Monthly Electricity Consumption Research Articles

Hybrid Cooling-Based Thermal Management of Containerised Vanadium Flow Battery Systems in Photovoltaic Applications

The integration of industrial batteries with photovoltaic applications is a common practice to charge the batteries using solar energy. Long-duration flow batteries are useful in dealing with the intermittency of renewable energy sources and offer a great opportunity for total fossil fuel replacement. In this study, the effects of different battery operation time and load profiles on the temperature dynamics of a containerised vanadium flow battery system are modelled and simulated for a range of locations and seasons to identify active cooling or heating requirements that might be needed to maintain safe operating temperatures. This paper explores and analyses the stack, tank, and container temperature dynamics of 6 h and 8 h containerised vanadium flow batteries (VFBs) during periods of higher charge and discharge current using computer simulations that apply insulation with passive or active hybrid cooling thermal management where needed to keep the battery temperature within a safe operating range under a range of climate conditions. According to the simulation results, when adopting the hybrid cooling strategy as described in the case study, for a 30 kW–240 kWh VFB system with ambient temperatures fluctuating between 25 °C and 45 °C, the monthly electricity consumption of the air conditioning system, calculated using average power, can be maintained at a relatively low level of approximately 330 kWh. By employing an air conditioning system with an airflow rate of 0.2 m3/s and a suitable thermal management strategy, it is sufficient to keep an 8 h system operating within a safe temperature range when the ambient temperature is between 15 °C and 35 °C. This study presents the first application of our previously developed containerised VFB thermodynamic model to explore the necessity of active cooling or heating in PV (photovoltaic) applications across different geographical locations and seasons. This analysis provides valuable insights for battery designers and manufacturers to understand the performance of containerised battery systems under various climate conditions. Furthermore, this paper is the first to apply this model for simulating 6 and 8 h batteries and to adopt a hybrid thermal management strategy. The simulation data offer guidance on whether active cooling or heating is required for industrialised vanadium batteries with capacities exceeding 6 h.

Does electricity price reduction bring a sustainable development of business: Evidence from fine-grained industrial electricity consumption data in China

This paper studies the impact of electricity price reduction policy on the economic activities and carbon emissions of different industries. Since 2018, the Chinese government has advocated reducing electricity price for industrial customers in order to alleviate the non-tax burden on businesses. Using monthly electricity consumption and user data from 2016 to 2019, we find that the electricity price reduction has significantly increased the industrial electricity consumption and users. Heterogeneity analyses show that the effect is greater in heavy polluted industries and industries in low and medium GDP regions. The results of threshold impact analysis show that the threshold value of heavy pollution industries was lower than that of general industry and commerce, while heavy pollution industries are more sensitive to electricity prices than general industries. Moreover, the reduction of electricity prices results in a higher percentage of carbon emissions growth in heavy pollution industries. Our result can also help the policymakers access the costs and benefits of electricity price reduction for industrial customers more accurately.

Assessment of Transport, Natural and Climatic Factors Influence on the Level of Electric Buses Energy Consumption in Urban Environment

The paper considers the issue of expanding the use of electric buses when transporting passengers on regular urban routes, which contribute to a significant reduction in the overall environmental pollution by road transport. Legislative actsconfirming the state support for the development of this industry are analyzed. The results of driving cycles of electric buses AKСM-E321 [AKSM-E321] and AKСM-E433 [AKSM-E433] in Minsk, electric buses ЛиАЗ-6274.00 [LiAZ-6274.00] and КАМАЗ-6282 [KAMAZ-6282] in Tyumen and Moscow are presented. The correlation of the specific average monthly electricity consumption and the average monthly ambient temperature is revealed. It has been established that for Moscow, the most significant factor influencing the electric bus power consumption are transport conditions. The ambient air temperature was identified as a key factor for the city of Tyumen. The research results make it possible to plan the use of electric buses on various urban routes based on runs without recharging. This may allow us to develop recommendations for the use of the studied brands of electric buses on routes of a certain length and complexity.

Time-Varying approaches for Long-Term Electric Load Forecasting under economic shocks

Long-term Load Forecasting (LTLF) plays a vital role in the planning of electric utilities. In the long run, utilities face various uncertainties caused by economic and environmental factors. These uncertainties have made LTLF more complex and inaccurate, thus, amplifying financial risks of utilities. A potent contributor to such losses in LTLF accuracy is economic shocks. This study proposes two probabilistic Time-Varying (TV) approaches to capture such shocks in LTLF and minimise accuracy loss, namely TV-XGB-X and TV-PR, and their combinations considering economic policy uncertainty. Both eXtreme Gradient Boosting (XGB) and Polynomial Regression (PR) are extended to include the long-run TV effects of economic shocks as eXogeneous predictors in this paper. These models and their combinations are compared with various non-TV approaches through experiments on the monthly electricity consumption of eight energy-intensive states in the United States. The results reveal that the proposed combined approaches outperform stand-alone models on all datasets. The findings of this study can help utilities in hedging financial risks under shocks.

Spatio-temporal Granularity Co-optimization Based Monthly Electricity Consumption Forecasting

Spatio-temporal Granularity Co-optimization Based Monthly Electricity Consumption Forecasting

УПРАВЛЕНИЕ ЭЛЕКТРОПОТРЕБЛЕНИЕМ ПРЕДПРИЯТИЯ ПО ПРОИЗВОДСТВУ МЕДИ

The paper considers the issues of managing the power consumption of an enterprise for the production of copper. The solution of these issues was carried out during the instrumental examination of the power supply system (SES) of the enterprise based on the results of a comprehensive energy audit. An analysis was made of the dynamics of electricity consumption for 2015-2018. It has been established that the uniformity of electricity consumption for production is maintained. The average monthly electricity consumption for 2017 was: for technology - 39,637 thousand kWh; for general shop expenses (general plant) - 6942 thou- sand kWh; in general, for production - 46579 thousand kWh. The total electricity consumption for production by product type is presented, taking into account the auxiliary consumption of all sections for the period 2015-2017. It was found that, compared with 2015, electricity consumption in 2017 for the most energy-intensive processes for electrolytic and blister copper and decreased by 6 % and 1.5 %, respectively, at the same time, an increase in consumption was observed for the production of technical sulfur, in 2016 by 7 %, in 2017 by 15 %...

DOWNLOAD PDF DOWNLOAD XML THE IMPACT OF SOLAR HOME SYSTEMS ON HOUSEHOLD ELECTRICITY CONSUMPTION IN RURAL BANGLADESH

This study examines the impact of Solar Home Systems (SHS) on household electricity consumption in rural Bangladesh using a quantitative cross-sectional design. A survey was conducted on 200 households in four rural districts selected based on their high proportion of households without access to grid electricity. Results showed that households with SHS had significantly higher monthly electricity consumption than those without SHS. The multiple linear regression analysis revealed a positive and significant impact of SHS ownership on household electricity consumption, after controlling for household income, size, education level of the household head, and access to grid electricity. The study highlights the potential of SHS to increase access to electricity and improve the quality of life in rural areas of Bangladesh. Keywords: Solar Home Systems, household electricity consumption, rural Bangladesh, energy access, renewable energy.

Decoupling based monthly net electricity consumption prediction model considering high penetration of distributed solar PV systems

The large-scale introduction of distributed photovoltaic (DPV) increases the need for retailers to consider and quantify the differences in monthly electricity consumption of customers to maximize their interests in trading in the forward electricity market. For customers with DPV, retailers need to predict net electricity consumption (NEC), which is actual electricity consumption (AEC) minus DPV generation. However, the DPV is behind the meter and DPV generation data is invisible to retailers. Therefore, the issue of how to distinguish the transition of customers from no DPV to with DPV and their DPV installation information needs to be addressed. To better capture the additions of DPV timely under high penetration of DPV, a decoupling-based monthly NEC prediction model considering the DPV installation update is proposed. Firstly, the features are extracted from the hourly NEC data of known customers with DPV to distinguish other customers whether installing DPV. Secondly, an online update framework of DPV installation evaluated by two validations is proposed. Thirdly, based on the difference in the electricity consumption series before and after the installation of DPV, the NEC is decoupled into AEC and DPV generation. Finally, the monthly DPV generation prediction results are subtracted from the monthly AEC prediction results to obtain the final monthly NEC results. Different scenarios of DPV penetration are set in case studies to test the performance between the proposed model and other direct models. The results indicate the superiority of the proposed method under high penetration of DPV.

Adaptive Optimal Greedy Clustering-Based Monthly Electricity Consumption Forecasting Method

Accurate monthly electricity consumption forecasting (MECF) is important for electricity retailers to mitigate trading risks in the electricity market. Clustering is commonly used to improve the accuracy of MECF. However, in the existing clustering-based forecasting methods, clustering and forecasting are independently performed and lack coordination, which limits the further improvement of forecasting accuracy. To address this issue, an adaptive optimal greedy clustering-based MECF method is proposed in this article. First, a metric of predictability is defined based on the goodness of fit and the cluster's average electricity consumption. Under a predefined number of clusters, the greedy clustering algorithm achieves the optimal division of individuals with the goal of maximizing predictability. Then, an adaptive method is designed to select the optimal number of clusters from a variety of clustering scenarios according to the prediction accuracy on the validation dataset. The effectiveness and superiority of the proposed method have been verified on a real-world dataset.

Environmental awareness and household energy saving of Chinese residents: Unity of knowing and doing or easier said than done?

Household energy saving is important for the realization of emission peak, carbon neutrality, and energy security goals in China. However, no conclusion has been reached on whether public environmental awareness can promote household energy saving. There are two major defects in previous studies. One is that they focus on the public intention to save energy rather than the real behavior; the other is that the endogenous problem caused by the measurement bias of environmental awareness is ignored. Based on China Family Panel Studies (CFPS) database, this study selects the change in average monthly household electricity charge and electricity consumption as the proxy variables of energy saving, and introduces the public perception level of social security and government corruption as the instrumental variable of environmental awareness. It is found that improvement of environmental awareness has statistical significance for household energy saving and there is still a lot of room for improvement. This conclusion keeps valid in several robustness tests. Further analysis shows that improvement of environmental awareness is more likely to promote energy saving in rural households, male household heads, and young people; and that education and income have a joint moderating effect on the energy saving effect of environmental awareness.

Can cash incentives modify groundwater pumping behaviors? Evidence from an experiment in Punjab

AbstractAs groundwater levels steadily decline in India, authorities are concerned about reducing extraction for irrigation purposes without jeopardizing food security. Very low or zero prices for electricity and water in agriculture is partly responsible for overextraction, but charging higher prices is politically not feasible. In this study, we describe the results of a pilot scheme implemented in Punjab, India, where farmers who enrolled were allocated a monthly entitlement of electricity units and compensated for unused electricity. Eight hours of uninterrupted daytime electricity supply were also provided under the scheme instead of the usual mix of daytime and night‐time supply. Analyzing data from a cross‐sectional farm household survey and instrumenting for enrollment, we find that self‐reported hours of irrigation for enrolled farmers were significantly lower than for non‐enrolled ones, with no impact on rice yields. We also find a reduction in monthly electricity consumption at electricity‐feeder level due to the pilot scheme using the synthetic control method. Our results suggest that the combination of daytime electricity provision and cash incentives for unused electricity has the potential to incentivize farmers to reduce electricity consumption and irrigation hours by at least 7.5% and up to 30% without impacting paddy yields.

Forecasting highly fluctuating electricity load using machine learning models based on multimillion observations

Dubai is an emerging metropolis with unique features, such as an extremely high expatriate ratio and turnover rate. These features, along with the extreme climatic conditions and dependency on energy-intensive water desalination, cause the electricity load to be high per capita and highly variable. Therefore, producing accurate electricity consumption predictions is critical to prevent blackouts or power loss, particularly for fast-growing cities. This study predicts the monthly electricity consumption in Dubai using various linear regression variants, support vector machines, decision tree models, ensemble models, and neural networks. The dataset consists of different demographic and climatic features as well as more than 50 million electricity consumption observations aggregated in monthly community-wide records. By analyzing the correlation between the various features and electricity consumption, a set of 18 factors was determined, with the number of expat sites, the total number of sites, and population identified as the most influential variables. The models examined were trained on the selected features, and their prediction performance was evaluated using various evaluation metrics. The results showed that the ensemble models were best in predicting consumption. Random forest outperformed the rest when trained using a temporally ordered dataset with 0.0437 and 0.0226 as root mean square error and mean absolute error values, respectively. In addition, the employment of a randomly split dataset resulted in better performance. Ensemble models were found to predict electricity consumption accurately when trained on 60% of the historical consumption records. The generalization and reliability of the top models were further tested by varying the training data volumes and applying rolling and moving cross-validation. Training the models on a fixed-size moving window of historical records leads to better performance and more reliable prediction.

Model of monthly electricity consumption of healthcare buildings based on climatological variables using PCA and linear regression

At this time, due to the global pandemic that has occurred, public administrations want to optimize resources and reduce greenhouse gases with more interest than before. It is the case of the Energy Regional Entity of the Junta de Castilla y León (Spain) that pursues the optimization of the energy consumption in particular of healthcare sector buildings. For this purpose, this work focuses on estimating electricity consumption for each month, for which different scenarios will be generated and the corresponding model is obtained for each scenario. This model has been developed considering the historical monthly data of consumption and climatic variables for the last 3 years. Electricity consumption in public sanitary buildings is related to their climatology, due to the use of air conditioning to adjust the indoor temperature. Subsequently, from the models obtained, the results will be analyzed. Significant differences have been observed in the estimation of electricity consumption with respect to the real data provided by the Junta de Castilla y León. The results obtained show how the availability of climatic variables increases the accuracy of the model obtained by about 30%.

A Comparative Study of Forecasting Electricity Consumption Using Machine Learning Models

Production of electricity from the burning of fossil fuels has caused an increase in the emission of greenhouse gases. In the long run, greenhouse gases cause harm to the environment. To reduce these gases, it is important to accurately forecast electricity production, supply and consumption. Forecasting of electricity consumption is, in particular, useful for minimizing problems of overproduction and oversupply of electricity. This research study focuses on forecasting electricity consumption based on time series data using different artificial intelligence and metaheuristic methods. The aim of the study is to determine which model among the artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), least squares support vector machines (LSSVMs) and fuzzy time series (FTS) produces the highest level of accuracy in forecasting electricity consumption. The variables considered in this research include the monthly electricity consumption over the years for different countries. The monthly electricity consumption data for seven countries, namely, Norway, Switzerland, Malaysia, Egypt, Algeria, Bulgaria and Kenya, for 10 years were used in this research. The performance of all of the models was evaluated and compared using error metrics such as the root mean squared error (RMSE), average forecasting error (AFE) and performance parameter (PP). The differences in the results obtained via the different methods are analyzed and discussed, and it is shown that the different models performed better for different countries in different forecasting periods. Overall, it was found that the FTS model performed the best for most of the countries studied compared to the other three models. The research results can allow electricity management companies to have better strategic planning when deciding on the optimal levels of electricity production and supply, with the overall aim of preventing surpluses or shortages in the electricity supply.

Data-driven random forest forecasting method of monthly electricity consumption

Data-driven random forest forecasting method of monthly electricity consumption

Development of an Efficient Electricity Consumption Prediction Model using Machine Learning Techniques

Electricity consumption has continued to go up rapidly to follow the rapid growth of the economy. Therefore, detecting anomalies in buildings' energy data is considered one of the most essential techniques to detect anomalous events in buildings. This paper aims to optimize the electricity consumption in households by forecasting the consumption of these households and, consequently, identifying the anomalies. Further, as the used dataset is huge and published publicly, many research used part of it based on their needs. In this paper, the dataset is grouped as daily consumption and monthly consumption to compare the network topologies of all other works that used the same dataset with the selected part. The proposed methodology will depend basically on long short-term memory (LSTM) because it is powerful, flexible, and can deal with complex multi-dimensional time-series data. The results of the model can accurately predict the future consumption of individual households in a daily or monthly consumption base, even if the household was not included in the original training set. The proposed daily model achieves Root Mean Square Error (RMSE) value of 0.362 and mean absolute error (MAE) of 19.7%, while the monthly model achieves an RMSE value of 0.376 and MAE of 17.8%. Our model got the lowest accuracy result when compared with other compared network topologies. The lowest RMSE achieved from other topologies is 0.37 and the lowest MAE is 18% where our model achieved RMSE of 0.362 and MAE of 17.8%. Further, the model can detect the anomalies efficiently in both daily electricity consumption data and monthly electricity consumption data. However, the daily electricity consumption readings are way better to detect anomalies than the monthly electricity consumption readings because of the different picks that appear in the daily consumption data.

Non-technical losses detection in power system

The digitization of distribution networks enables the collection of big data from which it is necessary to draw conclusions and detect anomalies among electricity consumers. This paper explains methodologies to detect non-technical losses, commercial losses, and electricity theft. Based on monthly electricity consumption measurements, possible and prevalent cases of anomalies and theft among consumers are identified. Indicators that can detect anomalies have been proposed for such types of load diagrams. The sensitivity of the indicators to different types of consumers was analyzed. The applicability of this methodology was examined for a set of real measurements, and its advantages were pointed out. This concept represents a good recommendation, as it is possible to observe and detect irregularities in electricity consumption.

Machine Learning Empowered Electricity Consumption Prediction

Electricity, being the most efficient secondary energy, contributes for a larger proportion of overall energy usage. Due to a lack of storage for energy resources, over supply will result in energy dissipation and substantial investment waste. Accurate electricity consumption prediction is vital because it allows for the preparation of potential power generation systems to satisfy the growing demands for electrical energy as well as: smart distributed grids, assessing the degree of socioeconomic growth, distributed system design, tariff plans, demand-side management, power generation planning, and providing electricity supply stability by balancing the amount of electricity produced and consumed. This paper proposes a medium-term prediction model that can predict electricity consumption for a given location in Saudi Arabia. Hence, this study implemented a standalone Artificial Neural Network (ANN) model and bagging ensemble for predicting total monthly electricity consumption in 18 locations across Saudi Arabia. The dataset used in this research is gathered exclusively from the Saudi Electric Company. The pre-processing phase included normalizing the data using min-max method and mapping the cyclical attribute to its sine and cosine facets. The number of neurons and learning rate of the standalone model were optimized using hyperparameter tuning. Finally, the standalone model was tested against the bagging ensemble using the optimized ANN. The bagging ensemble with an optimized ANN as the chosen classifier outperformed the standalone ANN model. The results for the proposed model produced 0.9116 Correlation Coefficient (CC), 0.2836 Mean Absolute Percentage Error (MAPE), 0.4578, Root Mean Squared Percentage Error (RMSPE), 0.0298 MAE, and 0.069 Root Mean Squared Error (RMSE), respectively.

Electricity consumption forecasting based on ensemble deep learning with application to the Algerian market

The economic sector is one of the most important pillars of countries. Economic activities of industry are intimately linked with the ability to meet their needs for electricity. Therefore, electricity forecasting is a very important task. It allows for better planning and management of energy resources. Several methods have been proposed to forecast energy consumption. In this work, to predict monthly electricity consumption for the economic sector, we develop a novel approach based on ensemble learning. Our approach combines three models that proved successful in the field, namely: Long Short Term Memory and Gated Recurrent Unit neural networks, and Temporal Convolutional Networks. The experiments have been conducted with almost 2000 clients and 14 years of monthly electricity consumption from Bejaia, Algeria. The results show that the proposed ensemble models achieve better performance than both the company's requirements and the prediction of the traditional individual models. Finally, statistical tests have been carried out to prove that significance of the ensemble models developed.

Evaluation of the economic viability of grid-connected photovoltaic systems in different Brazilian regions

This study aimed at the dimensioning and economic analysis of grid-connected photovoltaic systems in different cities in Brazil. As a criterion for the selection of the cities of interest, it was considered the capital with the highest number of residences in each of the five regions of the country, as well as the city where the authors are established, namely the cities of Salvador, Manaus, Goiânia, São Paulo, Curitiba, and Cascavel. Based on local characteristics and adopting an average monthly electricity consumption of 400 kWh, was developed the dimensioning of the photovoltaic systems, adopting the methodology presented by Pinho and Galdino (2014). Based on the components determined for the systems, budgets were made to enable their implementation. The investments to be made varied between US$ 4,682.97 and US$ 5,326.06. From these values, economic analyses were made using the discounted payback method. The projects presented different payback times, with the shortest payback time to the city of Manaus, with 9 years and the longest in the city of Curitiba, with 15 years. Therefore, it was confirmed the research hypothesis that the regional characteristics linked to the dimensioning of the photovoltaic systems directly affect the time of return on investment.