambient temperature and time were additionally used. The analysis carried out will be further used in building a model for predicting the consumption of electrical energy by a separate object of the energy system to improve the interaction between the consumer and the supplier of electrical energy.

Stacking Machine Learning Models to Forecast Hourly and Daily Electricity Consumption of Household Using Internet of Things

The objective of this paper is to design an efficient electricity consumption forecasting model using stacking ensemble technique and Internet of Things (IoT). Two stage process is applied in this paper. In the first stage, fifteen forecasting models (Auto-ARIMA, Holt-Winter (Additive), Exponential, Facebook Prophet, Light Gradient Boosting, AdaBoost, Support Vector Regression, Decision Tree, Extra Tree, Random Forest, Elastic net, K-Nearest Neighbour’s, XGBoost, Linear Regression, Long Short Term Memory) are applied to forecast electricity consumption at an hourly and daily level. In the next stage, the best four models are selected and stacked. We have considered the dataset of energy consumption by electrical appliances per minute in a house over seven days. The models are evaluated using root mean square error (RMSE), mean absolute error (MAE), R-square, and mean absolute percentage error (MAPE). The results show that the extra tree performed better among all the algorithms, and stacking further improves performance. Elastic net and decision tree algorithms have taken less time as compared to other models applied in this study.

Electricity Consumption Forecasting Based on a Bidirectional Long-Short-Term Memory Artificial Neural Network

The accurate forecasting of the hourly month-ahead electricity consumption represents a very important aspect for non-household electricity consumers and system operators, and at the same time represents a key factor in what regards energy efficiency and achieving sustainable economic, business, and management operations. In this context, we have devised, developed, and validated within the paper an hourly month ahead electricity consumption forecasting method. This method is based on a bidirectional long-short-term memory (BiLSTM) artificial neural network (ANN) enhanced with a multiple simultaneously decreasing delays approach coupled with function fitting neural networks (FITNETs). The developed method targets the hourly month-ahead total electricity consumption at the level of a commercial center-type consumer and for the hourly month ahead consumption of its refrigerator storage room. The developed approach offers excellent forecasting results, highlighted by the validation stage’s results along with the registered performance metrics, namely 0.0495 for the root mean square error (RMSE) performance metric for the total hourly month-ahead electricity consumption and 0.0284 for the refrigerator storage room. We aimed for and managed to attain an hourly month-ahead consumed electricity prediction without experiencing a significant drop in the forecasting accuracy that usually tends to occur after the first two weeks, therefore achieving a reliable method that satisfies the contractor’s needs, being able to enhance his/her activity from the economic, business, and management perspectives. Even if the devised, developed, and validated forecasting solution for the hourly consumption targets a commercial center-type consumer, based on its accuracy, this solution can also represent a useful tool for other non-household electricity consumers due to its generalization capability.

Electricity Technological Mix Forecasting for Life Cycle Assessment Aware Scheduling

Here we show the possibility to forecast the hourly day-ahead electricity consumption mix exploiting a deep learning model. Thus, in the context of the proposed life cycle assessment (LCA) aware scheduling framework, a production scheduling could be optimized to adapt its load profile in those hours that are predicted to have a lower environmental impact. The objective functions of the optimization would therefore be the LCA impacts of the consumed electricity mix. The increase in detail in the accounting can also be exploited to complement the life cycle inventory, allowing the overall assessment to be more adherent to reality.