Ensemble Empirical Model Decomposition Research Articles

A multi-energy load forecasting method based on complementary ensemble empirical model decomposition and composite evaluation factor reconstruction

Ensuring precise multi-energy load forecasting is crucial for the effective planning, management, and operation of Integrated Energy Systems (IES). This study proposes a novel multivariate load forecasting model based on time-series decomposition and reconstruction to handle the complex, high-dimensional multi-energy load data in IES and enhance forecasting accuracy. Initially, the model conducts a thorough correlation analysis and variable screening to minimize irrelevant data interference. It then applies denoising by decomposing the load sequence into modal components with distinct characteristics, using the complementary ensemble empirical mode decomposition (CEEMD). To overcome the unstable prediction accuracy inherent in time-domain decomposition methods, this study introduces an innovative composite evaluation factor (CEF) that reconstructs the modal components after considering their complexity, coupling, and frequency. The final predictions are generated using the proposed MTL-CNN-BiLSTM model, optimized with the attention mechanism. The results show that the proposed model significantly reduces error accumulation compared to traditional time-domain analysis methods, achieving a 37.40% reduction in average forecasting error and a 30.73% increase in forecasting efficiency.

Long Short-Term Memory-Based Twin Support Vector Regression for Probabilistic Load Forecasting.

A probabilistic load forecast that is accurate and reliable is crucial to not only the efficient operation of power systems but also to the efficient use of energy resources. In order to estimate the uncertainties in forecasting models and nonstationary electric load data, this study proposes a probabilistic load forecasting model, namely BFEEMD-LSTM-TWSVRSOA. This model consists of a data filtering method named fast ensemble empirical model decomposition (FEEMD) method, a twin support vector regression (TWSVR) whose features are extracted by deep learning-based long short-term memory (LSTM) networks, and parameters optimized by seeker optimization algorithms (SOAs). We compared the probabilistic forecasting performance of the BFEEMD-LSTM-TWSVRSOA and its point forecasting version with different machine learning and deep learning algorithms on Global Energy Forecasting Competition 2014 (GEFCom2014). The most representative month data of each season, totally four monthly data, collected from the one-year data in GEFCom2014, forming four datasets. Several bootstrap methods are compared in order to determine the best prediction intervals (PIs) for the proposed model. Various forecasting step sizes are also taken into consideration in order to obtain the best satisfactory point forecasting results. Experimental results on these four datasets indicate that the wild bootstrap method and 24-h step size are the best bootstrap method and forecasting step size for the proposed model. The proposed model achieves averaged 46%, 11%, 36%, and 44% better than suboptimal model on these four datasets with respect to point forecasting, and achieves averaged 53%, 48%, 46%, and 51% better than suboptimal model on these four datasets with respect to probabilistic forecasting.

Non-linear long-term trend in volume transport through the Korea/Tsushima Strait

Based on the relation between volume transport and sea level difference across the Korea/Tsushima Strait (KTS), in this study, we estimated the volume transport of the Tsushima Warm Current over the past four decades and examined its long-term trend using an ensemble empirical model decomposition (EEMD) method. The estimated geostrophic transports showed very good agreement with those measured by acoustic Doppler current profiler and those estimated from satellite altimetry-based sea level data. This corroborates the reliability of the long-term estimation. EEMD analysis revealed an acceleration in volume transport in the KTS, with a persistent increase in the trend rate occurring after the mid-1980s. Further analyses indicate that the trend shift in the KTS closely coincided with an upper-ocean warming trend in the East/Japan Sea (EJS) after the mid-1980s. Analyzing large-scale wind patterns suggests that long-term trends of wind stress curls over the North Pacific are likely a key driver of the trend shifts in the inflow through the KTS and the upper-ocean warming in the EJS over the past four decades.

Circadian cycles: A time-series approach


 
 
 The extraction of circadian cycles from experimental data can be interpreted as a specific case of time-series or signal analysis, but chrono- biology and time-series analysis appear to have developed according to separate paths. Whereas some techniques such as continuous (CWT) and discrete wavelet analysis (DWT) are used frequently in rhythmobiology, other specialized methdos such as digital filters, nonlinear mode decomposition (NMD), singular spectrum analysis (SSA), empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD) and complete ensemble empirical model decomposition with adaptive noise (CEEMDAN) have only occasionally been applied. No studies are available that compare the applicability between a wide variety of different methods or for different variables, and this is the purpose of the present contribution. These methods improve the goodness-of-fit of the circadian cycle with respect to the standard approach of cosinor analysis. They have the additional advantage of being able to quantify the day-to-day variability of the circadian parameters of mesor, amplitude, period and acrophase around their average values, with potential clinical applications to distinguish between healthy and unhealthy populations. Finally, the circadian parameters are interpreted within the context of homeostatic regulation with distinctive statistics for regulated and effector variables.
 
 

Forecasting wind speed using a reinforcement learning hybrid ensemble model: a high-speed railways strong wind signal prediction study in Xinjiang, China

Abstract Considering the application of wind-forecasting technology along the railway, it becomes an effective means to reduce the risk of train derailment and overturning. Accurate prediction of crosswinds can provide scientific guidance for safe train operation. To obtain more reliable wind-speed prediction results, this study proposes an intelligent ensemble forecasting method for strong winds along the high-speed railway. The method consists of three parts: the data preprocessing module, the hybrid prediction module and the reinforcement learning ensemble module. First, fast ensemble empirical model decomposition (FEEMD) is used to process the original wind speed data. Then, Broyden-Fletcher-Goldfarb-Shanno (BFGS) method, non-linear autoregressive network with exogenous inputs (NARX) and deep belief network (DBN), three benchmark predictors with different characteristics are employed to build prediction models for all the sublayers of decomposition. Finally, Q-learning is utilized to iteratively calculate the combined weights of the three models, and the prediction results of each sublayer are superimposed to obtain the model output. The real wind speed data of two railway stations in Xinjiang are used for experimental comparison. Experiments show that compared with the single benchmark model, the hybrid ensemble model has better accuracy and robustness for wind speed prediction along the railway. The 1-step forecasting results mean absolute error (MAE), mean absolute percentage error (MAPE) and root mean square error (RMSE) of Q-learning-FEEMD-BFGS-NARX-DBN in site #1 and site #2 are 0.0894 m/s, 0.6509%, 0.1146 m/s, and 0.0458 m/s, 0.2709%, 0.0616 m/s, respectively. The proposed ensemble model is a promising method for railway wind speed prediction.

Electrometallurgical Load Forecasting Based on Ensemble Learning Using CEEMDAN

Accurate load forecasting is conducive to stable power supply. It is difficult to forecast electrometallurgical load. It tends to fluctuate rapidly and randomly, especially for the ultra-short-term ones. In this work, we decompose the load into components and abstracting them with heterogeneous learners for the different characteristics. Complete ensemble empirical model decomposition adaptive noise (CEEMDAN) is introduced to data pre-treatment and signal decomposition, and different frequency sub-series are obtained. Then, we explore the complexity of sub-series by sample entropy (SE). For the low-frequency components, a low-complexity Random Forest (RF) model is designed for drawing the outline of the load fluctuating. For the high-frequency ones, a long short-term memory (LSTM) network is adopted to get the details of the fluctuating. Combined forecasting is implemented by reconstructing the predictions of the above two learners. The novel model is compared with several common models for electrometallurgical load forecasting by using industrial data of an electro-fused magnesium enterprise. Experimental results show that the proposal significantly outperforms the others.

Spatial and temporal characteristics of surface solar radiation in China and its influencing factors

The total-sky direct solar radiation at Earth’s surface (SRS) not only has an important impact on the earth’s climate and ecology, but also is a crucial parameter for solar photovoltaic power. SRS determines whether photovoltaic power plants can be built in the region and directly affects the efficiency of photovoltaic power generation. Therefore, the spatial and temporal distribution characteristics of SRS have a very important guiding significance for the construction of photovoltaic power stations. This study discusses the temporal and spatial characteristics of SRS and its influencing factors in China during 1961–2020 using ERA5 data and the empirical orthogonal function (EOF), rotated empirical orthogonal function (REOF), and ensemble empirical model decomposition (EEMD) methods. Our investigation reveals that the high-value SRS center is located on the southwestern Tibetan Plateau, while the low-value center occurs on the northeastern Yunnan–Guizhou Plateau and in the Sichuan Basin. Seasonal variability in SRS means that maximum values occur uniformly in summer, followed sequentially by spring, autumn, and winter. The spatial distribution of the leading SRS EOF mode exhibits a dipole pattern between the southern Tibetan Plateau and other regions. Combined with the time series, SRS in China underwent an interdecadal transition around the year 2000. The regression analysis shows that this pattern is mainly affected by surface air temperature, total precipitation, relative humidity and cloud cover. The time series evolution of SRS primarily reflects the interannual variability in annual-mean and four seasons; the variance contributions of decadal variability and secular trend are minor through the EEMD. The REOF separates Chinese SRS into 11 central regions, the top 5 being the western Tibetan Plateau, western Northwest China, the eastern Tibetan Plateau, northern Xinjiang, and North China. The relationship between SRS and meteorological parameters shows that SRS is positively correlated with surface air temperature and wind speed but negatively correlated with total precipitation, relative humidity, low and total cloud cover, and aerosol concentrations.

A Hybrid ARIMA-GABP Model for Predicting Sea Surface Temperature

Sea surface temperature (SST) is one of the most important parameters in air–sea interaction, and its accurate prediction is of great significance in the study of global climate change. However, SST is affected by heat flux, ocean dynamic processes, cloud coverage, and other factors, which means it contains linear and nonlinear components. Existing prediction models, especially single prediction models, cannot effectively handle these linear and nonlinear components in the meantime, degrading their accuracy concerning the prediction of SST. To remedy this weakness, this paper proposes a novel prediction model by the Lagrange multiplier method to combine the auto-regressive integrated moving average (ARIMA) model and the back propagation (BP) neural network model, where these two models have superior prediction performance for linear and nonlinear components, respectively. Moreover, the genetic algorithm is exploited to construct the genetic algorithm BP (GABP) neural network to further improve the performance of the proposed model. To verify the effectiveness of the proposed model, experiments predicting the SST based on historic time-series data are performed. The experiment results indicate that the mean absolute error (MAE) of the ARIMA-GABP model is only 0.3033 °C and the root mean square error (RMSE) is 0.3970 °C, which is better than the ARIMA model, BP neural network model, long short-term memory (LSTM) model, GABP neural network model, and ensemble empirical model decomposition BP model among various datasets. Therefore, the proposed model has superior and robust performance concerning predicting SST.

Gas Concentration Prediction Based on IWOA-LSTM-CEEMDAN Residual Correction Model.

In this study, to further improve the prediction accuracy of coal mine gas concentration and thereby preventing gas accidents and improving coal mine safety management, the standard whale optimisation algorithm’s (WOA) susceptibility to falling into local optima, slow convergence speed, and low prediction accuracy of the single-factor long short-term memory (LSTM) neural network residual correction model are addressed. A new IWOA-LSTM-CEEMDAN model is constructed based on the improved whale optimisation algorithm (IWOA) to improve the IWOA-LSTM one-factor residual correction model through the use of the complete ensemble empirical model decomposition with adaptive noise (CEEMDAN) method. The population diversity of the WOA is enhanced through multiple strategies and its ability to exit local optima and perform global search is improved. In addition, the optimal weight combination model for subsequence is determined by analysing the prediction error of the intrinsic mode function (IMF) of the residual sequence. The experimental results show that the prediction accuracy of the IWOA-LSTM-CEEMDAN model is higher than that of the BP neural network and the GRU, LSTM, WOA-LSTM, and IWOA-LSTM residual correction models by 47.48%, 36.48%, 30.71%, 27.38%, and 12.96%, respectively. The IWOA-LSTM-CEEMDAN model also achieves the highest prediction accuracy in multi-step prediction.

An improved typical meteorological year based on outdoor climate comprehensive description method

In order to further reduce the impact of climate fluctuations on the typical meteorological year (TMY) database, this paper introduces an ensemble empirical model decomposition method to extract the periodic fluctuation and random fluctuation data from outdoor climate data separately, and to construct a comprehensive description parameter that eliminates the influence of random fluctuation data. An innovative TMY based on the comprehensive description parameter was developed in six selected cities of different climate zones in China. Compared with the existing Chinese TMY development method and outdoor design parameters, it is found that the typical meteorological months (TMMs) of each city and the outdoor design parameters from the improved TMY database have changed to a certain extent. Through the correlation analysis between improved TMY database and the cumulative long-average meteorological data, it reveals that the improved TMY can better describe the local average climatic characteristics. Finally, this paper discusses the impact of the improved TMY on the building heat loss index and outdoor thermal comfort in different building shapes. The results demonstrate that the energy demand and outdoor thermal comfort analysis based on the improved TMY are closer to long-term averaged outdoor climate, and the calculation deviations compared with conventional method are reduced by 1.18%–21.08% and 53.42%–76.82% respectively. This research will refine outdoor climate data for building design and analysis.

Short-term wind speed forecasting based on long short-term memory and improved BP neural network

Accurate and reasonable wind speed prediction system has a significant impact on the utilization of wind energy. A novel combination forecasting model based on Long Short-Term Memory (LSTM) network and BP neural network is designed in this paper. This model combines the principle of deep learning algorithm and the improved BP neural network to deal with nonlinear wind speed prediction. Before the prediction, singular spectrum analysis (ssa) and complete ensemble empirical model decomposition adaptive noise (CEEMDAN) are selected as the data pretreatment part to de-noise the original wind speed data and decompose it into multiple components. This part is conducive to improving the signal-to-noise ratio (SNR) of wind speed data and simplifying the characteristics of wind speed data. Then, in order to reduce the error accumulation and computation redundancy, fuzzy entropy (FE) is used to calculate the time complexity of each component, according to the Spearman correlation, the inherent mode function (IMF) components are recombined to form a new subsequence. Experimental results show that the error accumulation can be reduced by 48.65% for dataset 1 and 29.53% for dataset 2, and the operation time can be reduced by about 50% for two datasets. To avoid the limitation of a single model, introducing the LSTM and improved BPNN which improved by sparrow search algorithm (SSA) two different prediction models are used to predict the sub sequences with high complexity and the low complexity subsequences, respectively. Finally, the predicted values of the models are superimposed to get the final values. In order to verify the validity of the proposed model, the final predictions, compared with six different prediction models, show that this model can achieve the best performance and obtain higher prediction accuracy. Such as the performance evaluation indexes (RMSE = 0.051, MAPE = 0.929%) are smallest obtained from dataset1 by one-step prediction, and (RMSE = 0.086, MAPE = 0.966%) are smallest obtained from dataset2 by one-step prediction. In addition, the Pearson correlation between the predicted value and the true wind speed value obtained by the prediction model applied to the two data sets is the highest 99.17% and 98.73%, respectively.

Handling Data Heterogeneity in Electricity Load Disaggregation via Optimized Complete Ensemble Empirical Mode Decomposition and Wavelet Packet Transform

Global warming is a leading world issue driving the common social objective of reducing carbon emissions. People have witnessed the melting of ice and abrupt changes in climate. Reducing electricity usage is one possible method of slowing these changes. In recent decades, there have been massive worldwide rollouts of smart meters that automatically capture the total electricity usage of houses and buildings. Electricity load disaggregation (ELD) helps to break down total electricity usage into that of individual appliances. Studies have implemented ELD models based on various artificial intelligence techniques using a single ELD dataset. In this paper, a powerline noise transformation approach based on optimized complete ensemble empirical model decomposition and wavelet packet transform (OCEEMD–WPT) is proposed to merge the ELD datasets. The practical implications are that the method increases the size of training datasets and provides mutual benefits when utilizing datasets collected from other sources (especially from different countries). To reveal the effectiveness of the proposed method, it was compared with CEEMD–WPT (fixed controlled coefficients), standalone CEEMD, standalone WPT, and other existing works. The results show that the proposed approach improves the signal-to-noise ratio (SNR) significantly.

Integrated bidding strategy of distributed energy resources based on novel prediction and market model

This paper presents an integrated operation model of renewable energy, distributed generators (DGs), energy storage, and demand response to overcome the challenges of renewable energy market participation. Additionally, an accurate prediction model for wind, photovoltaic (PV) power, and market price is introduced based on ensemble empirical model decomposition. In this model, radial basis function neural network (RBFNN) is used for the forecasting of subsignals from the analysis model. The training model of RBFNN is shaped based on the B-water cycle algorithm (WCA) optimization method. Additionally, by considering the adjusted market, demand response, and uncertainties analysis, this method reduced the economic damages of generators and loads. A case study test has consisted of a wind turbine, photovoltaic energy, fuel cell energy, demand response, and energy storage.

Forecasting oil production using ensemble empirical model decomposition based Long Short-Term Memory neural network

Oil production forecasting is an important means of understanding and effectively developing reservoirs. Reservoir numerical simulation is the most mature and effective method for production forecasting, but its accuracy mostly depends on high-quality history matching and accurate geological models. In order to achieve fast and accurate production predicting, an ensemble empirical mode decomposition (EEMD) based Long Short-Term Memory (LSTM) learning paradigm is proposed for oil production forecasting. In this paper, the original oil production series are first split into training set and test set. The data of test set is gradually added to the training set and decomposed by EEMD to obtain multiple intrinsic mode functions (IMFs). The stability of IMFs is analyzed by its Means and curve similarity computed by Dynamic time warping (DTW). Then proper number of stable IMFs are selected as predictor variables for machine learning. Considering the variation trend and context information of production series, LSTM is utilized to establish predictive model for production forecasting. The optimal hyper-parameters of LSTM are determined by Genetic algorithm (GA). For evaluation and verification purpose, the proposed model is applied to two actual oilfields from China. Empirical results demonstrated that the proposed approach is capable of giving almost perfect production forecasting.

Short-Term Wind Speed Forecasting With Principle-Subordinate Predictor Based on Conv-LSTM and Improved BPNN

To improve the accuracy of short term wind speed forecasting, a novel principle-subordinate prediction model based on Conv-LSTM network and BPNN is designed in this paper. The proposed model combines deep learning algorithms and improved neural network to deal with the problem of wind speed forecasting. In this model, the prediction sequence of each subseries is obtained by Conv-LSTM to form more smoother and characteristic series; the BPNN, optimized by MWOA (Modified Whale Optimization Algorithm), is trained with the reconstruction sequence, which processed for the prediction sequence by invert-EMD (inverse empirical model decomposition). Before prediction, singular spectrum analysis (SSA) and complete ensemble empirical model decomposition adaptive noise (CEEMDAN) are adopted to de-noise and decompose the original wind speed data into several subseries. This process is beneficial to improve the ratio of signal to noise and simply the features of wind speed data. In addition, the Conv-LSTM is tested on three datasets, the results proved that data process is advantaged to obtain higher quality wind speed datasets, and convolutional layer can deep extract the characteristics of each subseries, it can facilitate LSTM to make accurate prediction. The final prediction results, compared with other five different models, demonstrate that the proposed model can achieve higher precision. Such as the performance evaluation matrix (MAPE = 2.62%, RMSE = 0.151) are smallest obtained from experiments on three wind different wind speed datasets.

Assessment of mutual fund performance based on Ensemble Empirical Mode Decomposition

This study analyzes mutual fund performance in three different time scales. The mutual fund return time series is decomposed by ensemble empirical model decomposition method, which is a data analysis method, especially for processing nonstationary and nonlinear time series, into three time-scales, namely, short cycle, long cycle and trend, which have different meaning on mutual fund management. Short cycle represents the temporary volatility of the market and long cycle represents the operation circle of the mutual fund and trend represents the development tendency of the fund. The mutual funds are also divided into equity, bond, and mixture funds according to portfolio types. The performances of the three fund types are analyzed. The data set, having 2600 mutual funds, in this study is relatively large compared with that in other researches. Result shows that the bond and mixture funds have different management strategies from that of the equity fund, which means that, to seek excess profit, the equity fund focuses on short-cycle management and tends to ignore the long-cycle management, whereas the bond and mixture funds focus on long-cycle management and take less care on short-cycle management. In short cycle, all three sorts of funds are making excess profit through taking market system risk and have no significant performance on α return; in long cycle and trend, they seek excess profit through acquiring more α return. The assessment indices used to assess fund performance confirm the differences in the three fund’s management strategies.

Train Wheelset Bearing Multifault Impulsive Component Separation Using Hierarchical Shift‐Invariant Dictionary Learning

A wheelset bearing is a crucial energy transmission element in high‐speed trains. Any parts of the wheelset bearing that have faults may endanger the safety of the railway service. Therefore, it is important to monitor the running condition of a wheelset bearing. The multifault on a wheelset bearing is very common, and these impulsive components generated by different types of faults may interact with each other, which increases the difficulty of entirely identifying those faults. To solve the multifault problem, this paper proposed a hierarchical shift‐invariant K‐means singular value decomposition (H‐SI‐K‐SVD) to hierarchically separate those multifault impulsive components based on their fault power levels. Each of the separated impulse signals contains only one fault impulse, and the fault information could be highlighted both in time domain and frequency domain. In addition, the sparsity of envelope spectrum (SES) is introduced as an indicator to adaptively tune a key parameter in this method. The effectiveness of the proposed method is verified by both simulation and experimental signals. Compared with ensemble empirical model decomposition (EEMD), the proposed method exhibits better performance in separating the multifault impulsive components and detecting the faults of a wheelset bearing.

Prediction of atrial fibrillation recurrence before catheter ablation using an adaptive nonlinear and non-stationary surface ECG analysis

The recurrence rate of atrial fibrillation (AF) following catheter ablation is high. Successful non-recurrence prediction before ablation is financially and physically beneficial. Atrial fibrillation cycle length (AFCL) has been used for such predictions. The study explored a nonlinear and non-stationary signal analysis technique, ensemble empirical model decomposition (EEMD), to capture intrinsic AFCL pattern. Twenty-eight AF patients underwent regular catheter ablation protocols and follow-up treatments. Surface ECG were recorded before ablation procedures, and preprocessed with QRS-T cancellation method to extract intrinsic AF signals, which were then analyzed with EEMD to calculate AFCL adaptively. Conventional Fourier-based dominant frequency (DF) analysis was conducted for comparison. During 12 months follow-up, 17 patients maintained sinus rhythm while 11 patients had AF recurrence. Patients who maintained sinus rhythm had longer AFCL (152.2 (145.0, 157.6) ms) than those with AF recurrence (138.8 (135.0, 145.2) ms). Patients with AFCL >152.1 ms had no recurrence (Kaplan–Meier curve analysis, P=0.006, hazard ratio: 5.68). With AFCL as a predictor of AF non-recurrence at 12 months, the area under ROC curve is 0.80, while with DF analysis, the area is 0.66. EEMD-based intrinsic AFCL measured from surface ECG may serve as an effective non-invasive catheter ablation screening tool for AF non-recurrence.

A Hybrid Model Equipped with the Minimum Cycle Decomposition Concept for Short-Term Forecasting of Electrical Load Time Series

Electricity load forecasting is an essential, however complicated work. Due to the influence of a large number of uncertain factors, it shows complicated nonlinear combination features. Therefore, it is difficult to improve the prediction accuracy and the tremendous breadth of applicability especially for using a single method. In order to improve the performance including accuracy and applicability of electricity load forecasting, in this paper, a concept named minimum cycle decomposition (MCD) that the raw data are grouped according to the minimum cycle was proposed for the first time. In addition, a hybrid prediction model (HMM) based on one-order difference, ensemble empirical model decomposition (EEMD), mind evolutionary computation (MEC) and wavelet neural network (WNN) was also proposed in this study. The HMM model consists of two parts. Part one, pre-processing, known as one order difference to remove the trend of subsequence and EEMD to reduce the noise, was performed by HMM model on each subset. Part two, the WNN optimized by MEC (WNN + MEC) was applied on resultant subseries. Finally, a number of different models were used as the comparative experiment to validate the effectiveness of the presented method, such as back propagation neural network (BP-1), BPNN combined MCD (BP-2), WNN combined MCD (WNNM), a HMM (DEEPLSSVM) based on one-order difference, EEMD, particle swarm optimization and least squares support vector machine and a hybrid model (DEESGRNN) based on one-order difference, EEMD, simulate anneal and generalized regression neural network. Certain evaluation measurements are taken into account to assess the performance. Experiments were carried out on QLD (Queensland) and NSW (New South Wales) electricity markets historical data, and the experimental results show that the MCD has the advantages of improving model accuracy and of generalization ability. In addition, the simulation results also suggested that the proposed hybrid model has better performance.

Gold price analysis based on ensemble empirical model decomposition and independent component analysis

In recent years, the increasing level of volatility of the gold price has received the increasing level of attention from the academia and industry alike. Due to the complexity and significant fluctuations observed in the gold market, however, most of current approaches have failed to produce robust and consistent modeling and forecasting results. Ensemble Empirical Model Decomposition (EEMD) and Independent Component Analysis (ICA) are novel data analysis methods that can deal with nonlinear and non-stationary time series. This study introduces a new methodology which combines the two methods and applies it to gold price analysis. This includes three steps: firstly, the original gold price series is decomposed into several Intrinsic Mode Functions (IMFs) by EEMD. Secondly, IMFs are further processed with unimportant ones re-grouped. Then a new set of data called Virtual Intrinsic Mode Functions (VIMFs) is reconstructed. Finally, ICA is used to decompose VIMFs into statistically Independent Components (ICs). The decomposition results reveal that the gold price series can be represented by the linear combination of ICs. Furthermore, the economic meanings of ICs are analyzed and discussed in detail, according to the change trend and ICs’ transformation coefficients. The analyses not only explain the inner driving factors and their impacts but also conduct in-depth analysis on how these factors affect gold price. At the same time, regression analysis has been conducted to verify our analysis. Results from the empirical studies in the gold markets show that the EEMD–ICA serve as an effective technique for gold price analysis from a new perspective.