Figure 6 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Comparison of MAPE for all methods. ANN is the artificial neural network; TBATS stands for the general Exponential Smoothing State Space Model with Box-Cox Transformation, ARMA Errors, Trend and Seasonal Components (TBATS) method, and TBATS JASA stands for TBATS with regressors. AMC 24,168 is the regular nHWT method, and AMC 24,168,Easter stands for nHWT with DIMS.
Source publication
Forecasting electricity demand through time series is a tool used by transmission system operators to establish future operating conditions. The accuracy of these forecasts is essential for the precise development of activity. However, the accuracy of the forecasts is enormously subject to the calendar effect. The multiple seasonal Holt–Winters mod...
Context in source publication
Context 1
... this analysis, the same procedure to Spanish electricity demand, with and without regressors, has been applied. Figure 6 shows the MAPE obtained by all methods using the same dataset for all of the Easter days from Thursday to Monday. The names used in the graph correspond to the method used to obtain the forecasts. ...
Citations
... Two main conclusions can be drawn from this table: first, ANN and ARIMA multivariate models outperform the univariate versions, as expected; second, MV-bigPSF outperforms all the multivariate Finally, from the observation of these tables, it can be concluded that the proposed approach should include some improvements so that the summer months can be better forecast. Moreover, in view of the analysis of the errors distributed over the type of days, it can be concluded that even if MV-bigPSF achieved better results, there is still a need to improve the results for the festivities, especially in those that are not Saturday or Sunday (this fact is probably due to the similar behavior that weekends and festivities on Saturday or Sunday exhibit in terms of consumption (Trull et al., 2019)). As for the hour of the day, it can be concluded that no extra modifications are required. ...
... In general, the analysis of time series has two main objectives: to identify the nature of the phenomena represented by this time series and its prediction. The forecasting techniques based on time series models (Trull et al. 2019(Trull et al. , 2020 have been widely developed and applied in very diverse disciplines, such as economics, meteorology, medicine or resource management. ...
The time series analysis and prediction techniques are highly valued in many application fields, such as economy, medicine and biology, environmental sciences or meteorology, among others. In the last years, there is a growing interest in the sustainable and optimal management of a resource as scarce as essential: the water. Forecasting techniques for water management can be used for different time horizons from the planning of constructions that can respond to long-term needs, to the detection of anomalies in the operation of facilities or the optimization of the operation in the short and medium term. In this paper, a deep neural network is specifically designed to predict water consumption in the short-term. Results are reported using the time series of water consumption for a year and a half measured with 10-min frequency in the city of Murcia, the seventh largest city in Spain by number of inhabitants. The results are compared with K Nearest Neighbors, Random Forest, Extreme Gradient Boosting, Seasonal Autoregressive Integrated Moving Average and two persistence models as naive methods, showing the proposed deep learning model the most accurate results.
... Trull et al. [16,17] proposed the use of discrete-interval moving seasonalities (DIMS) to consider the calendar effect within a multiple seasonal Holt-Winters model, as part of the model itself. The results showed that this implementation outperformed previous methods, although the new model follows the guidelines of the original model. ...
... So we decided to use small values for all seasonalities (cases 9-10), which turned out to be the most effective. Tests with different lengths of ( ) were also performed: cases 11-13, in which a sequence of values was taken into account, following the indications of [19], and later approximations to the different cases studied (cases [14][15][16]. From the results, we concluded that, for this application, the best results are obtained using the same ( ) for all seasonalities, of length 15. ...
The decomposition of a time series into components is an exceptionally useful tool for understanding the behaviour of the series. The decomposition makes it possible to distinguish the long-term and the short-term behaviour through the trend component and the seasonality component. Among the decomposition methods, the STL (Seasonal Trend decomposition based on Loess) method stands out for its versatility and robustness. This method, however, has one main drawback: it works with a single seasonality, and does not deal with the calendar effect. In this article we present a new decomposition method, based on the STL, which allows the use of different seasonalities while allowing the calendar effect and special events to be introduced into the model using discrete-interval moving seasonalities (MSTL-DIMS). To show the improvements obtained, the MSTL-DIMS technique is applied to short-term load forecasting in some electricity systems, and the results are discussed.
... The electricity demand analysis has traditionally been done by means of classical statistical tools based on time series models [34,35]. Time series data can be defined as a chronological sequence of observations on a target variable. ...
Nowadays, electricity is a basic commodity necessary for the well-being of any modern society. Due to the growth in electricity consumption in recent years, mainly in large cities, electricity forecasting is key to the management of an efficient, sustainable and safe smart grid for the consumer. In this work, a deep neural network is proposed to address the electricity consumption forecasting in the short-term, namely, a long short-term memory (LSTM) network due to its ability to deal with sequential data such as time-series data. First, the optimal values for certain hyper-parameters have been obtained by a random search and a metaheuristic, called coronavirus optimization algorithm (CVOA), based on the propagation of the SARS-Cov-2 virus. Then, the optimal LSTM has been applied to predict the electricity demand with 4-h forecast horizon. Results using Spanish electricity data during nine years and half measured with 10-min frequency are presented and discussed. Finally, the performance of the proposed LSTM using random search and the LSTM using CVOA is compared, on the one hand, with that of recently published deep neural networks (such as a deep feed-forward neural network optimized with a grid search) and temporal fusion transformers optimized with a sampling algorithm, and, on the other hand, with traditional machine learning techniques, such as a linear regression, decision trees and tree-based ensemble techniques (gradient-boosted trees and random forest), achieving the smallest prediction error below 1.5%.
... Electricity consumption in the USA was predicted with adaptive models by Rahman A. and Ahmar A. S. [133]. In Spain, electricity demand during Easter was forecasted using similar models [134]. Similar forecasting methods were applied to study the demand for electricity in Colombian quarries and incinerators [135]. ...
Poland, as a member of the European Union (EU), has to fulfill the obligations resulting
from its membership in it. It is necessary to comply with numerous directives and other legal provisions adopted by the European Commission in the field of the energy market and production. Meeting the demands of the European Green Deal, as well as the solutions presented in the Fit for 55 package, is very difficult. In Poland, coal is still used in over 67% of electricity production. This article presents an attempt to join the multi-threaded discussion on renewable energy sources (RES) and the possibility of increasing their share in Poland’s energy mix. This article defines the RES support mechanisms in Poland, presents the support systems and instruments functioning within them, and also provides a statistical prediction of trends in energy production from RES for upcoming
years. The research utilized the Brown, Holt, and Winters models and the cause-and-effect model. The research conducted in this article shows that Poland must make significant efforts to decarbonize the economy; in addition, the too quickly changing RES support system is not conducive to the development of these sources.
... Early approaches for electricity consumption prediction rely on statistical methods [12]. However, recent research uses this type of method for comparison purposes. ...
Bstract
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.
... For TSA and ML techniques this has been done by using wavelet or Fourier transformation in [39,58,90,108,111,120,[175][176][177][178][179][180]. Particular attention was payed to the prediction of special events and holidays in [118,[181][182][183]. ...
... Historic energy demand [17,27,30,[61][62][63]75,[84][85][86]91,96,118,131,133,134,138,140,143,146,[148][149][150]152,154,[156][157][158][159][160]168,181,189,192,202,230,231,234,239,240,242,243,255,262,263,268,270,273,277,280,282,285,289,292,327,329,331,337,338,340,344,356,357,363,364,367,371,395,397,398,400,401,404,404,407,[438][439][440]442,446,447,465,468] Weather data [27,[61][62][63]75,84,91,96,118,138,[140][141][142]146,[148][149][150]154,157,159,160,183,239,242,255,289,292,329,338,340,363,367,394,397,404,407,[438][439][440]442,446,447,449,465,468] Calendar data [27,[61][62][63]118,138,140,146,150,154,157,159,160,183,230,239,280,292,331,340,400,438,440,446,447,449,468] Demographic or economic data [75,85,133,141,148,157,158,189,234,255,262,270,277,285,292,298,327,330,331,338,351,395,439,440,446,447,465,468] Technical system data [61,63,75,85,96,144,152,158,159,327,329,330,337,338,344,358,394,395,398,400,449,458,468] Usage or behavioral data [63,86,96,142,255,327,330,395,400,401] Energy prices [63,96,148,280,331,439,458] TSA/ ARCH Historic energy demand [17,29,30,39,47,48,59,60,79,81,95,104,105,109,113,120,131,134,136,143,155,156,162,167,[178][179][180]182,202,227,231,240,241,243,[245][246][247][249][250][251]253,256,259,261,[263][264][265][271][272][273]276,281,283,288,290,294,296,297,324,333,339,342,343,346,356,363,367,369,371,373,403,407,414,418,430,443,479] Weather data [39,95,136,143,180,202,243,253,259,261,263,264,290,339,343,356,363,367,407,430] Calendar data [39,48,95,109,113,120,136,162,202,227,231,241,243,245,263,290,342,343,414] Demographic or economic data [29,81,178,240,241,246,273,356,443] Technical system data n/a Usage or behavioral data [339] Energy prices [178,241,246] Stochastic Historic energy demand [20,27,29,30,33,34,40,44,45,64,66,68,79,93,98,133,139,167,176,184,202,203,228,238,243,246,257,276,294,324,414,418] Weather data [27,40,52,68,93,98,139,176,202,203,238,243,334,347] Calendar data [27,44,52,93,98,121,122,184,202,203,228,238,243,347,414] Demographic or economic data [29,34,40,66,93,122,133,246,334,347] Technical system data [20,52,66,68,93,121,334,347] Usage or behavioral data [40,44,52,66,98,121,122,334] Energy prices [98,246] Fuzzy Historic energy demand [16,18,[47][48][49]51,59,69,70,75,[112][113][114]118,133,135,163,164,192,251,252,270,272,284,285,327,336,349,426,453,470] Weather data [69,70,75,112,114,118,151,163,164,349,470] Calendar data [48,70,[112][113][114]118,164,284,349,470] Demographic or economic data [49,75,133,270,285,327,336,475] Technical system data [327,409,453] Usage or behavioral data [151,327] Energy prices [49] Table A7. Techniques and input data used per article (4/4). ...
... Regional[30,60,79,113,136,140,146,157,183,227,249,264,276,282,290,356,438,440,442] National[118,142,155,182,242,243,292,294,308,318,330] ...
In this article, a systematic literature review of 419 articles on energy demand modeling, published between 2015 and 2020, is presented. This provides researchers with an exhaustive overview of the examined literature and classification of techniques for energy demand modeling. Unlike in existing literature reviews, in this comprehensive study all of the following aspects of energy demand models are analyzed: techniques, prediction accuracy, inputs, energy carrier, sector, temporal horizon, and spatial granularity. Readers benefit from easy access to a broad literature base and find decision support when choosing suitable data-model combinations for their projects. Results have been compiled in comprehensive figures and tables, providing a structured summary of the literature, and containing direct references to the analyzed articles. Drawbacks of techniques are discussed as well as countermeasures. The results show that among the articles, machine learning (ML) techniques are used the most, are mainly applied to short-term electricity forecasting on a regional level and rely on historic load as their main data source. Engineering-based models are less dependent on historic load data and cover appliance consumption on long temporal horizons. Metaheuristic and uncertainty techniques are often used in hybrid models. Statistical techniques are frequently used for energy demand modeling as well and often serve as benchmarks for other techniques. Among the articles, the accuracy measured by mean average percentage error (MAPE) proved to be on similar levels for all techniques. This review eases the reader into the subject matter by presenting the emphases that have been made in the current literature, suggesting future research directions, and providing the basis for quantitative testing of hypotheses regarding applicability and dominance of specific methods for sub-categories of demand modeling.
... To guarantee good prediction results, training data from at least one year before the forecast begins is required. Other well-established statistical forecast methods are General Exponential Smoothing with inclusion of seasonality (Holt-Winters) [4] and autoregressive integrated moving average (ARIMA) [5,6] and combination of ARIMA and Artificial Neural Networks [7]. They can consider influences resulting from changing trends, seasonal differences and irregularities in load data and work well with a limited amount of training samples. ...
The paper presents a new approach for the prediction of load active power 24 h ahead using an attended sequential encoder and stacked decoder model with Long Short-Term Memory cells. The load data are owned by the New York Independent System Operator (NYISO) and is dated from the years 2014–2017. Due to dynamics in the load patterns, multiple short pieces of training on pre-filtered data are executed in combination with the transfer learning concept. The evaluation is done by direct comparison with the results of the NYISO forecast and additionally under consideration of several benchmark methods. The results in terms of the Mean Absolute Percentage Error range from 1.5% for the highly loaded New York City zone to 3% for the Mohawk Valley zone with rather small load consumption. The execution time of a day ahead forecast including the training on a personal computer without GPU accounts to 10 s on average.
... In this methodology, the period and length of the seasonality are modified in a selected way, so that the demand for a similar day is used to feed the model and make forecasts. Trull et al. [22] presented a Holt-Winters model, with discrete-interval moving seasonalities (DIMS) included in the model and used it to improve predictions during an Easter period. This period in Spain is characterized by having a duration of 120 hours (from Holy Thursday to Easter Monday), with similar and repetitive behavior each year, despite occurring on different dates. ...
... The model tries to reproduce the previous behaviour of the time series and cannot deal with the anomalous load occurring during the special event, as these models behave robust against variations [19]. Trull et al. [22] include discrete seasonalities related to special events, which only apply when the event occurs and can be smoothed as other general seasonality (DIMS). The general nHWT-DIMS models are described in Appendix A. The nHWT-DIMS model for the holidays, bridges and Easter holidays are shown in Equations (5-12). ...
... In some regions, Easter Monday also depends on the year. The strategy for modelling Easter is to use DIMS with 120 hours length [22]. The holidays considered in this article are gathered in Table 2, where crosses indicate occurrence, while blanks indicate the holidays took place during the weekend and has been removed from the study. ...
Transmission System Operators provide forecasts of electricity demand to the electricity system. The producers and sellers use this information to establish the next day production units planning and prices. The results obtained are very accurate. However, they have a great deal with special events forecasting. Special events produce anomalous load conditions, and the models used to provide predictions must react properly against these situations. In this article, a new forecasting method based on multiple seasonal Holt-Winters modelling including discrete-interval moving seasonalities is applied to the Spanish hourly electricity demand to predict holidays with a 24-hour prediction horizon. It allows the model to integrate the anomalous load within the model. The main results show how the new proposal outperforms regular methods and reduces the forecasting error from 9.5% to under 5% during holidays.
... Trull et al. [25] include the use of discrete seasonality in their model, so that the model seen in (6)-(9) now results in (21)- (25), which is named nHWT-DIMS: ...
... Trull et al. [25] include the use of discrete seasonality in their model, so that the model seen in (6)-(9) now results in (21)- (25), which is named nHWT-DIMS: ...
... D (a) t a * and D (b) t b * are the DIMS as described in Table 4 with smoothing parameters δ Table 4. To use the model, the procedure described in [25] is carried out. Initially, the initial values for the level are obtained as the moving average of the first period of one hour; for the trend as the slope between the first and second cycle of one hour; and for the seasonal indices, the weighting of the series in the first cycle on the moving average. ...
Distribution companies use time series to predict electricity consumption. Forecasting techniques based on statistical models or artificial intelligence are used. Reliable forecasts are required for efficient grid management in terms of both supply and capacity. One common underlying feature of most demand–related time series is a strong seasonality component. However, in some cases, the electricity demanded by a process presents an irregular seasonal component, which prevents any type of forecast. In this article, we evaluated forecasting methods based on the use of multiple seasonal models: ARIMA, Holt-Winters models with discrete interval moving seasonality, and neural networks. The models are explained and applied to a real situation, for a node that feeds a galvanizing factory. The zinc hot-dip galvanizing process is widely used in the automotive sector for the protection of steel against corrosion. It requires enormous energy consumption, and this has a direct impact on companies’ income statements. In addition, it significantly affects energy distribution companies, as these companies must provide for instant consumption in their supply lines to ensure sufficient energy is distributed both for the process and for all the other consumers. The results show a substantial increase in the accuracy of predictions, which contributes to a better management of the electrical distribution.
