Search results

This paper aims to propose an approach based upon the principal component analysis (PCA) to define a contribution rate for each variable and then select the main variables as inputs to a neural network for energy load forecasting in the region southeastern Brazil.

The proposed approach defines a contribution rate of each variable as a weighted sum of the inner product between the variable and each principal component. So, the contribution rate is used for selecting the most important features of 27 variables and 6,815 electricity data for a multilayer perceptron network backpropagation prediction model. Several tests, starting from the most significant variable as input, and adding the next most significant variable and so on, are accomplished to predict energy load (GWh). The Kaiser–Meyer–Olkin and Bartlett sphericity tests were used to verify the overall consistency of the data for factor analysis.

Although energy load forecasting is an area for which databases with tens or hundreds of variables are available, the approach could select only six variables that contribute more than 85% for the model. While the contribution rates of the variables of the plants, plus energy exchange added, have only 14.14% of contribution, the variable the stored energy has a contribution rate of 26.31% being fundamental for the prediction accuracy.

Besides improving the forecasting accuracy and providing a faster predictor, the proposed PCA-based approach for calculating the contribution rate of input variables providing a better understanding of the underlying process that generated the data, which is fundamental to the Brazilian reality due to the accentuated climatic and economic variations.

The purpose of this study is to present a hybrid approach to model and predict long-term energy peak load using Bayesian and Holt–Winters (HW) exponential smoothing techniques.

Bayesian inference is administered by Markov chain Monte Carlo (MCMC) sampling techniques. Machine learning tools are used to calibrate the values of the HW model parameters. Hybridization is conducted to reduce modeling uncertainty. The technique is applied to real load data. Monthly peak load forecasts are calculated as weighted averages of HW and MCMC estimates. Mean absolute percentage error and the coefficient of determination (R²) indices are used to evaluate forecasts.

The developed hybrid methodology offers advantages over both individual combined techniques and reveals more accurate and impressive results with R² above 0.97. The new technique can be used to assist energy networks in planning and implementing production projects that can ensure access to reliable and modern energy services to meet the sustainable development goal in this sector.

This is original research.

The current challenge for forecasting smart meters electricity consumption lies in the uncertainty and volatility of load profiles. Moreover, forecasting the electricity consumption for all the meters requires an enormous amount of time. Most papers tend to avoid such complexity by forecasting the electricity consumption at an aggregated level. This paper aims to forecast the electricity consumption for all smart meters at an individual level. This paper, for the first time, takes into account the computational time for training and forecasting the electricity consumption of all the meters.

A novel hybrid autoregressive-statistical equations idea model with the help of clustering and whale optimization algorithm (ARSEI-WOA) is proposed in this paper to forecast the electricity consumption of all the meters with best performance in terms of computational time and prediction accuracy.

The proposed model was tested using realistic Irish smart meters energy data and its performance was compared with nine regression methods including: autoregressive integrated moving average, partial least squares regression, conditional inference tree, M5 rule-based model, k-nearest neighbor, multilayer perceptron, RandomForest, RPART and support vector regression. Results have proved that ARSEI-WOA is an efficient model that is able to achieve an accurate prediction with low computational time.

This paper presents a new hybrid ARSEI model to perform smart meters load forecasting at an individual level instead of an aggregated one. With the help of clustering technique, similar meters are grouped into a few clusters from which reduce the computational time of the training and forecasting process. In addition, WOA improves the prediction accuracy of each meter by finding an optimal factor between the average electricity consumption values of each cluster and the electricity consumption values for each one of its meters.

The rapid urbanization of Indian cities and the population surge in cities has steered a massive demand for energy, thereby increasing the carbon emissions in the environment. Information and technology advancements, aided by predictive tools, can optimize this energy demand and help reduce harmful carbon emissions. Out of the multiple factors governing the energy consumption and comfort of buildings, indoor room temperature is a critical one, as it envisages the need for regulating the temperature. This paper aims to propose a mathematical model for short-term forecasting of indoor room temperature in the Indian context to optimize energy consumption and reduce carbon emissions in the environment.

A study is conducted to forecast the indoor room temperature of an Indian corporate building structure, based upon various external environmental factors: temperature and rainfall and internal factors like cooling control, occupancy behavior and building characteristics. Expert insight and principal component analysis are applied for appropriate variables selection. The machine learning approach using Box–Jenkins time series models is used for the forecasting of indoor room temperature.

ARIMAX model, with lagged forecasted and explanatory variables, is found to be the best-fit model. A predictive short-term hourly temperature forecasting model is developed based upon ARIMAX model, which yields fairly accurate results for data set pertaining to the building conditions and climatic parameters in the Indian context. Results also investigate the relationships between the forecasted and individual explanatory variables, which are validated using theoretical proofs.

The models considered in this research are Box–Jenkins models, which are linear time series models. There are non-linear models, such as artificial neural network models and deep learning models, which can be a part of this study. The study of hybrid models including combined forecasting techniques comprising linear and non-linear methods is another important area for future scope of study. As this study is based on a single corporate entity, the models developed need to be tested further for robustness and reliability.

Forecasting of indoor room temperature provides essential practical information about meeting the in-future energy demand, that is, how much energy resources would be needed to maintain the equilibrium between energy consumption and building comfort. In addition, this forecast provides information about the prospective peak usage of air-conditioning controls within the building indoor control management system through a feedback control loop. The resultant model developed can be adopted for smart buildings within Indian context.

This study has been conducted in India, which has seen a rapid surge in population growth and urbanization. Being a developing country, India needs to channelize its energy needs judiciously by minimizing the energy wastage and reducing carbon emissions. This study proposes certain pre-emptive measures that help in minimizing the consumption of available energy resources as well as reducing carbon emissions that have significant impact on the society and environment at large.

A large number of factors affecting the indoor room temperature present a research challenge for model building. The paper statistically identifies the parameters influencing the indoor room temperature forecasting and their relationship with the forecasted model. Considering Indian climatic, geographical and building structure conditions, the paper presents a systematic mathematical model to forecast hourly indoor room temperature for next 120 h with fair degree of accuracy.

The purpose of this paper is to propose an extensiveness intelligent hybrid model to short-term load electricity forecast that can simultaneously model the seasonal complicated nonlinear uncertain patterns in the data. For this purpose, a fuzzy seasonal version of the multilayer perceptrons (MLP) is developed.

In this paper, an extended fuzzy seasonal version of classic MLP is proposed using basic concepts of seasonal modeling and fuzzy logic. The fundamental goal behind the proposed model is to improve the modeling comprehensiveness of traditional MLP in such a way that they can simultaneously model seasonal and fuzzy patterns and structures, in addition to the regular nonseasonal and crisp patterns and structures.

Eventually, the effectiveness and predictive capability of the proposed model are examined and compared with its components and some other models. Empirical results of the electricity load forecasting indicate that the proposed model can achieve more accurate and also lower risk rather than classic MLP and some other fuzzy/nonfuzzy, seasonal nonseasonal, statistical/intelligent models.

One of the most appropriate modeling tools and widely used techniques for electricity load forecasting is artificial neural networks (ANNs). The popularity of such models comes from their unique advantages such as nonlinearity, universally, generality, self-adaptively and so on. However, despite all benefits of these methods, owing to the specific features of electricity markets and also simultaneously existing different patterns and structures in the electrical data sets, they are insufficient to achieve decided forecasts, lonely. The major weaknesses of ANNs for achieving more accurate, low-risk results are seasonality and uncertainty. In this paper, the ability of the modeling seasonal and uncertain patterns has been added to other unique capabilities of traditional MLP in complex nonlinear patterns modeling.

This paper aims to present a hybrid model to mid-term forecast the load of transmission substations based on the knowledge of expert site and multi-objective posterior framework. The main important challenges in load forecasting are the different behavior of load in specific days. Regular days, holidays and special holidays, days after a holidays and days of load shifting are characterized by abnormal load profiles. The knowledge of these days is verified by expert operators in regional dispatching centers.

In this paper, a hybrid model for power prediction of transmission substations based on the combination of similar day selection and multi-objective posterior technique has been proposed. In the first step, the important data for prediction is provided. Posterior method is used in the second step for prediction that it is based on kernel functions. A multi-objective optimization has been formulated with three type of output accuracy measurement function that it is solved by non-dominated sorting genetic technique II (NSGT-II) method. TOPSIS way is used to find the best point of Pareto.

The presented method has been tested in four scenarios for three different transmission stations, and the test results have been compared. The presented results indicate that the presentation method has better results and is robust to different load characteristics, which can be used for better forecasting of different stations for better planning of repairs and network operation.

The main contributions of this paper can be categorized as follows: A hybrid model based on similar days selection and multi-objective framework posterior is presented. Similar day selection is done by expert site that the day type and days with scheduled repair are considered. Hyperparameters of posterior process are found by NSGT-II based on TOPSIS method.

Liberalisation of the European electricity sector has allowed the industrial consumers to freely choose their electricity suppliers. Proliferation of different contract proposals for such supply means that all proposals need to be carefully evaluated for correct supplier renewal choice. The purpose of this paper is to propose a methodology for the evaluation of heterogeneous proposals of electricity supply that would help industrial consumers to be ready to face supply contractors.

The method relies on a three‐stage analysis: characterisation of electricity consumption in the industrial process; demand forecasts based on energy drivers and consumption characterisation; and finally a detailed tariff analysis. The method is illustrated through a case study of a renewal contract of an Italian industrial plant with a 20 percent incidence of electrical energy cost on the final product. The investigation also includes a sensitivity analysis on combustible basket price and the distribution of daily working load.

The evaluation of 14 proposals for the case study was carried out and the best offer for the case study company was selected. However, the overall price variation is 4 percent among different proposals and the electrical energy price shows an increase of 12 percent compared with the previous year. This suggests limited effectiveness of the competitive market in the Italian context.

The method can be considered as a practical guide for the electrical energy contract renewal process of any industrial consumer that would help minimize its cost.

The proposed method is based on an innovative investigation of the consumption characterisation of the industry based on energy drivers. This approach allows the industries to develop their own strategies for the contract renewal. The analysis presented here could be expanded to include more specific supply clauses for a more comprehensive analysis.

This study aims to short-therm forecasting of power generation output for this purpose, an adaptive neuro-fuzzy inference system (ANFIS) is designed to forecast the output power of power plant based on climate factors considering wind speed and wind direction simultaneously.

Several methods and algorithms have been proposed for systems forecasting in various fields. One of the strongest methods for modeling complex systems is neuro-fuzzy that refers to combinations of artificial neural network and fuzzy logic. When the system becomes more complex, the conventional algorithms may fail for network training. In this paper, an integrated approach, including ANFIS and metaheuristic algorithms, is used for increasing forecast accuracy.

Power generation in power plants is dependent on various factors, especially climate factors. Operating power plant in Iran is very much influenced because of climate variation, including from tropical to subpolar, and severely varying temperature, humidity and air pressure for each region and each season. On the other hands, when wind speed and wind direction are used simultaneously, the training process does not converge, and the forecasting process is unreliable. The real case study is mentioned to show the ability of the proposed approach to remove the limitations.

First, ANFIS is applied for forecasting based on climate factors, including wind speed and wind direction, that have rarely been used simultaneously in previous studies. Second, the well-known and more widely used metaheuristic algorithms are applied to improve the learning process for forecasting output power and compare the results.

Improving the accuracy and reducing computational costs of predictions, especially the prediction of time series, is one of the most critical parts of the decision-making processes and management in different areas and organizations. One of the best solutions to achieve high accuracy and low computational costs in time series forecasting is to develop and use efficient hybrid methods. Among the combined methods, parallel hybrid approaches are more welcomed by scholars and often have better performance than sequence ones. However, the necessary condition of using parallel combinational approaches is to estimate the appropriate weight of components. This weighting stage of parallel hybrid models is the most effective factor in forecasting accuracy as well as computational costs. In the literature, meta-heuristic algorithms have often been applied to weight components of parallel hybrid models. However, such that algorithms, despite all unique advantages, have two serious disadvantages of local optima and iterative time-consuming optimization processes. The purpose of this paper is to develop a linear optimal weighting estimator (LOWE) algorithm for finding the desired weight of components in the global non-iterative universal manner.

In this paper, a LOWE algorithm is developed to find the desired weight of components in the global non-iterative universal manner.

Empirical results indicate that the accuracy of the LOWE-based parallel hybrid model is significantly better than meta-heuristic and simple average (SA) based models. The proposed weighting approach can improve 13/96%, 11/64%, 9/35%, 25/05% the performance of the differential evolution (DE), genetic algorithm (GA), particle swarm optimization (PSO) and SA-based parallel hybrid models in electricity load forecasting. While, its computational costs are considerably lower than GA, PSO and DE-based parallel hybrid models. Therefore, it can be considered as an appropriate and effective alternative weighing technique for efficient parallel hybridization for time series forecasting.

In this paper, a LOWE algorithm is developed to find the desired weight of components in the global non-iterative universal manner. Although it can be generally demonstrated that the performance of the proposed weighting technique will not be worse than the meta-heuristic algorithm, its performance is also practically evaluated in real-world data sets.

China is by far the world’s largest energy consumer and importer. Reasonably forecasting the trend of China’s total energy consumption (CTEC) is of great significance. The purpose of this paper is to propose a new-structure grey system model (NSGM (1, 1)) to forecast CTEC.

Two matrices for computing the parameters of NSGM (1, 1) were defined and the specific calculation formula was derived. Since the NSGM (1, 1) model increases the number of its background values, which improves the smoothness effect of the background value and weakens the effects of extreme values in the raw sequence on the model’s performance; hence it has better simulation and prediction performances than traditional grey models. Finally, NSGM (1, 1) was used to forecast China’s total energy consumption during 2016-2025. The forecast showed CTEC will grow rapidly in the next ten years.

Therefore, in order to meet the target of keeping CTEC under control at 4.8 billion tons of standard coal in 2020, Chinese government needs to take necessary measures such as transforming the economic development pattern and enhancing the energy utilization efficiency.

A new-structure grey forecasting model, NSGM (1, 1), is proposed in this paper, which improves the smoothness and weakens the effects of extreme values and has a better structure and performance than those of other grey models. The authors successfully employ the new model to simulate and forecast CTEC. The research findings could aid Chinese government in formulating energy policies and help energy exporters make rational energy yield plans.