Electricity Demand Forecasting With a Modified Extreme-Learning Machine Algorithm DOI Creative Commons
Chen Chen,

Chuangang Ou,

Mingxiang Liu

et al.

Frontiers in Energy Research, Journal Year: 2022, Volume and Issue: 10

Published: Aug. 15, 2022

To operate the power grid safely and reduce cost of production, power-load forecasting has become an urgent issue to be addressed. Although many load models have been proposed, most still suffer from poor model training, limitations sensitive outliers, overfitting forecasts. The current load-forecasting methods may lead generation additional operating costs for system, even damage distribution network security related systems. address this issue, a new prediction with mixed loss functions was proposed. is based on Pinball–Huber’s extreme-learning machine whale optimization algorithm. In specific, Pinball–Huber loss, which insensitive outliers largely prevents overfitting, proposed as objective function (ELM) training. Based ELM, algorithm added improve it. At last, effect hybrid verified using two real datasets (Nanjing Taixing). Experimental results confirmed that can achieve satisfactory improvements both datasets.

Language: Английский

Novel wind speed forecasting model based on a deep learning combined strategy in urban energy systems DOI
Hao Yan, Wendong Yang,

Kedong Yin

et al.

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 219, P. 119636 - 119636

Published: Feb. 2, 2023

Language: Английский

Citations

45
A hybrid deep learning framework for air quality prediction with spatial autocorrelation during the COVID-19 pandemic DOI Creative Commons
Zixi Zhao, Jinran Wu, Fengjing Cai

et al.

Scientific Reports, Journal Year: 2023, Volume and Issue: 13(1)

Published: Jan. 18, 2023

Abstract China implemented a strict lockdown policy to prevent the spread of COVID-19 in worst-affected regions, including Wuhan and Shanghai. This study aims investigate impact these lockdowns on air quality index (AQI) using deep learning framework. In addition historical pollutant concentrations meteorological factors, we incorporate social spatio-temporal influences particular, spatial autocorrelation (SAC), which combines temporal with correlation, is adopted reflect influence neighbouring cities data. Our analysis obtained estimates effects as − 25.88 20.47 The corresponding prediction errors are reduced by about 47% for 67% Shanghai, enables much more reliable AQI forecasts both cities.

Language: Английский

Citations

41
Daily suspended sediment concentration forecast in the upper reach of Yellow River using a comprehensive integrated deep learning model DOI
Jinsheng Fan, Xiaofang Liu, Weidong Li

et al.

Journal of Hydrology, Journal Year: 2023, Volume and Issue: 623, P. 129732 - 129732

Published: June 8, 2023

Language: Английский

Citations

19
Climate change and coastal morphodynamics: Interactions on regional scales DOI Creative Commons
Piyali Chowdhury, Naresh Kumar Goud Lakku, Susana Lincoln

et al.

The Science of The Total Environment, Journal Year: 2023, Volume and Issue: 899, P. 166432 - 166432

Published: Aug. 19, 2023

Climate change and its impacts, combined with unchecked human activities, intensify pressures on coastal environments, resulting in modification of the morphodynamics. Coastal zones are intricate constantly changing areas, making monitoring interpretation data a challenging task, especially remote beaches regions limited historical data. Traditionally, sensing numerical methods have played vital role analysing earth observation supporting modelling complex ecosystems. However, emergence artificial intelligence-based techniques has shown promising results, offering additional advantage filling gaps, predicting data-scarce regions, multidimensional datasets collected over extended periods time larger spatial scales. The main objective this study is to provide comprehensive review existing literature, discussing both traditional various emerging approaches used studying dynamics, shoreline analysis, monitoring. Ultimately, proposes climate resilience framework enhance zone management practices policies, fostering among communities. outcome aligns supports particularly SDG 13 UN (Climate Action) advances it by identifying relevant erosion studies proposing integrated plans informed real-time collection analysis/modelling using physics-based models.

Language: Английский

Citations

17
Photovoltaic Power Prediction Based on VMD-BRNN-TSP DOI Creative Commons
Guici Chen, Tingting Zhang,

Wenyu Qu

et al.

Mathematics, Journal Year: 2023, Volume and Issue: 11(4), P. 1033 - 1033

Published: Feb. 17, 2023

Overfitting often occurs in neural network training, and networks with higher generalization ability are less prone to this phenomenon. Aiming at the problem that of photovoltaic (PV) power prediction model is insufficient, a PV time-sharing (TSP) combining variational mode decomposition (VMD) Bayesian regularization (BRNN) proposed. Firstly, meteorological sequences related output selected by mutual information (MI) analysis. Secondly, VMD processing performed on filtered sequences, which aimed reducing non-stationarity data; then, normalized cross-correlation (NCC) signal-to-noise ratio (SNR) between components obtained signal original data calculated, after key influencing factors screened out eliminate correlation redundancy data. Finally, divided into two datasets based whether irradiance day zero or not. Meanwhile, predictions using BRNN for each datasets. Then, results reordered chronological order, realized conclusively. It was experimentally verified mean absolute value error (MAE) method proposed paper 0.1281, reduced 40.28% compared back propagation (BPNN) same dataset, squared (MSE) 0.0962, coefficient determination (R2) 0.9907. Other indicators also confirm much significance TSP contributive.

Language: Английский

Citations

8
A hybrid intelligence model for predicting dissolved oxygen in aquaculture water DOI Creative Commons
Huanhai Yang, Mingyu Sun,

Shue Liu

et al.

Frontiers in Marine Science, Journal Year: 2023, Volume and Issue: 10

Published: June 6, 2023

Dissolved oxygen is an important water quality indicator that affects the health of aquatic products in aquaculture, and its monitoring prediction are great significance. To improve accuracy dissolved series, a hybrid model based on variational mode decomposition (VMD) deep belief network (DBN) optimized by improved slime mould algorithm (SMA) proposed this paper. First, VMD used to decompose nonlinear time series into several relatively stable intrinsic function (IMF) subsequences with different frequency scales. Then, SMA applying elite opposition-based learning convergence factors increase population diversity enhance local search global capabilities. Finally, optimize hyperparameters DBN, aquaculture VMD-ISMA-DBN constructed. The predict each IMF subsequence, ISMA optimization adaptively select optimal DBN model, results accumulated obtain final result series. data from 8 marine ranches Shandong Province, China were verify performance model. Compared stand-alone has been significantly improved, MAE MSE have reduced 43.28% 40.43% respectively, ( R 2 ) increased 8.37%. show higher than other commonly intelligent models (ARIMA, RF, TCN, ELM, GRU LSTM); hence, it can provide reference for accurate regulation quality.

Language: Английский

Citations

8
A Novel Approach for Reconstruction of IMFs of Decomposition and Ensemble Model for Forecasting of Crude Oil Prices DOI Creative Commons
Muhammad Naeem, Muhammad Aamir, Jian Yu

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 34192 - 34207

Published: Jan. 1, 2024

In recent eras, the complexity and fluctuations of global crude oil prices have affected economic progress society. It is therefore, price prediction has hauled attention scholars policymakers. Driven by this critical concern for forecasting prices, we introduces a novel hybrid model keeping in mind primary objective enhancing accuracy while considering specific characteristics as inherent data. To achieve achievement, trend eliminated, allowing scrutiny whether residual component validates assurance series ran stochastic trends. Following removal trend, undergoes rigorous evaluation through autoregressive following decomposition model. Then got support from vector machine, integrated moving average long-short term memory. The predictions can be evaluated using various performance metrics. proposed model's robustness are rigorously Diebold-Mariano test comparison to competing models. Furthermore, ability via directional forecast. Ultimately, empirical findings explicitly determine superior predictive capabilities over alternative approaches.

Language: Английский

Citations

3
Analysis of fine-grained sediment dynamics from field observations with a vector autoregressive model DOI
Zixi Zhao, Shaotong Zhang, Jinran Wu

et al.

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 644, P. 132100 - 132100

Published: Oct. 1, 2024

Language: Английский

Citations

3
Solving the one dimensional vertical suspended sediment mixing equation with arbitrary eddy diffusivity profiles using temporal normalized physics-informed neural networks DOI Open Access
Shaotong Zhang, Jiaxin Deng, Xian Li

et al.

Physics of Fluids, Journal Year: 2024, Volume and Issue: 36(1)

Published: Jan. 1, 2024

Analytical solutions are practical tools in ocean engineering, but their derivation is often constrained by the complexities of real world. This underscores necessity for alternative approaches. In this study, potential Physics-Informed Neural Networks (PINN) solving one-dimensional vertical suspended sediment mixing (settling-diffusion) equation which involves simplified and arbitrary Ds profiles explored. A new approach temporal Normalized (T-NPINN), normalizes time component proposed, it achieves a remarkable accuracy (Mean Square Error 10−5 Relative Loss 10−4). T-NPINN also proves its ability to handle challenges posed long-duration spatiotemporal models, formidable task conventional PINN methods. addition, free limitations numerical methods, e.g., susceptibility inaccuracies stemming from discretization approximations intrinsic algorithms, particularly evident within intricate dynamic oceanic environments. The demonstrated versatility make compelling complement techniques, effectively bridging gap between analytical approaches enriching toolkit available research engineering.

Language: Английский

Citations

2
Optimization of suspended particulate transport parameters from measured concentration profiles with a new analytical model DOI
Shaotong Zhang, Zixi Zhao, Jinran Wu

et al.

Water Research, Journal Year: 2024, Volume and Issue: 254, P. 121407 - 121407

Published: March 1, 2024

Language: Английский

Citations

2