Deep learning systems for forecasting the prices of crude oil and precious metals DOI Creative Commons
Parisa Foroutan, Salim Lahmiri

Financial Innovation, Год журнала: 2024, Номер 10(1)

Опубликована: Июль 16, 2024

Abstract Commodity markets, such as crude oil and precious metals, play a strategic role in the economic development of nations, with prices influencing geopolitical relations global economy. Moreover, gold silver are argued to hedge stock cryptocurrency markets during market downsides. Therefore, accurate forecasting metals is critical. Nevertheless, due nonlinear nature, substantial fluctuations, irregular cycles predicting their challenging task. Our study contributes commodity price literature by implementing comparing advanced deep-learning models. We address this gap including alongside our analysis, offering more comprehensive understanding metal markets. This research expands existing knowledge provides valuable insights into prices. In study, we implemented 16 deep- machine-learning models forecast daily West Texas Intermediate (WTI), Brent, gold, The employed long short-term memory (LSTM), BiLSTM, gated recurrent unit (GRU), bidirectional units (BiGRU), T2V-BiLSTM, T2V-BiGRU, convolutional neural networks (CNN), CNN-BiLSTM, CNN-BiGRU, temporal network (TCN), TCN-BiLSTM, TCN-BiGRU. compared performance baseline random forest, LightGBM, support vector regression, k-nearest neighborhood using mean absolute error (MAE), percentage error, root squared evaluation criteria. By considering different sliding window lengths, examine results reveal that TCN model outperforms others for WTI, silver, achieving lowest MAE values 1.444, 1.295, 0.346, respectively. BiGRU performs best an 15.188 30-day input sequence. Furthermore, LightGBM exhibits comparable best-performing overall. These findings critical investors, policymakers, mining companies, governmental agencies effectively anticipate trends, mitigate risk, manage uncertainty, make timely decisions strategies regarding oil,

Язык: Английский

Long Short-Term Memory Network-Based Metaheuristic for Effective Electric Energy Consumption Prediction DOI Creative Commons

Simran Kaur Hora,

P Rachana,

Rocío Pérez de Prado

и другие.

Applied Sciences, Год журнала: 2021, Номер 11(23), С. 11263 - 11263

Опубликована: Ноя. 27, 2021

The Electric Energy Consumption Prediction (EECP) is a complex and important process in an intelligent energy management system its importance has been increasing rapidly due to technological developments human population growth. A reliable accurate model for EECP considered key factor appropriate policy. In recent periods, many artificial intelligence-based models have developed perform different simulation functions, engineering techniques, optimal forecasting order predict future demands on the basis of historical data. this article, new metaheuristic based Long Short-Term Memory (LSTM) network proposed effective EECP. After collecting data sequences from Individual Household Power (IHEPC) dataset Appliances Load (AEP) dataset, refinement accomplished using min-max standard transformation methods. Then, LSTM with Butterfly Optimization Algorithm (BOA) BOA used select hyperparametric values which precisely describe EEC patterns discover time series dynamics domain. This extensive experiment conducted IHEPC AEP datasets shows that obtains minimum error rate relative existing models.

Язык: Английский

Процитировано

136
Machine Learning-Based Digital Twin for Predictive Modeling in Wind Turbines DOI Creative Commons
Muhammad Fahim, Vishal Sharma, Tuan-Vu Cao

и другие.

IEEE Access, Год журнала: 2022, Номер 10, С. 14184 - 14194

Опубликована: Янв. 1, 2022

Wind turbines are one of the primary sources renewable energy, which leads to a sustainable and efficient energy solution. It does not release any carbon emissions pollute our planet. The wind farms monitoring power generation prediction is complex problem due unpredictability speed. Consequently, it limits decision management team plan consumption in an effective way. Our proposed model solves this challenge by utilizing 5G-Next Generation-Radio Access Network (5G-NG-RAN) assisted cloud-based digital twins’ framework virtually monitor form predictive forecast speed predict generated power. developed based on Microsoft Azure twins infrastructure as 5-dimensional platform. modeling deep learning approach, temporal convolution network (TCN) followed non-parametric k-nearest neighbor (kNN) regression. Predictive has two components. First, processes univariate time series data its Secondly, estimates for each quarter year ranges from week whole month (i.e., medium-term prediction) To evaluate experiments performed onshore publicly available datasets. obtained results confirm applicability framework. Furthermore, comparative analysis with existing classical models shows that designed approach better results. can assist remotely well estimate advance.

Язык: Английский

Процитировано

128
A multi-factor driven spatiotemporal wind power prediction model based on ensemble deep graph attention reinforcement learning networks DOI
Chengqing Yu, Guangxi Yan, Chengming Yu

и другие.

Energy, Год журнала: 2022, Номер 263, С. 126034 - 126034

Опубликована: Ноя. 11, 2022

Язык: Английский

Процитировано

90
Temporal Convolutional Networks with RNN approach for chaotic time series prediction DOI
Hatice Vildan Dudukcu, Murat Taşkıran, Zehra Gülru Çam Taşkıran

и другие.

Applied Soft Computing, Год журнала: 2022, Номер 133, С. 109945 - 109945

Опубликована: Дек. 17, 2022

Язык: Английский

Процитировано

78
State-of-charge estimation of lithium-ion battery based on second order resistor-capacitance circuit-PSO-TCN model DOI
Feng Li, Wei Zuo, Kun Zhou

и другие.

Energy, Год журнала: 2023, Номер 289, С. 130025 - 130025

Опубликована: Дек. 17, 2023

Язык: Английский

Процитировано

55
State of charge estimation of lithium-ion batteries based on PSO-TCN-Attention neural network DOI
Feng Li, Wei Zuo, Kun Zhou

и другие.

Journal of Energy Storage, Год журнала: 2024, Номер 84, С. 110806 - 110806

Опубликована: Фев. 9, 2024

Язык: Английский

Процитировано

55
A TCN-Based Hybrid Forecasting Framework for Hours-Ahead Utility-Scale PV Forecasting DOI
Yiyan Li, Lidong Song, Si Zhang

и другие.

IEEE Transactions on Smart Grid, Год журнала: 2023, Номер 14(5), С. 4073 - 4085

Опубликована: Янв. 16, 2023

This paper presents a Temporal Convolutional Network (TCN) based hybrid PV forecasting framework for enhancing hours-ahead utility-scale forecasting. The consists of two models: physics-based trend (TF) model and data-driven fluctuation (FF) model. Three TCNs are integrated in the for: i) blending inputs from different Numerical Weather Prediction sources TF to achieve superior performance on hourly profiles, ii) capturing spatial-temporal correlations between detector sites target site FF more accurate forecast intra-hour power drops, iii) reconciling results obtain coherent with both trends fluctuations well preserved. To automatically identify most contributive neighboring forming network, scenario-based correlation analysis method is developed, which significantly improves capability large caused by cloud movements. tested, validated using actual data collected 95 farms North Carolina. Simulation show that 6 hours ahead improved 20% - 30% compared state-of-the-art methods.

Язык: Английский

Процитировано

53
Deep learning for time series forecasting: a survey DOI Creative Commons
Xiangjie Kong, Zhenghao Chen,

Weiyao Liu

и другие.

International Journal of Machine Learning and Cybernetics, Год журнала: 2025, Номер unknown

Опубликована: Фев. 8, 2025

Язык: Английский

Процитировано

5
An Experimental Review on Deep Learning Architectures for Time Series Forecasting DOI
Pedro Lara-Benítez, Manuel Carranza-García, José C. Riquelme

и другие.

International Journal of Neural Systems, Год журнала: 2020, Номер 31(03), С. 2130001 - 2130001

Опубликована: Ноя. 24, 2020

In recent years, deep learning techniques have outperformed traditional models in many machine tasks. Deep neural networks successfully been applied to address time series forecasting problems, which is a very important topic data mining. They proved be an effective solution given their capacity automatically learn the temporal dependencies present series. However, selecting most convenient type of network and its parametrization complex task that requires considerable expertise. Therefore, there need for deeper studies on suitability all existing architectures different this work, we face two main challenges: comprehensive review latest works using experimental study comparing performance popular architectures. The comparison involves thorough analysis seven types terms accuracy efficiency. We evaluate rankings distribution results obtained with proposed under architecture configurations training hyperparameters. datasets used comprise more than 50,000 divided into 12 problems. By 38,000 these data, provide extensive forecasting. Among studied models, show long short-term memory (LSTM) convolutional (CNN) are best alternatives, LSTMs obtaining accurate forecasts. CNNs achieve comparable less variability parameter configurations, while also being efficient.

Язык: Английский

Процитировано

100
Comparing LSTM and GRU Models to Predict the Condition of a Pulp Paper Press DOI Creative Commons
Balduíno César Mateus, Mateus Mendes, José Torres Farinha

и другие.

Energies, Год журнала: 2021, Номер 14(21), С. 6958 - 6958

Опубликована: Окт. 22, 2021

The accuracy of a predictive system is critical for maintenance and to support the right decisions at times. Statistical models, such as ARIMA SARIMA, are unable describe stochastic nature data. Neural networks, long short-term memory (LSTM) gated recurrent unit (GRU), good predictors univariate multivariate present paper describes case study where performances units compared, based on different hyperparameters. In general, exhibit better performance, pulp presses. final result demonstrates that, maximize equipment availability, units, demonstrated in paper, best options.

Язык: Английский

Процитировано

97