A novel machine learning approach for estimation of electricity demand: An empirical evidence from Thailand
Introduction
The great influence of electric energy on economic development is well-understood. In general, electricity demand is defined as the amount of electricity generated and distributed in a specific region over a specific period. Accurate estimation of the electricity demand is a crucial factor for energy management. In this context, many technological developments and progresses have been achieved. Up to now, different methods are employed for the prediction of the electricity demand [1]. Generally, these methods can be categorized into three major groups [2]: (1) autoregressive integrated moving average (ARIMA), (2) multiple linear regression (MLR) and (3) machine learning techniques. ARIMA models are stochastic difference equations commonly used for the modeling of stochastic disturbances in time series analysis [3]. Cho et al. [4] conducted a comparative study between ARIMA and traditional regression approach for the customer short term load forecasting. Abdel-Aal and Al-Garni [5] used this technique to predict the domestic electric energy consumption in Saudi Arabia. Ediger and Akar [6] applied ARIMA to the estimation of the future energy demand in Turkey. Suhartono and Endharta [7] used double seasonal ARIMA model for short term electricity load demand forecasting in Indonesia. Mohamed et al. [8] investigated the double seasonal ARIMA model for forecasting the double seasonal (daily and weekly) Malaysia load demand time series. Taylor [9], [10] and Taylor et al. [11] employed various techniques such as double seasonal exponential smoothing; principal component analysis, and double seasonal ARIMA for electricity demand forecasting up to a day ahead for Rio de Janeiro and a series of half-hourly demand for England and Wales. MLR is another statistical approach which is widely used for the energy demand estimation [2]. A major drawback of the regression and other statistical analyses is that they model the nature of the corresponding problem by a pre-defined linear or nonlinear equation [12].
Over the last decade, machine learning has attracted much attention in both academic and empirical fields for tackling real world problems. The machine learning systems are powerful tools for design of computer programs. They automatically learn from experience and extract various discriminators [13]. Artificial neural networks (ANNs) are the most widely used branch of machine learning. ANNs have been widely applied to different problems in energy conversion and management (e.g. [14], [15], [16], [17], [18], [19]). Hsu and Chen [20] considered GDP, population and temperature for the ANN-based modeling of the regional peak load in Taiwan. Ringwood et al. [21] proposed prediction models for electricity demand on short, medium and long time scales in the Republic of Ireland using ANNs. Catalao al. [22] applied the ANN to predict the next-week prices in the electricity market of Spain. Azadeh et al. [23], [24] utilized ANNs for the energy demand estimation in Iran. Azadeh et al. [1] presented a novel integrated fuzzy system, data mining and time series framework to predict the electricity demand for seasonal and monthly changes in electricity consumption especially in developing countries such as China and Iran with non-stationary data. Azadeh et al. [25] used ANN and time series for forecasting electrical consumption. The advantage of ANN methodology through analysis of variance (ANOVA) was shown by Azadeh et al. [25]. Support vector model (SVM) is another machine learning technique that has been successfully applied to predict the electric consumption [26]. In this context, Fan and Chen [27] developed a load forecasting method for short-term load forecasting, based on an adaptive two-stage hybrid network with self-organized map (SOM) and SVM. Using the actual data taken from the New York ISO and the Western Farmers Electric Cooperative in Oklahoma, Fan et al. [28] proposed a novel forecasting model for day ahead electricity load forecasting based on bayesian clustering by dynamics (BCD) and support vector regression (SVR). The BCD–SVR model adopted an integrated architecture to handle the non-stationarity of time series. Despite having a good performance, ANNs and SVM are considered black-box models. That is, they do not provide the knowledge of process they obtain a solution. Thus, they are not capable of generating practical prediction equations. Another major limitation of the ANNs is that the structure of the network needs to be identified in advance [7], [29].
A robust machine learning approach for predicting electricity demand is genetic programming (GP) [30]. GP is a robust branch of evolutionary algorithms (EAs) that creates computer programs to solve a problem using the principle of Darwinian natural selection. GP has several advantages over the conventional and ANN techniques. A notable feature of GP is that it can produce prediction equations without a need to define the form of the existing relationship [29], [31], [32]. Lee et al. [33] showed that GP is a powerful tool for long-term forecasting of electric power demand in Korea. Later, Bhattacharya et al. [34] employed GP for modeling electricity demand prediction in Australia.
Simulated annealing (SA) is a well-known optimization method. The Metropolis algorithm [35] is known as the foundation of SA to simulate the annealing process [29]. Some researchers coupled GP and SA to improve the efficiency of GP [36], [37]. There are very limited applications of the hybrid GP and SA technique to solve real world problems [31], [32], [38], [39]. Unlike ANNs, SVM and classical GP, applications of this hybrid method in the field energy conversion and management are conspicuous by their absence [29].
This study investigates the potential of the coupled technique of GP and SA (GSA), to predict the total electricity demand in Thailand from 1986 to 2009. The results made by the developed GSA models were further compared with those obtained by a conventional statistical method. The paper is organized as follows: Section 2 presents brief descriptions of the standard GP and GSA techniques. Section 3 outlines the model development using GSA and reviews the results. The detailed performance analysis of the proposed model is discussed in Section 4. The results of the sensitivity analysis are given in Section 5. Finally, concluding remarks are outlined in Section 6.
Section snippets
Machine learning
Machine learning is a branch of artificial intelligence essentially inspired from biological learning [13]. The machine learning approach deals with the design of computer programs and systems that are able to automatically learn with experience [13], [40]. The machine learning methods extract knowledge and complex patterns from machine readable data [41]. A type of machine learning used herein is supervised machine learning. This methodology is based on mapping a set of input information to
The proposed methodology for the estimation of electricity demand
In general, the steps followed by the machine learning techniques to find optimal models are the same. In this study, the proposed methodology for developing a precise prediction model for the electricity demand was similar to the procedure presented in [29]. The steps of the proposed algorithm are as follows:
- I.
Determination of input and output variables of the model.
- II.
Collecting data set S containing annual energy data of Thailand from 1986 to 2009.
- III.
Divide S into two subsets: training (STraining)
Performance analysis
Precise models were to predict the electricity demand in Thailand. Based on a rational hypothesis, Smith [46] suggested the following criteria for judging performance of a model:
- •
If a model gives |R| > 0.8, a strong correlation exists between the predicted and measured values.
- •
If a model gives 0.2 < |R| < 0.8 a correlation exists between the predicted and measured values.
- •
If a model gives |R| < 0.2, a weak correlation exists between the predicted and measured values.
In all cases, the error values (e.g.
Sensitivity analysis
The contribution of each input parameter in the GSA models was evaluated through a sensitivity analysis. In order to evaluate the importance of the input parameters, their frequency values [43] were obtained. A frequency value equal to 1 for an input indicates that this input variable has been appeared in 100% of the best thirty programs evolved by GSA [29], [31], [32], [39]. The frequency values of the predictor variables are presented in Fig. 6. According to this figure, the electricity
Conclusion
In the present study, a new hybrid search algorithm combining GP and SA, called GSA was used to predict the electricity demand in Thailand. The historical data from 1986 to 2009 were used to develop the model. The validity of the model was tested for a part of test results beyond the training data domain. The proposed models produce better outcomes than the traditional MLR and ANN models. An expected observation from the results of the sensitivity analysis was that the electricity demand is
References (55)
- et al.
Improved estimation of electricity demand function by integration of fuzzy system and data mining approach
Energy Convers Manage
(2008) - et al.
Forecasting monthly electric energy consumption in eastern Saudi Arabia using univariate time-series analysis
Energy
(1997) - et al.
ARIMA forecasting of primary energy demand by fuel in Turkey
Energy Policy
(2007) Triple seasonal methods for short-term electricity demand forecasting
Eur J Oper Res
(2010)- et al.
A comparison o univariate methods for forecasting electricity demand up to a day ahead
Int J Forecast
(2006) Artificial neural network approach to spatial estimation of wind velocity data
Energy Convers Manage
(2006)Artificial neural network based modeling of performance characteristics of deep well pumps with splitter blade
Energy Convers Manage
(2006)- et al.
Forecasting daily urban electric load profiles using artificial neural networks
Energy Convers Manage
(2004) - et al.
Annual electricity consumption forecasting by neural network in high energy consuming industrial sectors
Energy Convers Manage
(2008) - et al.
Forecasting of electricity prices with neural networks
Energy Convers Manage
(2006)
Regional load forecasting in Taiwan-applications of artificial neural networks
Energy Convers Manage
Short-term electricity prices forecasting in a competitive market: a neural network approach
Electr Power Syst Res
Intergraion of artificial neural networks and genetic algorithm to predict electrical energy consumption
Appl Math Comput
A simulated-based neural network algorithm for forecasting electrical energy consumption in Iran
Energy Policy
Forecasting electrical consumption by integration of neural network, time series and ANOVA
Appl Math Comput
Electric load forecasting by support vector model
Appl Math Model
Machine learning based switching model for electricity load forecasting
Energy Convers Manage
A hybrid computational approach to estimate solar global radiation: an empirical evidence from Iran
Energy
Formulation of flow number of asphalt mixes using a hybrid computational method
Constr Build Mater
Genetic programming model for long-term forecasting of electric power demand
Electr Power Syst Res
Beware of q2
J Mole Graph Model
Permanent deformation analysis of asphalt mixtures using soft computing techniques
Exp Syst Appl
Prediction of Principal Ground-Motion Parameters Using a Hybrid Method Coupling Artificial Neural Networks and Simulated Annealing
Comput Struct
Enhancement of the durability characteristics of concrete nanocomposite pipes with modified graphite nanoplatelets
Constr Build Mater
Enhancement of the structural efficiency and performance of concrete pipes through fiber reinforcement
Constr Build Mater
Multi-Stage Genetic Programming: A New Strategy to Nonlinear System Modeling
Inf Sci
Energy-Based Models for Assessment of Soil Liquefaction
Geosci Frontiers
Cited by (42)
Efficient daily electricity demand prediction with hybrid deep-learning multi-algorithm approach
2023, Energy Conversion and ManagementPanel semiparametric quantile regression neural network for electricity consumption forecasting
2022, Ecological InformaticsAn evolutionary-based predictive soft computing model for the prediction of electricity consumption using multi expression programming
2021, Journal of Cleaner ProductionCitation Excerpt :In the current decade, GP-based methods have attracted much attention from the academia. For example, Mostafavi et al. (2013) applied GP to estimate the electricity demand with respect to stock index, population, revenue and GDP between 1986 and 2009 in Thailand. The findings showed that not only the developed GP model is more accurate than ANN and regression, it can also provide a very useful mathematical model for energy demand forecasting.
A review on machine learning forecasting growth trends and their real-time applications in different energy systems
2020, Sustainable Cities and SocietyTarget and demand for renewable energy across 10 ASEAN countries by 2040
2019, Electricity Journal