Forecasting of Turkey's net electricity energy consumption on sectoral bases

In this study forecast of Turkey's net electricity energy consumption on sectoral basis until 2020 is explored. Artificial neural networks (ANN) is preferred as forecasting tool. The reasons behind choosing ANN are the ability of ANN to forecast future values of more than one variable at the same time and to model the nonlinear relation in the data structure. Founded forecast results by ANN are compared with official forecasts.     

Modeling of electricity consumption in the Asian gaming and tourism center—Macao SAR,People's Republic of China

The use of electricity is indispensable to modern life. As Macao Special Administrative Region becomes a gaming and tourism center in Asia, modeling the consumption of electricity is critical to Macao's economic development. The purposes of this paper are to conduct an extensive literature review on modeling of electricity consumption, and to identify key climatic, demographic, economic and/or industrial factors that may affect the electricity consumption of a country/city. It was identified that the five factors, namely temperature, population, the number of tourists, hotel room occupancy and days per month, could be used to characterize Macao's monthly electricity consumption. Three selected approaches including multiple regression, artificial neural network (ANN) and wavelet ANN were used to derive mathematical models of the electricity consumption. The accuracy of these models was assessed by using the mean squared error (MSE), the mean squared percentage error (MSPE) and the mean absolute percentage error (MAPE). The error analysis shows that wavelet ANN has a very promising forecasting capability and can reveal the periodicity of electricity consumption.     

Determinants of household energy consumption in India

Improving access to affordable modern energy is critical to improving living standards in the developing world. Rural households in India, in particular, are almost entirely reliant on traditional biomass for their basic cooking energy needs. This has adverse effects on their health and productivity, and also causes environmental degradation. This study presents a new generic modelling approach, with a focus on cooking fuel choices, and explores response strategies for energy poverty eradication in India. The modelling approach analyzes the determinants of fuel consumption choices for heterogeneous household groups, incorporating the effect of income distributions and traditionally more intangible factors such as preferences and private discount rates. The methodology is used to develop alternate future scenarios that explore how different policy mechanisms such as fuel subsidies and micro-financing can enhance the diffusion of modern, more efficient, energy sources in India.     

基于小波变换与Elman神经网络的短期风速组合预测

风速的准确预测对风电场发电系统的经济和安全运行有着重要的作用。为了克服风速随机性强的缺点,提高短期风速预测的精度,提出了一种将小波变换与Elman神经网络相结合的短期风速组合预测模型。该模型由小波预处理模块和神经网络预测模块组成。首先利用小波预处理模块将风速序列作多尺度分解,重构得到不同频段的子序列,然后利用Elman神经网络模块分别对其训练和预测。实际风速预测结果表明,与单一的Elman和ARMA法相比,该组合预测模型的预测精度有较大的改善,可以用于风电场短期风速的预测。     

Residential electricity consumption in Portugal: Findings from top-down and bottom-up models

An econometric study of the Portuguese residential electricity consumption is presented, with a focus on the influence of dwelling characteristics on consumption. The relationship between the dwelling and household characteristics on per capita residential electricity consumption is estimated at two different scales, involving two distinct databases: the first includes data at the municipality level for 2001, the second is the most recent Portuguese consumer expenditure survey that was collected in 2005 and 2006. The results of the analysis at both scales are consistent and indicate that household and dwelling characteristics have a significant influence on residential electricity consumption. Our results show that in Portugal the direct effect of income on electricity consumption is low and becomes smaller when more relevant control variables are included in the analysis. Future demand of electricity in Portugal will be significantly influenced by trends in socioeconomic factors as well as changes in the building stock. These trends should be taken in consideration in the formulation of policy measures to reduce electricity consumption.     

Understanding household energy consumption patterns: When “West Is Best” in Metro Manila

This paper addresses the topic of energy and development through a multi-disciplinary and systemic approach that combines environmental considerations with a social understanding of consumption. The focus is on electricity usage in the home and specifically lighting and cooling. Set in the urban mega-polis of Metro Manila, the Philippines, energy consumption is first placed in its biophysical perspective: the energy sources and electricity grid are presented, in relation to the Philippines as well as the region. The research findings then explore the social and cultural drivers behind household electricity consumption, revealing in several examples the strong influence of globalization—understood here as the flow of people, remittances, images and ideas. Policy recommendations are provided, based on the research results, with concluding remarks relevant to other similar contexts.     

Measurements of household electricity and domestic hot water use in dwellings and the effect of different monitoring time resolution

The use of household electricity and domestic hot water has been measured for 72 apartments in an apartment building located in the south of Sweden. The measurements were carried out with samples every 6 s, a tenfold increase in resolution compared to available published data, during a measurement period of five days, in the winter season, including a weekend. The influence of the time resolution on the distribution of data was analysed by integrating the 6 s data to represent longer logging intervals. Extreme values, especially the high values, are shown to be reduced if the time interval is increased. The maximum household electric power was 50% higher at a 6 s resolution compared to 60 s and the corresponding difference for domestic hot water flow was 40%. Daily variations has to be considered for photovoltaic installations and solar thermal collectors, energy simulations of buildings need at least hourly data and all kind of power design in a building or its services benefits from much more resolved data.     

Price sensitivity of residential energy consumption in Norway

The main aim of this paper is to test the stability of the results of a model which focus on the relationship between the choice of heating equipment and the residential energy consumption. The results for the income and energy price variables are of special interest. Stability in the time dimension is tested by applying the model on micro data for each of the years 1993–1995. The parameter estimates are stable within a 95% confidence interval. However, the estimated impact of the energy price variable on energy consumption was considerably weaker in 1994 than in 1993 and 1995. The results for two different income groups in the pooled data set are also subject to stability testing. The energy price sensitivity in residential energy consumption is found to be higher for high-income households than for low-income households.     

Dynamics of productivity change in the Australian electricity industry: Assessing the impacts of electricity reform

The Australian electricity industry has undergone a significant reform, since the mid-1990s. Key changes comprised functional unbundling, market restructuring, regulatory reform, public corporatisation and privatisation. Technological development has been another indisputable constituent of these changes, in the wake of ICT revolution. The principle rationale behind these changes has been that they would improve productivity of the industry and social well-being of people. This paper examines the dynamics of productivity changes in the Australian electricity industry and conducts several hypotheses-testings to identify whether industry's efficiency measures are truly improved as a result of the reform-driven changes. Malmquist Total Factor Productivity Index approach and ANOVA are used for this purpose. The results reveal that the productivity gains in the industry have been largely driven by technological improvements and, to a lesser extent, by reform-induced comparative efficiency gains. On average at national level and for the entire industry, there are efficiency gains that, to large extents, can be attributed to functional unbundling and public corporatisation and, to a lesser extent, to market restructuring and privatisation. The results, however, reveal that the reform-driven changes have made insignificant contribution to comparative efficiency, at the level of thermal generation.     

证据理论融合蚁群神经网络的短期负荷组合预测

为提高短期负荷预测的精度,引入了证据理论融合蚁群神经网络的组合预测方法,根据重庆市负荷的实际数据,采用蚁群神经网络作为单一模型对其进行初步预测,由BP神经网络对预测误差及主要外界影响因素进行分析建模,获得了每个模型的可信度,并用证据理论对可信度进行合成得到组合权值,进而实现对短期电力负荷的组合预测。结果表明,该方法拟合误差小、预测精度高,具有一定的应用价值。     

The impact of household consumption on energy use and CO2 emissions in China

In this paper, the consumer lifestyle approach is applied to analyze the impact of consumption by urban and rural households on energy use and CO₂ emissions for different regions and income levels in China. Grey Model is used to compare the relationship between energy consumption, consumption expenditure and CO₂ emissions for different lifestyles. The results show that direct energy consumption is diverse for urban households and simple for rural households in China. Direct energy consumption and CO₂ emissions are increasing faster for urban than for rural households. Indirect energy consumption and CO₂ emissions for urban households are much greater than the direct consumption values. The total indirect energy consumption and CO₂ emissions differ by regions and the structures are different, but the latter differences are not obvious. The impact of household income is enormous. Indirect energy consumption and CO₂ emissions are higher for high-income than for low-income households. The structural difference for indirect energy consumption and CO₂ emissions for households with different income levels is significant. The higher the income, the more diverse is the energy consumption and CO₂ emission structure. The structures for indirect energy use and CO₂ emissions are diverse for urban households, but simple for rural households.     

GHG reduction potential of changes in consumption patterns and higher quality levels: Evidence from Swiss household consumption survey

An effective consumer-oriented climate policy requires knowing the GHG reduction potential of sustainable consumption. The aim of this study is to draw lessons from differences in consumption between households with high and low GHG emissions. We evaluate a survey of 14,500 households and use a method that allows measuring changes in price level of consumption. Comparing the 10% of households with the highest GHG emissions per capita with the lowest 10% – controlling for differences in expenditure level and household structure – we find a range 5–17 tons of CO₂-equivalent per capita and year. The observed differences stem mainly from heating, electricity use, car use, and travel by aircraft. Consumption patterns with low GHG emissions are characterized by less spending on mobility, but more on leisure and quality oriented consumption (leading to higher prices per unit). Further characteristics are: a higher share of organic food, low meat consumption and fewer detached single family houses. Our findings imply that a significant reduction in GHG emissions would be possible by adopting real-world consumption patterns observable in society. The twin challenge is to shift consumption towards more climate friendly patterns, and to prevent any trend towards high emitting consumption patterns.     

The role of income in energy consumption behaviour: Evidence from French households data

The main purpose of this paper is to characterise quantitatively the impact of income on household energy consumption in the residential and transport sectors. Starting from the data collected in a paper survey, we analyse the extent of the constraint experienced by households in terms of equipment purchasing behaviour and daily energy consumption. This analysis shows that the least well-off households are particularly constrained since the share of their budget represented by these energy services is very large (15–25%), and this corresponds to a level of energy service well below that of the better-off households. The case of space-heating shows a factor of 2 in terms of level of comfort achieved between the extreme 10-percentiles. These households also face a strong capital constraint for equipment purchases. This leads either to a large increase in the required rate of return or to a reduction in the proportion of households that are prepared to replace their equipment earlier. The least well-off households are thus doubly constrained, since it is more difficult for them to invest. In our opinion, it is crucial to take into account this observation in the context of political measures aimed at reducing households’CO₂ emissions.     

ANN modeling of water consumption in the lead-acid batteries

Due to importance of the quantity of water loss in the life cycle of lead-acid batteries, water consumption tests were performed on 72 lead-acid batteries with low antimony grid alloy at different charge voltages and temperatures. Weight loss of batteries was measured during a period of 10 days. The behavior of batteries in different charge voltages and temperatures were modeled by artificial neural networks (ANNs) using MATLAB 7 media. Four temperatures were used in the training set, out of which three were used in prediction set and one in validation set. The network was trained by training and prediction data sets, and then was used for predicting water consumption in all three temperatures of prediction set. Finally, the network obtained was verified while being used in predicting water loss in defined temperatures of validation set. To achieve a better evaluation of the model ability, three models with different validation temperatures were used (model 1 = 50 °C, model 2 = 60 °C and model 3 = 70 °C). There was a good agreement between predicted and experimental results at prediction and validation sets for all the models.     

Prediction of net energy consumption based on economic indicators (GNP and GDP) in Turkey

The most important theme in this study is to obtain equations based on economic indicators (gross national product—GNP and gross domestic product—GDP) and population increase to predict the net energy consumption of Turkey using artificial neural networks (ANNs) in order to determine future level of the energy consumption and make correct investments in Turkey. In this study, three different models were used in order to train the ANN. In one of them (Model 1), energy indicators such as installed capacity, generation, energy import and energy export, in second (Model 2), GNP was used and in the third (Model 3), GDP was used as the input layer of the network. The net energy consumption (NEC) is in the output layer for all models. In order to train the neural network, economic and energy data for last 37 years (1968–2005) are used in network for all models. The aim of used different models is to demonstrate the effect of economic indicators on the estimation of NEC. The maximum mean absolute percentage error (MAPE) was found to be 2.322732, 1.110525 and 1.122048 for Models 1, 2 and 3, respectively. R² values were obtained as 0.999444, 0.999903 and 0.999903 for training data of Models 1, 2 and 3, respectively. The ANN approach shows greater accuracy for evaluating NEC based on economic indicators. Based on the outputs of the study, the ANN model can be used to estimate the NEC from the country's population and economic indicators with high confidence for planing future projections.     

Change in consumer sensitivity to electricity prices in response to retail deregulation: A panel empirical analysis of the residential demand for electricity in the United States

About ten years have passed since the deregulation of the U.S. retail electricity market, and it is now generally accepted that the available data is adequate to quantitatively assess and compare conditions before and after deregulation. This study, therefore, estimates the changes in price elasticity in the residential electricity market to examine the changes, if any, in household sensitivity (as a result of retail electricity market deregulation policies) to residential electricity rates. Specifically, six types of panel data are prepared, based on three cross-sections—all states (except for Alaska and Hawaii) and the District of Columbia, deregulated states, and non-deregulated states—and two time series—the period before deregulation and the period after deregulation. The panel empirical analysis techniques are used to determine whether or not the variables are stationary, and to estimate price elasticity. We find that there is no substantial difference in the price elasticity between deregulated and non-deregulated states for both periods—before deregulation and after deregulation. Thus, it can be said that the deregulation of the retail electricity market has not made consumers more sensitive to electricity rates and that retail deregulation policies are not the cause of price elasticity differences between deregulated and non-deregulated states.     

City-block-scale sensitivity of electricity consumption to air temperature and air humidity in business districts of Tokyo,Japan

The sensitivity of electricity consumption to air temperature and air humidity are effective indicators in evaluating the impacts of countermeasures against urban heat islands. The impacts of these countermeasures vary in time and space and so sensitivities based on finer resolution data are needed. Using actual hourly electric power consumption data from the business districts of Tokyo, we calculated the sensitivity of electric power consumption using multiple regression analysis. The sensitivities appear from 07:00 to 23:00 local standard time (LST) during weekdays during both winter and summer, mainly from 09:00 to 17:00 LST. The sensitivities to air temperature during winter are approximately 0.7–1.1 (W/floor-m²)/°C on an average and those during summer are approximately 1.1–1.4 on an average; the sensitivities to air humidity are approximately 0.6–0.9 on an average. It was found that the sensitivities to air temperature are caused due to heating during winter and cooling during summer; further, the sensitivities to air humidity were caused by dehumidification not for conditioning the air humidity of the room but for the condensation around the air-conditioner's coils with cooling during summer.     

Short-term performance degradation prediction of a commercial vehicle fuel cell system based on CNN and LSTM hybrid neural network

Short-term performance degradation prediction is significant for fuel cell system control and health management. This paper presents a hybrid deep learning method by combining the convolutional neural network (CNN) and long short-term memory (LSTM) network to predict the short-term degradation of a 110 kW fuel cell system used for the commercial vehicle. First, the complete ensemble empirical mode decomposition (CEEMD) is applied to decompose the nonlinear and non-stationary voltage sequence extracted by the sliding window into modality sequences with different characteristic time scales. Then, these modality sequences are input into the corresponding CNN-LSTM for voltage prediction. Experimental results show that the proposed CNN-LSTM can reduce the root mean square error (RMSE) by 13.55% and 34.40%, respectively, compared to the single CNN and LSTM because it combines the spatial feature extraction ability of CNN and the powerful prediction ability of LSTM. Furthermore, the CEEMD–CNN–LSTM can reduce RMSE by 36.92% compared to CNN-LSTM since the impact of exogenous factors on the recoverable decay and intrinsic decay of the fuel cell can be separated easily for better model learning. The CEEMD–CNN–LSTM is also compared with other recently published deep learning models based on the same data set, and the results show that the prediction framework in this paper has higher accuracy.     

Forecast of electricity consumption in Cyprus up to the year 2030: The potential impact of climate change

This paper provides a forecast of electricity consumption in Cyprus up to the year 2030, based on econometric analysis of energy use as a function of macroeconomic variables, prices and weather conditions. If past trends continue electricity use is expected to triple in the coming 20–25 years, with the residential and commercial sectors increasing their already high shares in total consumption. Besides this reference scenario it was attempted to assess the impact of climate change on electricity use. According to official projections, the average temperature in the Eastern Mediterranean is expected to rise by about 1 °C by the year 2030. Using our econometrically estimated model, we calculated that electricity consumption in Cyprus may be about 2.9% higher in 2030 than in the reference scenario. This might lead to a welfare loss of 15 million Euros in 2020 and 45 million Euros in 2030; for the entire period 2008–2030 the present value of costs may exceed 200 million Euros (all expressed in constant Euros of 2007). Moreover, we assessed the additional peak electricity load requirements in the future because of climate change: extra load may amount to 65–75 Megawatts (MW) in the year 2020 and 85–95 MW in 2030.     

Air conditioning in the region of Madrid, Spain: An approach to electricity consumption, economics and CO2 emissions

An understanding of electricity consumption due to residential air conditioning (AC) may improve production and environmental impact strategy design. This article reports on a study of peak and seasonal electricity consumption for residential air conditioning in the region of Madrid, Spain. Consumption was assessed by simulating the operation of AC units at the outdoor summer temperature characteristics of central Spain. AC unit performance when operating under part load conditions in keeping with weather conditions was also studied to find cooling demand and energy efficiency. Likewise final electricity consumption was computed and used to calculate energy costs and greenhouse gas emissions (GHGs). Cooling demand, when family holidays outside the region were factored into the calculations, came to 1.46 × 10⁹ kWh. Associated seasonal electricity demand was 617 × 10⁶ kWh and seasonal performance of AC units around 2.4. Electricity consumption in the whole region was observed to peak on 30 June 2008 at 5.44 × 10⁶ kW, being the load attributable to residential AC 1.79 × 10⁶ kW, resulting about 33% of the total peak consumption. The seasonal cost per household was about €156 and the total equivalent warming impact was 572 × 10³ t CO₂. The method proposed can be adapted for use in other regions.