A base station microgrid traffic prediction method based on IOOA-CNN-BiLSTM DOI Open Access
Ming Yan, Wenhao Guo, S. Xian

et al.

Journal of Physics Conference Series, Journal Year: 2025, Volume and Issue: 3000(1), P. 012029 - 012029

Published: April 1, 2025

Abstract The rapid advancement of 5G technology has raised significant concerns regarding the energy consumption base stations for mobile network operators. Integrating traditional station power supply systems with microgrids to maximize utilization renewable demonstrated considerable potential in addressing challenges faced by stations. However, inherent randomness communication traffic loads adversely affects reliable operation microgrids. To tackle this issue, we propose a prediction model based on deep learning methods. Initially, reference scenario microgrid is established, followed employment an Improved Osprey Optimization Algorithm (IOOA) enhance convergence speed and mitigate risk local optima. Ultimately, key parameters CNN-BiLSTM are optimized using IOOA. Experimental results from real datasets corroborate superiority proposed concerning MAPE R 2 indicators, as well perform effectively savings.

Language: Английский

Design and test of adaptive energy management strategy for plug-in hybrid electric vehicle considering traffic information DOI

Dehua Shi,

Shiqi Li, Han Xu

et al.

Energy, Journal Year: 2025, Volume and Issue: unknown, P. 136093 - 136093

Published: April 1, 2025

Language: Английский

Citations

0
A base station microgrid traffic prediction method based on IOOA-CNN-BiLSTM DOI Open Access
Ming Yan, Wenhao Guo, S. Xian

et al.

Journal of Physics Conference Series, Journal Year: 2025, Volume and Issue: 3000(1), P. 012029 - 012029

Published: April 1, 2025

Abstract The rapid advancement of 5G technology has raised significant concerns regarding the energy consumption base stations for mobile network operators. Integrating traditional station power supply systems with microgrids to maximize utilization renewable demonstrated considerable potential in addressing challenges faced by stations. However, inherent randomness communication traffic loads adversely affects reliable operation microgrids. To tackle this issue, we propose a prediction model based on deep learning methods. Initially, reference scenario microgrid is established, followed employment an Improved Osprey Optimization Algorithm (IOOA) enhance convergence speed and mitigate risk local optima. Ultimately, key parameters CNN-BiLSTM are optimized using IOOA. Experimental results from real datasets corroborate superiority proposed concerning MAPE R 2 indicators, as well perform effectively savings.

Language: Английский

Citations

0