Chaotic Time Series Prediction Using LSTM with CEEMDAN

Guo, Yanan; Xiaoqun, Cao; Liu, Bainian; Peng, Kecheng

doi:10.1088/1742-6596/1617/1/012094

Cited by 15 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The load data sequence of the 5G base station has nonlinear spatiotemporal and other periodic characteristics, so the load data sequence can be regarded as the superposition of various frequency sequences. From the viewpoint of prediction, it can be seen that, when there are fluctuating and periodic characteristics of the sequences with different frequencies, the data sequence has a strong prediction ability [25]. In order to realize the accurate prediction of short-term electricity load data in the past few days, it is firstly necessary to decompose the base station load data sequence according to different frequency characteristics, then construct the load prediction model according to the load sequence of different frequency characteristics, and finally obtain the overall base station load prediction results through the superposition of decomposed sequences.…”

Section: Ceemdan Data Processing Frameworkmentioning

confidence: 99%

“…When constructing load prediction models, the introduction of deep learning networks can reveal the load characteristics more essentially. For example, Guo et al combined CEEMDAN with long short-term memory (LSTM) to reduce the difficulty of predicting chaotic time series and improve prediction accuracy [25]. Zou et al combined CEEMDAN, singular spectrum analysis (SSA), and phase space reconstruction (PSR) to achieve higher multilevel prediction accuracy [26].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid load prediction model of 5G base station based on time series decomposition and GRU network with parameter optimization

Hua,

Sun,

2024

IET Generation Trans & Dist

View full text Add to dashboard Cite

To ensure the safe and stable operation of 5G base stations, it is essential to accurately predict their power load. However, current short‐term prediction methods are rarely applied rationally in pertinent circumstances to the features of base station power load over time. For high accuracy and generalization capabilities, this work proposes a hybrid approach that combines gated recurrent unit (GRU) with particle swarm optimization (PSO) and completes ensemble empirical mode decomposition with adaptive noise (CEEMDAN). The complex load is decomposed into multiple components to improve the fit of the neural network. To deal with the nonlinearity that constrains the modal aliasing and data noise, CEEMDAN is used to reconstruct the trend and noise sequences. The GRU network is utilized to improve the neural network fitness and obtain long‐term features. In addition, PSO is used to optimize the number of neurons and the learning rate of the GRU. Compared with existing neural network GRUs, the RMSE is reduced by 16.6, the mean absolute error is reduced by 11.97, and the coefficient of R2 is improved by 0.13, indicating that the model has a better fitting effect. The comparisons prove that the proposed model has better accuracy than the existing methods.

show abstract

Section: Ceemdan Data Processing Frameworkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hybrid load prediction model of 5G base station based on time series decomposition and GRU network with parameter optimization

Hua,

Sun,

2024

IET Generation Trans & Dist

View full text Add to dashboard Cite

show abstract

“…This chaotic system plays an important role in complex mathematics-based subjects, such as the atmosphere, aerospace engineering, finance, etc. [1] Additionally, research on this complex system in recent years has mainly focused on how to improve the prediction accuracy [1][2][3]. Thus, in this era of big data, scholars are keen to use machine learning and deep learning for predicting stock prices and its trends which is concluded in chaotic system for recent research trends in prediction [4].…”

Section: Introductionmentioning

confidence: 99%

A stacked forecasting model-CEEMDAN-BPMs model

2022

AJCIS

View full text Add to dashboard Cite

For the predictive effects of individual models vary, unlike conventional implementations, this paper presents a new more comprehensive approach-CEEMDAN-BPMs model, which aim to the goal to the accuracy improvement of stock price forecasting, especially interesting for analysis nonlinear and nonstationary financial time series. This paper introduced a new model, that is BPMs model, furthermore, this new model is applied to financial time series prediction for high frequency data and low frequency data respectively. The key idea on the BPMs model relies on method of weighted linear stacking. Based on this new model with two decomposition method empirical mode decomposition (EMD) and complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) are proposed in this paper. The paper employs the indicator mean absolute percentage error(MAPE), mean absolute error(MAE), mean square error(MSE)and correlation coefficient evaluation criterion and empirical results present that forecasting effects of new model CEEMDAN-BPMs is optimal in forecasting.

show abstract

“…Reference [28]also indicated that EEMD can reduce the prediction error. Guo et al [39] proposed hybrid models based on deep learning methods and CEMMDAN have great potential in the field of traffic flow prediction. VMD is the state-of-theart decomposition algorithm, which is seldom employed in the field of short-time traffic flow prediction.…”

Section: Introductionmentioning

confidence: 99%

Effect of Multi-Scale Decomposition on Performance of Neural Networks in Short-Term Traffic Flow Prediction

et al. 2021

View full text Add to dashboard Cite

Numerous studies employ multi-scale decomposition to improve the prediction performance of neural networks, but the grounds for selecting the decomposition algorithm are not explained, and the effects of decomposition algorithms on other performance of neural networks are also lacking further study. This paper studies the influence of commonly used multi-scale decomposition algorithms including EMD (Empirical Mode Decomposition), EEMD(Ensemble Empirical Mode Decomposition), CEEMDAN (Complete Ensemble Empirical Mode Decomposition with Adaptive Noise), VMD (Variational Mode Decomposition), WD (Wavelet Decomposition), and WPD (Wavelet Packet Decomposition) on the performance of Neural Networks. Decomposition algorithms are adopted to decompose traffic flow data into component signals, and then K-means is used to cluster component signals into volatility components, periodic components, and residual components. A Bi-directional LSTM (BiLSTM) neural network is adopted as the standard model for training and forecasting. Finally, three metrics, including prediction performance, robustness, and generalization performance are proposed to evaluate the influence of the multi-scale decomposition algorithm for neural networks comprehensively. By comparing the evaluation results of different hybrid models, this study provides some useful suggestions on proper multi-scale decomposition algorithm selection in short-time traffic flow prediction.

show abstract

Chaotic Time Series Prediction Using LSTM with CEEMDAN

Cited by 15 publications

References 15 publications

Hybrid load prediction model of 5G base station based on time series decomposition and GRU network with parameter optimization

Hybrid load prediction model of 5G base station based on time series decomposition and GRU network with parameter optimization

A stacked forecasting model-CEEMDAN-BPMs model

Effect of Multi-Scale Decomposition on Performance of Neural Networks in Short-Term Traffic Flow Prediction

Contact Info

Product

Resources

About