Energy Load Forecasting Using Empirical Mode Decomposition and Support Vector Regression

Ghelardoni, Luca; Ghio, Alessandro; Anguita, Davide

doi:10.1109/tsg.2012.2235089

Cited by 191 publications

(63 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Factors which influence the electricity consumption are recognized and the mapping relation between key factors and electricity consumption are mined [25,26]. Ghelardoni et al [27] use the empirical mode decomposition method to divide the time series into two parts, describing the trend and the local oscillation of energy consumption values, respectively, and then use them to train the support vector regression model. Che et al [28] use the human knowledge to construct fuzzy membership functions for each similar subgroup and then build an adaptive fuzzy comprehensive model based on self-organizing mapping, support vector machine, and fuzzy reasoning for prediction.…”

Section: Related Workmentioning

confidence: 99%

Predicting Short-Term Electricity Demand by Combining the Advantages of ARMA and XGBoost in Fog Computing Environment

Zheng

Yang

et al. 2018

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

With the rapid development of IoT, the disadvantages of Cloud framework have been exposed, such as high latency, network congestion, and low reliability. Therefore, the Fog Computing framework has emerged, with an extended Fog Layer between the Cloud and terminals. In order to address the real-time prediction on electricity demand, we propose an approach based on XGBoost and ARMA in Fog Computing environment. By taking the advantages of Fog Computing framework, we first propose a prototypebased clustering algorithm to divide enterprise users into several categories based on their total electricity consumption; we then propose a model selection approach by analyzing users' historical records of electricity consumption and identifying the most important features. Generally speaking, if the historical records pass the test of stationarity and white noise, ARMA is used to model the user's electricity consumption in time sequence; otherwise, if the historical records do not pass the test, and some discrete features are the most important, such as weather and whether it is weekend, XGBoost will be used. The experiment results show that our proposed approach by combining the advantage of ARMA and XGBoost is more accurate than the classical models.

show abstract

Section: Related Workmentioning

confidence: 99%

Predicting Short-Term Electricity Demand by Combining the Advantages of ARMA and XGBoost in Fog Computing Environment

Zheng

Yang

et al. 2018

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…EMD and LMD have been extensively shown as good and popular adaptive methods for processing nonlinear and nonstationary signals. They were widely used in many applications, such as solar radiation forecasting [16], energy load forecasting [22], climate forecasting [23], and time-frequency estimation for electroencephalogram [24]. Because the EMD and LMD have different decomposition mechanisms, the sub-sequences obtained by these two methods also have some differences, which are exactly the description of the original signal from different perspectives.…”

Section: Signal Decompositionmentioning

confidence: 99%

Hourly Solar Radiation Forecasting Using a Volterra-Least Squares Support Vector Machine Model Combined with Signal Decomposition

et al. 2018

View full text Add to dashboard Cite

Accurate solar forecasting facilitates the integration of solar generation into the grid by reducing the integration and operational costs associated with solar intermittencies. A novel solar radiation forecasting method was proposed in this paper, which uses two kinds of adaptive single decomposition algorithm, namely, empirical mode decomposition (EMD) and local mean decomposition (LMD), to decompose the strong non-stationary solar radiation sequence into a set of simpler components. The least squares support vector machine (LSSVM) and the Volterra model were employed to build forecasting sub-models for high-frequency components and low-frequency components, respectively, and the sub-forecasting results of each component were superimposed to obtain the final forecast results. The historical solar radiation data collected on Golden (CO, USA), in 2014 were used to evaluate the accuracy of the proposed model and its comparison with that of the ARIMA, the persistent model. The comparison demonstrated that the superior performance of the proposed hybrid method.

show abstract

“…Classical methods for long-term system load forecasting are mainly in three categories: time series models [2][3][4][5], correlation models [6][7][8][9] and artificial intelligence models [9][10][11][12][13]. Time series models forecast the future load based on the historical load data, so the underlying assumption is that the future load will follow the same trend as its past.…”

Section: Introductionmentioning

confidence: 99%

Long-term system load forecasting based on data-driven linear clustering method

Han

Yan

2017

J. Mod. Power Syst. Clean Energy

View full text Add to dashboard Cite

In this paper, a data-driven linear clustering (DLC) method is proposed to solve the long-term system load forecasting problem caused by load fluctuation in some developed cities. A large substation load dataset with annual interval is utilized and firstly preprocessed by the proposed linear clustering method to prepare for modelling. Then optimal autoregressive integrated moving average (ARIMA) models are constructed for the sum series of each obtained cluster to forecast their respective future load. Finally, the system load forecasting result is obtained by summing up all the ARIMA forecasts. From error analysis and application results, it is both theoretically and practically proved that the proposed DLC method can reduce random forecasting errors while guaranteeing modelling accuracy, so that a more stable and precise system load forecasting result can be obtained.

show abstract

Energy Load Forecasting Using Empirical Mode Decomposition and Support Vector Regression

Cited by 191 publications

References 29 publications

Predicting Short-Term Electricity Demand by Combining the Advantages of ARMA and XGBoost in Fog Computing Environment

Predicting Short-Term Electricity Demand by Combining the Advantages of ARMA and XGBoost in Fog Computing Environment

Hourly Solar Radiation Forecasting Using a Volterra-Least Squares Support Vector Machine Model Combined with Signal Decomposition

Long-term system load forecasting based on data-driven linear clustering method

Contact Info

Product

Resources

About