Cited by Short-Term Photovoltaic Power Forecasting Using Issa-Based Informer Combined with Fcm-Based Similar Day Selection and Mrsvd-Vmd Decomposition

Building energy consumption prediction and optimization using different neural network-assisted models; comparison of different networks and optimization algorithms DOI

Sadegh Afzal, Afshar Shokri,

Behrooz M. Ziapour

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 127, P. 107356 - 107356

Published: Nov. 9, 2023

Language: Английский

Citations

SMGformer: integrating STL and multi-head self-attention in deep learning model for multi-step runoff forecasting DOI

Wenchuan Wang, M. H. Gu,

Yang-hao Hong

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 9, 2024

Accurate runoff forecasting is of great significance for water resource allocation flood control and disaster reduction. However, due to the inherent strong randomness sequences, this task faces significant challenges. To address challenge, study proposes a new SMGformer forecast model. The model integrates Seasonal Trend decomposition using Loess (STL), Informer's Encoder layer, Bidirectional Gated Recurrent Unit (BiGRU), Multi-head self-attention (MHSA). Firstly, in response nonlinear non-stationary characteristics sequence, STL used extract sequence's trend, period, residual terms, multi-feature set based on 'sequence-sequence' constructed as input model, providing foundation subsequent models capture evolution runoff. key features are then captured layer. Next, BiGRU layer learn temporal information these features. further optimize output MHSA mechanism introduced emphasize impact important information. Finally, accurate achieved by transforming through Fully connected verify effectiveness proposed monthly data from two hydrological stations China selected, eight compare performance results show that compared with Informer 1th step MAE decreases 42.2% 36.6%, respectively; RMSE 37.9% 43.6% NSE increases 0.936 0.975 0.487 0.837, respectively. In addition, KGE at 3th 0.960 0.805, both which can maintain above 0.8. Therefore, accurately sequence extend effective period

Language: Английский

Citations

A novel hybrid model based on modal decomposition and error correction for building energy consumption prediction DOI

Meiqi Huo,

Weijie Yan,

Guoqian Ren

et al.

Energy, Journal Year: 2024, Volume and Issue: 294, P. 130811 - 130811

Published: Feb. 26, 2024

Language: Английский

Citations

Advanced Energy Performance Modelling: Case Study of an Engineering and Technology Precinct DOI

Faham Tahmasebinia, Lin Lin,

Shuo Wu

et al.

Buildings, Journal Year: 2024, Volume and Issue: 14(6), P. 1774 - 1774

Published: June 12, 2024

The global demand for energy is significantly impacted by the consumption patterns within building sector. As such, importance of simulation and prediction growing exponentially. This research leverages Building Information Modelling (BIM) methodologies, creating a synergy between traditional software methods algorithm-driven approaches comprehensive analysis. study also proposes method monitoring select management factors, step that could potentially pave way integration digital twins in systems. grounded case newly constructed educational New South Wales, Australia. physical model was created using Autodesk Revit, conventional BIM methodology. EnergyPlus, facilitated OpenStudio, employed software-based analysis output then used to develop preliminary algorithm models regression strategies Python. In this analysis, temperature relative humidity each unit were as independent variables, with their being dependent variable. sigmoid model, known its accuracy interpretability, advanced simulation. combined sensor data real-time prediction. A basic twin (DT) example simulate dynamic control air conditioning lighting, showcasing adaptability effectiveness system. explores potential machine learning, specifically reinforcement optimizing response environmental changes usage conditions. Despite current limitations, identifies future directions. These include enhancing developing complex algorithms boost efficiency reduce costs.

Language: Английский

Citations

Analysis of different neural network models based on variational modal decomposition and dung beetle optimizer algorithm for the prediction of air-conditioning energy consumption in multifunctional complex large public buildings DOI

Jianwen Liu, Yuxiang Zhang,

K Wen

et al.

Energy and Buildings, Journal Year: 2025, Volume and Issue: 334, P. 115518 - 115518

Published: Feb. 24, 2025

Language: Английский

Citations

Informer Hybrid Model for PV Power Forecasting Using Empirical Wavelet Decomposition with Improved Grid Clustering DOI

松青王

Software Engineering and Applications, Journal Year: 2025, Volume and Issue: 14(01), P. 46 - 62

Published: Jan. 1, 2025

Language: Английский

Citations

Improving the accuracy of daily runoff prediction using informer with black kite algorithm, variational mode decomposition, and error correction strategy DOI

Wenchuan Wang,

H. Ren,

Zong Li

et al.

Stochastic Environmental Research and Risk Assessment, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 28, 2025

Language: Английский

Citations

Fusing multi-sensor data for bag filter system risk early warning based on deep learning DOI

Yuexian Hou, Qiang Wang,

Yamin Lin

et al.

Process Safety and Environmental Protection, Journal Year: 2025, Volume and Issue: unknown, P. 107096 - 107096

Published: April 1, 2025

Language: Английский

Citations

Energy consumption dynamic prediction for HVAC systems based on feature clustering deconstruction and model training adaptation DOI

Huiheng Liu, Yanchen Liu, Huakun Huang

et al.

Building Simulation, Journal Year: 2024, Volume and Issue: 17(9), P. 1439 - 1460

Published: July 19, 2024

Language: Английский

Citations

A Novel Hybrid Model Combining BPNN Neural Network and Ensemble Empirical Mode Decomposition DOI

Huiling Li, Qi Wang,

Daijun Wei

et al.

International Journal of Computational Intelligence Systems, Journal Year: 2024, Volume and Issue: 17(1)

Published: April 2, 2024

Abstract Neural network models have been successfully used to predict stock prices, weather, and traffic patterns. Due the sensitivity of data, it is very effective in identifying maintaining long-term dependencies time series. The back propagation neural (BPNN) model works well regression classification applications, such as predicting prices sales volumes. BPNN needs sort out mapping between inputs outputs before continuous values. integrated with ensemble empirical mode decomposition (EEMD), a new hybrid prediction constructed. Integrating decomposition, collecting preprocessing sequence features, reducing noise, improving robustness, then training networks returned feature vectors instead. In international gold price series forecasting, $$R^2$$ R 2 1.85 $$\%$$ % better than existing EEMD-LSTM model, 3.8 5.44 independent long short-term memory (LSTM) models, respectively. Compared LSTM, plays performance EEMD better, reduces error certain extent, improves accuracy.

Language: Английский

Citations