Energy Demand Equations Research Articles

Application of PSO algorithm to choose the best scenario for energy demand forecast of residential and commercial sectors in Iran

Purpose This paper aims to select the best scenario for energy demand forecast of residential and commercial sectors in Iran by using particle swarm optimization algorithm. Design/methodology/approach In this study, using variables affecting energy demand of residential and commercial sectors in Iran, the future status of energy demand in these sectors is predicted. Using the particle swarm optimization algorithm, both linear and exponential forms of energy demand equations were studied under 72 different scenarios with various variables. The data from 1968 to 2011 were applied for model development and the appropriate scenario choice. Findings An exponential model with inputs including total value added minus that of the oil sector, value of made buildings, total number of households and consumer energy price index is the most suitable model. Finally, energy demand of residential and commercial sectors is estimated up to the year 2032. Results show that the energy demand of the sectors will achieve a level of about 1,718 million barrels of oil equivalent per year by 2032. Originality/value To the best of our knowledge in this study a suitable model is selected for energy demand forecast of residential and commercial sectors by evaluation of various models with different variables as inputs.

Economic modelling of energy services: Rectifying misspecified energy demand functions

Although it is well known that energy demand is derived, since energy is required not for its own sake but for the energy services it produces – such as heating, lighting, and motive power – energy demand models, both theoretical and empirical, often fail to take account of this feature. In this paper, we highlight the misspecification that results from ignoring this aspect, and its empirical implications – biased estimates of price elasticities and other measures – and provide a relatively simple and empirically practicable way to rectify it, which has a strong theoretical grounding. To do so, we develop an explicit model of consumer behaviour in which utility derives from consumption of energy services rather than from the energy sources that are used to produce them. As we discuss, this approach opens up the possibility of examining many aspects of energy demand in a theoretically sound way that have not previously been considered on a widespread basis, although some existing empirical work could be interpreted as being consistent with this type of specification. While this formulation yields demand equations for energy services rather than for energy or particular energy sources, these are shown to be readily converted, without added complexity, into the standard type of energy demand equation(s) that is (are) typically estimated. The additional terms that the resulting energy demand equations include, compared to those that are typically estimated, highlight the misspecification that is implicit when typical energy demand equations are estimated. A simple solution for dealing with an apparent drawback of this formulation for empirical purposes, namely that information is required on typically unobserved energy efficiency, indicates how energy efficiency can be captured in the model, such as by including exogenous trends and/or including its possible dependence on past energy prices. The approach is illustrated using an empirical example that involves estimation of an aggregate energy demand function for the UK with data over the period 1960–2011.

Carbon tax scenarios and their effects on the Irish energy sector

Abstract In this paper we use annual time series data from 1960 to 2008 to estimate the long run price and income elasticities underlying energy demand in Ireland. The Irish economy is divided into five sectors: residential, industrial, commercial, agricultural and transport, and separate energy demand equations are estimated for all sectors. Energy demand is broken down by fuel type, and price and income elasticities are estimated for the primary fuels in the Irish fuel mix. Using the estimated price and income elasticities we forecast Irish sectoral energy demand out to 2025. The share of electricity in the Irish fuel mix is predicted to grow over time, as the share of carbon intensive fuels such as coal, oil and peat, falls. The share of electricity in total energy demand grows most in the industrial and commercial sectors, while oil remains an important fuel in the residential and transport sectors. Having estimated the baseline forecasts, two different carbon tax scenarios are imposed and the impact of these scenarios on energy demand, carbon dioxide emissions, and government revenue is assessed. If it is assumed that the level of the carbon tax will track the futures price of carbon under the EU-ETS, the carbon tax will rise from € 21.50 per tonne CO2 in 2012 (the first year forecasted) to € 41 in 2025. Results show that under this scenario total emissions would be reduced by approximately 861,000 tonnes of CO2 in 2025 relative to a zero carbon tax scenario, and that such a tax would generate € 1.1 billion in revenue in the same year. We also examine a high tax scenario under which emissions reductions and revenue generated will be greater. Finally, in order to assess the macroeconomic effects of a carbon tax, the carbon tax scenarios were run in HERMES, the ESRI's medium-term macroeconomic model. The results from HERMES show that, a carbon tax of € 41 per tonne CO2 would lead to a 0.21% contraction in GDP, and a 0.08% reduction in employment. A higher carbon tax would lead to greater contractions in output.

The Integration of Artificial Neural Networks and Particle Swarm Optimization to Forecast World Green Energy Consumption

In this study an integrated particle swarm optimization (PSO) and artificial neural network (ANN) is presented for analyzing world fossil fuels, primary energy and green energy consumption. For this purpose, these steps are followed: STEP 1: In the first step, PSO is applied in order to determine world's oil, natural gas, coal and primary energy demand equations based on socioeconomic indicators. world population, gross domestic product, oil trade movement and natural gas trade movement are used as socioeconomic indicators in this study. Two scenarios are defined for forecasting each socioeconomic indicator in a future time domain: Scenario I: For each socioeconomic indicator, the polynomial trend line is fitted to the observed data with the highest correlation coefficient value and projected for a future time domain. Scenario II: for each socioeconomic indicator, a feed-forward back propagation ANN is trained and projected for a future time domain. STEP 2: In the second step, world green energy consumption is projected based on oil, natural gas, coal, and primary energy consumption using PSO. The best results of the first step are used for future forecasting of world green energy consumption. World green energy consumption is forecasted up to the year 2040.

Using Bees Algorithm and Artificial Neural Network to Forecast World Carbon Dioxide Emission

In this study, an integrated multi-layer perceptron neural network and Bees Algorithm is presented for analyzing world CO2 emissions. For this purpose, the following steps are done: STEP 1: In the first step, the Bees Algorithm is applied in order to determine the world's fossil fuels and primary energy demand equations based on socio-economic indicators. The world's population, gross domestic product, oil trade movement, and natural gas trade movement are used as socio-economic indicators in this study. The following scenarios are designed for forecasting each socio-economic indicator in a future time domain: Scenario I: For each socio-economic indicator, several polynomial trend lines are fitted to the observed data and the best fitted polynomial (highest correlation coefficient (R2) value) for each socio-economic indicator is used for future forecasting. Scenario II: For each socio-economic indicator, several neural networks are trained and the best trained network for each socio-economic indicator is used for future forecasting. STEP 2: In the second step, world CO2 emission is projected based on the oil, natural gas, coal, and primary energy consumption using Bees Algorithm. The related data from 1980 to 2006 are used, partly for installing the models (1980–1999) and partly for testing the models (2000–2006). World CO2 emission is forecasted up to year 2040.

Pathways to a low-carbon economy for the UK with the macro-econometric E3MG model

This paper examines different carbon pathways for achieving deep CO 2 reduction targets for the UK using a macro-econometric hybrid model E3MG, which stands for Energy–Economy–Environment Model at the Global level. The E3MG, with the UK as one of its regions, combines a top-down approach for modeling the global economy and for estimating the aggregate and disaggregate energy demand and a bottom-up approach (Energy Technology subModel, ETM) for simulating the power sector, which then provides feedback to the energy demand equations and the whole economy. The ETM submodel uses a probabilistic approach and historical data for estimating the penetration levels of the different technologies, considering their economic, technical and environmental characteristics. Three pathway scenarios (CFH, CLC and CAM) simulate the CO 2 reduction by 40%, 60% and 80% by 2050 compared to 1990 levels respectively and are compared with a reference scenario (REF), with no reduction target. The targets are modeled as the UK contribution to an international mitigation effort, such as achieving the G8 reduction targets, which is a more realistic political framework for the UK to move towards deep reductions rather than moving alone. This paper aims to provide modeling evidence that deep reduction targets can be met through different carbon pathways while also assessing the macroeconomic effects of the pathways on GDP and investment.

Identification-robust simulation-based inference in joint discrete/continuous models for energy markets

In the analysis of energy use models, a common problem consists in correcting for endogenous discrete-choice variables. Indeed, energy demand equations often include endogenous dummies which reflect the underlying discrete-choice for e.g. energy equipment. The latter lead to discrete/continuous (D/C) statistical models where the discrete and continuous components are statistically dependent, so weak-identification problems may occur which stem from the “quality” of the first stage instrumental model. These problems are studied in the context of energy demand analysis. A wide mixed-logit-based class of models is considered which allow for dependent choices, heteroskedasticity and multi-dimensionality. The severity of weak-identification problems and relevance for empirical practice are documented, even with very large data sets. Tractable and reliable (in the sense of type I error control) solutions are proposed which combine generalized Anderson–Rubin (GAR) procedures and maximum simulated likelihood (MSL) methods for models commonly used in practice. Results are illustrated via Monte-Carlo examples and an empirical study on electricity demand.

Energy Demand Estimation Based on Two-Different Genetic Algorithm Approaches

Energy modeling is a subject of widespread current interest among engineers and scientists concerned with problems of energy production and consumption. Energy planning is not possible without a reasonable knowledge of past and present energy consumption and likely future demands. In this study, two forms of the energy demand equations are developed in order to improve energy demand estimation efficiency for future projections based on the genetic algorithm (GA) notion. The genetic algorithm energy demand (GAEDM) model is used to estimate Turkey's future energy demand based on gross domestic product, population, import, and export figures. Both equations proposed here are non-linear, of which one is exponential and the other is quadratic. The quadratic form of the GAEDM model provided a slightly better fit solution to the observed data and can be used with a high correlation coefficient for Turkey's future energy projections. It is expected that this study will be helpful in developing highly applicable and productive planning for energy policies.

DEMAND FOR ENERGY AMONG HOUSEHOLDS IN IJEBU DIVISION, OGUN STATE, NIGERIA

This study examines the influence of households' socio-economic characteristics on household demand for electricity, petrol, diesel, kerosene, firewood, domestic gas, and transport in commercial vehicles. Primary data obtained in a cross-section survey of 90 households selected across six communities in Ijebu-Division of Ogun State, Nigeria was used in estimating a system of energy demand equations and elasticities. The study reveals that an average household in the sample had about five members, headed by a 52 year old male that had about nine years of formal education. The mean monthly household consumption expenditure was 15,458.63, of which about 25% was expended on the seven commodities. While the influence of education and household size on household energy use were insignificant; income (budget size), household ownership of electrical/electronic appliances and automobiles, as well as age of household heads exercised significant influence on the relative shares of some/all of the seven energy commodities in household budgets in the study area. The income effects were positive for all the energy commodities, except firewood. Demand for petrol, diesel and domestic gas were income elastic. Thus, the study concludes that improvement in income would cause increase in demand for electricity and petroleum products in the study area, but worsening real income would place greater demand on biomass fuel.

Genetic algorithm approach to estimate transport energy demand in Turkey

Transport energy modeling is a subject of current interest among transport engineers and scientists concerned with problems of sustainable transport. Transport energy planning is not possible without a reasonable knowledge of past and present energy consumption and likely future demands. In this study, three forms of the energy demand equations are developed in order to improve transport energy demand estimation efficiency for future projections based on genetic algorithm (GA) notion. The Genetic Algorithm Transport Energy Demand Estimation (GATEDE) model is developed using population, gross domestic product and vehicle-km. All equations proposed here are linear and non-linear, of which one is linear, second is exponential and third is quadratic. The quadratic form of the GATEDE model provided better-fit solution to the observed data and can be used with a high correlation coefficient for Turkey's future transport energy projections. It is expected that this study will be helpful in developing highly applicable and productive planning for transport energy policies. The GATEDE gives transport energy demand in comparison with the other transport energy demand projections. The GATEDE model plans the sectoral energy demand of Turkey until 2020.

Impact of Carbon Dioxide Emissions Reduction on the Austrian Economy

A linked econometric input–output (IO) model of the Austrian economy with an energy block is used in this study to assess the sectoral effects of carbon dioxide emissions reduction. The energy block and the other commodities are linked by a partitioned IO model. Energy demand is described using aggregate energy demand equations, by activities and subdemand systems of the translog type for different fuel types. The conversion of energy is modelled using an IO model of the energy sector. Measures for carbon dioxide reduction from detailed expert studies are introduced in the energy model and in the econometric model. The primary impacts are on energy demand, fuel shares and investment in new energy technologies. The simulation results of the partitioned IO model show different impacts on gross output, GDP and employment.

Residential energy demand modelling in developing regions: The use of multivariate statistical techniques

This paper presents a new approach for modelling residential energy demand. In developing regions it is considered a new approach as energy demand equations apply to ‘homogeneous’ groups of consumers which are endogenously defined. The structural analysis of energy demand is the first phase of the approach which defines the set (tree) of consumption groups. These are obtained by applying multivariate statistical techniques on cross-section pooled data. Principal components analysis and discriminant analysis are the main methods used. The set of groups obtained is linked to a set of equations through a qualitative response model which simulates the decisions of households. Equations concerning energy consumption, the choice of energy equipment and the repartition by energy products are then estimated for each group. An application for the Cyclades region is presented. The model consists of 269 equations, 261 parameters and 15 exogenous variables. Scenarios and results for 1985–2000 are given together with a number of suggestions for further research.

Energy Shocks and the Demand for Energy

This paper discusses developments in energy consumption and oil markets since the early 1970s, highlighting the fall in energy and oil consumption per unit of output and the accompanying reduction in industrialised countries' exposure and vulnerability to energy shocks. In an attempt to analyse the determinants of aggregate output, a very simple model is subsequently presented to discuss the major transmission channels of energy price shocks and the related risk of disturbances to long-term equilibrium growth. The focus is then turned on investment and the capital stock and their role in the determination of energy demand. Energy demand equations are empirically derived for seven major countries, distinguishing in each case between demand for energy in industry, transportation and the commercial and residential sectors.

A switching regression model with different change-points for individual coefficients and its application to the energy demand equations for Japan

A switching regression model with different change-points for individual coefficients and its application to the energy demand equations for Japan

Noisy Data and Uncertain Coefficients: A Comment

Noisy data are frequently used to estimate regression coefficients for energy demand equations. Although analysts new to the area might expect reported coefficients and forecasts to reflect this source of uncertainty, reported numbers, in general, do not reflect it. Recently, Kher et al. (1987, hereinafter KSS) confronted the problem and proposed a new technique for reporting forecasts based on the estimation of bounds for regression coefficients. Regression coefficient bounds reflect the uncertainty in an estimated model stemming from the use of noisy data. In this comment I identify additional studies that have addressed the estimation of such bounds and also present an example of a more common use of them.