Comparison of ARIMA and ANN Models Used in Electricity Price Forecasting for Power Market

Gao, Gao; Lo, K.L.; Fan, Fulin

doi:10.4236/epe.2017.94b015

Cited by 28 publications

(20 citation statements)

References 7 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Among the different approaches, some of the most common and traditional methods are the statistical models for time series prediction, named Autoregressive Integrated Moving Average (ARIMA) models [45]. Furthermore, ARIMA models are commonly employed as benchmark models to compare the predictions' performance [46,47].…”

Section: Market Minimum Bid Activation Time Activation Frequencymentioning

confidence: 99%

Exploiting Artificial Neural Networks for the Prediction of Ancillary Energy Market Prices

et al. 2018

View full text Add to dashboard Cite

The increase of distributed energy resources in the smart grid calls for new ways to profitably exploit these resources, which can participate in day-ahead ancillary energy markets by providing flexibility. Higher profits are available for resource owners that are able to anticipate price peaks and hours of low prices or zero prices, as well as to control the resource in such a way that exploits the price fluctuations. Thus, this study presents a solution in which artificial neural networks are exploited to predict the day-ahead ancillary energy market prices. The study employs the frequency containment reserve for the normal operations market as a case study and presents the methodology utilized for the prediction of the case study ancillary market prices. The relevant data sources for predicting the market prices are identified, then the frequency containment reserve market prices are analyzed and compared with the spot market prices. In addition, the methodology describes the choices behind the definition of the model validation method and the performance evaluation coefficient utilized in the study. Moreover, the empirical processes for designing an artificial neural network model are presented. The performance of the artificial neural network model is evaluated in detail by means of several experiments, showing robustness and adaptiveness to the fast-changing price behaviors. Finally, the developed artificial neural network model is shown to have better performance than two state of the art models, support vector regression and ARIMA, respectively.

show abstract

Section: Market Minimum Bid Activation Time Activation Frequencymentioning

confidence: 99%

Exploiting Artificial Neural Networks for the Prediction of Ancillary Energy Market Prices

et al. 2018

View full text Add to dashboard Cite

show abstract

“…In recent years, one of the most popular ways main aim is to carefully and rigorously study the appropriate model which can predict future values seasonal, and irregular influence), which can con through the specific time duration [7]. The AR applications, such as natural environment [8 Autoregressive integrated moving average model e.g., in forecasting tourist traffic at airports [15], in [18], unemployment analysis [19], in studies of e [20,21], and in wind energy and runoff forecasts [22 are also used in fisheries [24] and for the needs of fires, and prognosis of tree diseases [25]. Autoregre used in studying sea coastal zones, e.g., for foreca and in zooplankton studies [29].…”

Section: Estimation Of Parameters and Diagnostic Testing Of Modelsmentioning

confidence: 99%

“…It has three control constants seasonal, and irregular influence), which can control and manage influence of time segme through the specific time duration [7]. The ARIMA models are now widely used for applications, such as natural environment [8][9][10][11], medicine [12], and engineering Autoregressive integrated moving average modelling is often used in many areas of the ec e.g., in forecasting tourist traffic at airports [15], in road transport [16,17], in real estate price a [18], unemployment analysis [19], in studies of electricity consumption and their price fo [20,21], and in wind energy and runoff forecasts [22,23]. Short-term forecasts using the ARIMA are also used in fisheries [24] and for the needs of forestry, such as the prediction of drought fires, and prognosis of tree diseases [25].…”

mentioning

confidence: 99%

Time Decomposition and Short-Term Forecasting of Hydrometeorological Conditions in the South Baltic Coastal Zone of Poland

Tylkowski

Hojan

2019

Geosciences

View full text Add to dashboard Cite

This article presents an analysis of time-series for hydrometeorological conditions determining the behavior of the natural environment in the South Baltic coastal zone of Poland. The analysis is based on monthly data for average air temperature, total atmospheric precipitation, and average sea level during the 50-year period from 1966–2015 for three coastal stations in Hel, Ustka, and Świnoujście. Time decomposition of these hydrometeorological conditions and formulation of short-term forecasts were carried out using ARIMA modelling. This study identifies the seasonal and non-seasonal parameters that determine both current and future hydrometeorological conditions. Moreover, it indicates the spatial differences among features of the analyzed time-series, estimated parameters of the selected models, and forecasts. The ARIMA models used for the Polish Baltic coastal zone are somewhat spatially homogenous. This is especially true of the models for average monthly air temperature, which are identical across the entire coastal zone (2,0,1)(2,1,0)12. Very similar are the models for average monthly sea level across the central and west coast (1,0,0)(1,1,0)12. The model for the east coast, however, was determined to be slightly different (2,0,2)(2,1,0)12. In contrast to those for air temperature and sea level, the models used for atmospheric precipitation were different for each site. Among the parameters modelled, the effect of AR(p) processes was greater than that of MA(q) processes. The monthly models for Ustka are an example of this: average air temperature (2,0,1)(2,1,0)12, atmospheric precipitation (0,0,3)(2,1,0)12, and average sea level (1,0,0)(1,1,0)12. Time decomposition of extreme hydrometeorological conditions has an important utilitarian significance. The climate of the Polish Baltic coastal zone is getting warmer, the sea level is rising, and the frequency of extreme hydrometeorological events is increasing. Time decomposition of hydrometeorological conditions based on monthly data did not reveal long-term trends. In the last half-century, hydrometeorological conditions have been conducive to erosion of coastal dunes and cliffs. These factors determine changes in the natural environment and limit the development potential of the coastal zone. The time decomposition, modelling, and forecasting of hydrometeorological conditions are thus very important for many areas of human activity, especially those related to management, protection, and development of the coast.

show abstract

“…For the conventional time-series statistical method, it holds the assumption that the electricity price has linear relationship with its influencing factors. This kind of forecasting technique mainly includes the auto-regressive integrated moving average (ARIMA) [6][7][8] method and generalized autoregressive conditional heteroscedasticity (GARCH) [9][10][11]. However, in fact, the relationships between electricity price and its influencing factors are not linear.…”

Section: Introductionmentioning

confidence: 99%

A Novel Hybrid BND-FOA-LSSVM Model for Electricity Price Forecasting

Guo

Zhao

2017

Information

View full text Add to dashboard Cite

Accurate electricity price forecasting plays an important role in the profits of electricity market participants and the healthy development of electricity market. However, the electricity price time series hold the characteristics of volatility and randomness, which make it quite hard to forecast electricity price accurately. In this paper, a novel hybrid model for electricity price forecasting was proposed combining Beveridge-Nelson decomposition (BND) method, fruit fly optimization algorithm (FOA), and least square support vector machine (LSSVM) model, namely BND-FOA-LSSVM model. Firstly, the original electricity price time series were decomposed into deterministic term, periodic term, and stochastic term by using BND model. Then, these three decomposed terms were forecasted by employing LSSVM model, respectively. Meanwhile, to improve the forecasting performance, a new swarm intelligence optimization algorithm FOA was used to automatically determine the optimal parameters of LSSVM model for deterministic term forecasting, periodic term forecasting, and stochastic term forecasting. Finally, the forecasting result of electricity price can be obtained by multiplying the forecasting values of these three terms. The results show the mean absolute percentage error (MAPE), root mean square error (RMSE) and mean absolute error (MAE) of the proposed BND-FOA-LSSVM model are respectively 3.48%, 11.18 Yuan/MWh and 9.95 Yuan/MWh, which are much smaller than that of LSSVM, BND-LSSVM, FOA-LSSVM, auto-regressive integrated moving average (ARIMA), and empirical mode decomposition (EMD)-FOA-LSSVM models. The proposed BND-FOA-LSSVM model is effective and practical for electricity price forecasting, which can improve the electricity price forecasting accuracy.

show abstract

Comparison of ARIMA and ANN Models Used in Electricity Price Forecasting for Power Market

Cited by 28 publications

References 7 publications

Exploiting Artificial Neural Networks for the Prediction of Ancillary Energy Market Prices

Exploiting Artificial Neural Networks for the Prediction of Ancillary Energy Market Prices

Time Decomposition and Short-Term Forecasting of Hydrometeorological Conditions in the South Baltic Coastal Zone of Poland

A Novel Hybrid BND-FOA-LSSVM Model for Electricity Price Forecasting

Contact Info

Product

Resources

About