SHORT-TERM POWER PREDICTION OF 5G PHOTOVOLTAIC BASE STATIONS BASED ON ICOA-BP

Zhang Zhanyong; Wang Chaomin; Chen Junjiang; Gao Xuchong; Guo Wenhao; Qin Tuanfa

doi:10.19912/j.0254-0096.tynxb.2024-2444

PDF(2274 KB)

Acta Energiae Solaris Sinica ›› 2026, Vol. 47 ›› Issue (5) : 720-731. DOI: 10.19912/j.0254-0096.tynxb.2024-2444

SHORT-TERM POWER PREDICTION OF 5G PHOTOVOLTAIC BASE STATIONS BASED ON ICOA-BP

Zhang Zhanyong^1,2, Wang Chaomin^1,2, Chen Junjiang^1,2, Gao Xuchong^1,2, Guo Wenhao^2,3, Qin Tuanfa^1,2

Author information +

History +

Abstract

To reduce the high energy consumption and costs of 5G communication technology, 5G photovoltaic base stations （PVBSs） integrate efficient and low-cost photovoltaic power generation technologies and employ energy routers to combine communication with energy utilization. To ensure the stability of the power supply system in 5G PVBSs, this study proposes a short-term power prediction method based on a back propagation （BP） neural network optimized by the improved crayfish optimization algorithm （ICOA）. The ICOA enhances global search capability and convergence speed through circular chaotic mapping, mirror reflection learning, an improved aquila optimizer, and the Lévy flight strategy. It effectively optimizes the weights and biases of the BP neural network to enhance photovoltaic power prediction accuracy. Moreover, the model employs principal component analysis to capture data correlations and reduce data dimensionality. A loop traversal algorithm is employed to select the optimal number of nodes in the hidden layer, ensuring optimal model performance. The experimental results show that the ICOA has excellent optimization and convergence capabilities. Furthermore, the ICOA-BP model achieves higher prediction accuracy under different weather conditions than BP neural network models optimized by the northern goshawk optimization algorithm, grey wolf optimization algorithm, whale optimization algorithm, and crayfish optimization algorithm. This improvement significantly enhances the stability of the power supply system in 5G PVBSs.

Key words

photovoltaic power generation / prediction model / neural network / improved crayfish optimization algorithm / energy router

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Zhang Zhanyong, Wang Chaomin, Chen Junjiang, Gao Xuchong, Guo Wenhao, Qin Tuanfa. SHORT-TERM POWER PREDICTION OF 5G PHOTOVOLTAIC BASE STATIONS BASED ON ICOA-BP[J]. Acta Energiae Solaris Sinica. 2026, 47(5): 720-731 https://doi.org/10.19912/j.0254-0096.tynxb.2024-2444

References

[1] NICOLA P, DAVID L, MARCO M, et al.Joint load control and energy sharing for renewable powered small base stations: a machine learning approach[J]. IEEE transactions on green communications and networking, 2021, 5(1): 512-525.
[2] NAFEA H B, SALLAM M M, ZAKI F W.Study of DRX sleep mode performance on virtual base station energy saving in 5G networks[J]. Wireless personal communications: an internaional journal, 2021, 118(4): 3251-3270.
[3] LIU L, WANG Y, WANG Z, et al.Potential contributions of wind and solar power to China's carbon neutrality[J]. Resources, conservation and recycling, 2022, 180: 106155.
[4] ZHI K L, JIE Z, FENG S J, et al.A short-term power output forecasting model based on correlation analysis and ELM-LSTM for distributed PV system[J]. Journal of electrical and computer engineering, 2020, 2020(2020): 1-10.
[5] HUANG J B, GUO W H, WEI R, et al.Short‐term power forecasting method for 5G photovoltaic base stations on non‐ sunny days based on SDN‐integrated INGO‐BP and RGAN[J]. IET renewable power generation, 2024, 18(6): 1019-1039.
[6] LIU L N, CHEN X, ZHAO M L, et al.Mobile-edge computing framework with data compression for wireless network in energy internet[J]. Tsinghua science and technology, 2019, 24(3): 271-280.
[7] TANG Z T, YANG Y H, BLAABJERG F.An interlinking converter for renewable energy integration into hybrid grids[J]. IEEE transactions on power electronics, 2021, 36(3): 2499-2504.
[8] ZHANG X, WANG Z, ZHOU Z, et al.Optimal dispatch of multiple photovoltaic integrated 5G base stations for active distribution network demand response[J]. Frontiers in energy research, 2022, 10: 919197.
[9] YAN M, GUO W H, HU Y L, et al.Improved hybrid sparrow search algorithm for an extreme learning machine neural network for short‐term photovoltaic power prediction in 5G energy‐routing base stations[J]. IET renewable power generation, 2023, 17(2): 336-348.
[10] PRABHAKARAN S, ANNIE UTHRA R, PREETHAROSELYN J.Feature extraction and classification of photovoltaic panels based on convolutional neural network[J]. Computers, materials and continua, 2022, 74(1): 1437-1455.
[11] WANG S, SUN Y, ZHANG S, et al.Very short-term probabilistic prediction of PV based on multi-period error distribution[J]. Electric power systems research, 2023, 214: 108817.
[12] 薛阳, 燕宇铖, 贾巍, 等. 基于改进灰狼算法优化长短期记忆网络的光伏功率预测[J]. 太阳能学报, 2023, 44(7): 207-213.
XUE Y, YAN Y C, JIA W, et al.Photovoltaic power prediction model based on IGWO-LSTM[J]. Acta energiae solaris sinica, 2023, 44(7): 207-213.
[13] WANG Y, FU Y, XUE H.Improved prediction method of PV output power based on optimised chaotic phase space reconstruction[J]. IET renewable power generation, 2020, 14(11): 1831-1840.
[14] 王玲芝, 李晨阳, 刘婧, 等. 基于GRO-SSA-LSTM的短期光伏发电功率预测[J]. 太阳能学报, 2025, 46(2): 401-409.
WANG L Z, LI C Y, LIU J, et al.Short term photovoltaic power prediction based on GRO-SSA-LSTM[J]. Acta energiae solaris sinica, 2025, 46(2): 401-409.
[15] MA X L, PANG Q L, XIE Q S.Short-term prediction model of photovoltaic power generation based on rough set-BP neural network[J]. Journal of physics, 2021, 1871(1): 12010.
[16] 杨志淳, 胡伟, 杨帆, 等. 大规模分布式光伏并网系统CPS联合仿真同步方法及仿真平台[J]. 太阳能学报, 2025, 46(3): 301-309.
YANG Z C, HU W, YANG F, et al.Synchronization method and simulation platform for CPS co-simulation of large-scale distributed photovoltaic grid-connected system[J]. Acta energiae solaris sinica, 2025, 46(3): 301-309.
[17] JIA H M, RAO H H, WEN C S, et al.Crayfish optimization algorithm[J]. Artificial intelligence review, 2023, 56(SUPPL 2): 1919-1979.
[18] 李宏宇, 钱谦, 潘家文, 等. 混沌累积差异增强的小龙虾优化算法[J]. 小型微型计算机系统, 1-10[2025-07-03].http://kns.cnki.net/kcms/detail/21.1106.TP.20240730.0946.004.html.
LI H Y, QIAN Q, PAN J W, et al. Chaotic accumulative difference-enhanced crawfish optimization algorithm[J]. Journal of Chinese computer systems, 1-10[2025-07-03].http://kns.cnki.net/kcms/detail/21.1106.TP.20240730.0946.004.html.
[19] 黄金宝. 5G光伏基站短期功率预测与能源调度方案研究[D]. 南宁: 广西大学, 2024.
HUANG J B.Research on short-term power prediction and energy scheduling scheme for 5G photovoltaic base station[D]. Nanning: Guangxi University, 2024.
[20] ZHANG Y, HU Q W, LI H L, et al.A back propagation neural network-based radiometric correction method (BPNNRCM) for UAV multispectral image[J]. IEEE journal of selected topics in applied earth observations and remote sensing, 2023, 16: 112-125.
[21] DEHGHANI M, HUBÁLOVSKÝ Š, TROJOVSKÝ P. Northern goshawk optimization: a new swarm-based algorithm for solving optimization problems[J]. IEEE access, 2021, 9: 162059-162080.
[22] FARIS H, ALJARAH I, AL-BETAR M A, et al. Grey wolf optimizer: a review of recent variants and applications[J]. Neural computing and applications, 2018, 30(2): 413-435.
[23] GHAREHCHOPOGH F S, GHOLIZADEH H.A comprehensive survey: whale optimization algorithm and its applications[J]. Swarm and evolutionary computation, 2019, 48: 1-24.