A Hybrid Power Load Forecasting Framework with Attention-Based Network and Multi-Scale Decomposition DOI
Jiaming Zhu, Dezhi Liu, Lili Niu

и другие.

Опубликована: Янв. 1, 2024

Язык: Английский

CNNs-Transformer based day-ahead probabilistic load forecasting for weekends with limited data availability DOI
Zhirui Tian, Weican Liu, Wenqian Jiang

и другие.

Energy, Год журнала: 2024, Номер 293, С. 130666 - 130666

Опубликована: Фев. 10, 2024

Язык: Английский

Процитировано

35
Optimising post-disaster waste collection by a deep learning-enhanced differential evolution approach DOI Creative Commons
Maziar Yazdani, Kamyar Kabirifar, Milad Haghani

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 132, С. 107932 - 107932

Опубликована: Янв. 31, 2024

In the aftermath of natural disasters, efficient waste collection becomes a crucial challenge, owing to dynamic and unpredictable nature generation, coupled with resource constraints. This paper presents an innovative hybrid methodology that synergizes Long Short-Term Memory (LSTM) machine learning Differential Evolution (DE) optimisation augment efforts post-disaster. The approach leverages real-time data forecast generation high accuracy, facilitating development adaptable strategies. Our is designed dynamically update plans in response evolving scenarios, ensuring timely effective decision-making. Field tests conducted earthquake-prone city have demonstrated superior performance this method managing under fluctuating conditions. Moreover, in-depth sensitivity analysis helps identifying key areas for improvement. Significantly outperforming traditional models, offers substantial time savings equips disaster teams robust tool addressing challenges collection.

Язык: Английский

Процитировано

14
A coupled framework for power load forecasting with Gaussian implicit spatio temporal block and attention mechanisms network DOI
Dezhi Liu, Xuan Lin,

Hanyang Liu

и другие.

Computers & Electrical Engineering, Год журнала: 2025, Номер 123, С. 110263 - 110263

Опубликована: Март 20, 2025

Язык: Английский

Процитировано

1
Comparison of energy consumption prediction models for air conditioning at different time scales for large public buildings DOI
Jianwen Liu,

Zhihong Zhai,

Yuxiang Zhang

и другие.

Journal of Building Engineering, Год журнала: 2024, Номер 96, С. 110423 - 110423

Опубликована: Авг. 14, 2024

Язык: Английский

Процитировано

4
Mitigating concept drift challenges in evolving smart grids: An adaptive ensemble LSTM for enhanced load forecasting DOI
Abdul Azeem, Idris Ismail,

Syed Sheeraz Mohani

и другие.

Energy Reports, Год журнала: 2025, Номер 13, С. 1369 - 1383

Опубликована: Янв. 15, 2025

Язык: Английский

Процитировано

0
Online decoupling feature framework for optimal probabilistic load forecasting in concept drift environments DOI
Chaojin Cao, Yaoyao He, Xiaodong Yang

и другие.

Applied Energy, Год журнала: 2025, Номер 392, С. 125952 - 125952

Опубликована: Апрель 25, 2025

Язык: Английский

Процитировано

0
HybridDep: An elastic hybrid resources allocation strategy for I/O‐intensive applications DOI Creative Commons
Pengmiao Li, Yuchao Zhang,

Sang Y. Yun

и другие.

IET Communications, Год журнала: 2025, Номер 19(1)

Опубликована: Янв. 1, 2025

Abstract Along with the rapid development of B5G/6G, number applications grows rapidly and data amount explodes exponentially, putting a massive burden on resource‐limited edge servers. To fully utilize limited resources, virtualization technology is introduced to provide elastic deployment for in But I/O‐intensive applications, allocating resources not as easy compute‐intensive ones, because required I/O unknown due request uncertainty. Many existing researches try solve this multi‐application problem by peaks clipping valleys filling, resource utilization. However, fact, times most hybrid deployed are similar each other, which invalidates those traditional solutions. address challenge, actual analysed complementary peak valley periods time space dimensions found. Based finding, an strategy HybridDep proposed, multiple applications. Validated simulation experiments using real datasets traces, algorithm can reduce about 3.2% cost than compared algorithm.

Язык: Английский

Процитировано

0
Short-Term Electricity-Load Forecasting by deep learning: A comprehensive survey DOI
Qi Dong, Rubing Huang, Chenhui Cui

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 154, С. 110980 - 110980

Опубликована: Май 6, 2025

Язык: Английский

Процитировано

0
Transfer-AE: A novel Autoencoder-based Impact Detection Model for Structural Digital Twin DOI
Chengjia Han, Zixin Wang, Yuguang Fu

и другие.

Applied Soft Computing, Год журнала: 2024, Номер 166, С. 112174 - 112174

Опубликована: Авг. 30, 2024

Язык: Английский

Процитировано

3
Multivariable correlation feature network construction and health condition assessment for unlabeled single-sample data DOI

Dan Xu,

Xiaoqi Xiao,

Jianguo Zhang

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 133, С. 108220 - 108220

Опубликована: Март 22, 2024

Язык: Английский

Процитировано

2