AI-Driven Terminal Access Optimization and Resource Allocation Model under High-Penetration of Renewable Energy
DOI:
https://doi.org/10.13052/spee1048-5236.4433Keywords:
LSTM (Long Short-Term Memory), deep learning, collaborative algorithm, terminal accessAbstract
Against the backdrop of a high proportion of renewable energy being integrated into the power system, the dynamics of terminal device access and the uncertainty of energy supply pose severe challenges to traditional resource allocation mechanisms. This paper proposes a collaborative model for AI-driven terminal access optimization and resource allocation. By integrating deep reinforcement learning and a dynamic priority assessment mechanism, the model achieves adaptive access control of terminal devices and elastic allocation of computing resources in scenarios with distributed energy fluctuations.
The model design adopts a hierarchical decision-making architecture. The upper layer predicts the supply – demand status of regional renewable energy based on the LSTM network, while the lower layer dynamically adjusts the terminal access strategy and resource allocation weights through a multi – agent collaborative algorithm. Simulation experiments based on the NREL renewable energy dataset show that in scenarios where the fluctuation amplitude of wind and solar power output exceeds 40%, compared with traditional heuristic algorithms, this model can increase resource utilization by 22.1%, raise the task completion rate to 93.7%, and keep the decision – making delay stable within the 200ms threshold.
Downloads
References
Zhang Z Y, Wang J Z, Xia Y R, et al. Solar-mixer: an efficient end-to-end model for long-sequence photovoltaic power generation time series forecasting [J]. IEEE Transactions on Sustainable Energy, 2023, 14(4): 1979–1991.
Yang Mao, Jia Mengqi, Zhang Wei, et al. Power fore-casting for photovoltaic cluster in long forecasting period based on power reconstruction and temporal characteristic constraints [J]. Automation of Electric Power Systems, 2024, 48(15): 102–111.
Zhang Ziqi, Chen Zhong. Transformation mechanisms and characterization methods for flexibility and uncertainty in active distribution networks with multiple entities [J]. Automation of Electric Power Systems, 2024, 48(13): 79–88.
Zhao Yao, Gao Shaowei, Li Dongdong, et al. Short-term interval probability prediction of photovoltaic power based on weather similarity clustering and quantile regression neural network [J]. Automation of Electric Power Systems, 2023, 47(23): 152–161.
Li Y Y, Song L D, Zhang S, et al. A TCN-based hybrid forecasting framework for hours-ahead utility-scale PV forecasting [J]. IEEE Transactions on Smart Grid, 2023, 14(5): 4073–4085.
Liu J X, Zang H X, Ding T, et al. Sky-image-derived deep decomposition for ultra-short-term photovoltaic power forecasting [J]. IEEE Transactions on Sustainable Energy, 2024, 15(2): 871–883.
Du L F, Zhang L H, Wang X. Generative adversarial framework-based one-day-ahead forecasting method of photovoltaic power output [J]. IET Generation, Transmission & Distribution, 2020, 14(19): 4234–4245.
Li Feng, Ding Jie, Zhou Caiqi, et al. Key technologies of large-scale grid-connected operation of distributed photovoltaic under new-type power system [J]. Power System Technology, 2024, 48(1): 184–196.
Guermoui M, Bouchouicha K, Bailek N, Et Al. Forecasting intra-hour variance of photovoltaic power using a new integrated model [J]. Energy Conversion and Management, 2021, 245: 114569.
Wang F, Li J N, Zhen Z, et al. Cloud feature extraction and fluctuation pattern recognition based ultrashort-term regional PV power forecasting [J]. IEEE Transactions on Industry Applications, 2022, 58(5): 6752–6767.
Lai W Z, Zhen Z, Wang F, et al. Sub-region division based short-term regional distributed PV power forecasting method considering spatio-temporal correlations [J]. Energy, 2024, 288: 129716.
Zhangyangke, Li Gang, Li Xiufeng. Short-term forecasting method for regional photovoltaic power based on typical representative power stations and improved SVM [J]. Electric Power Automation Equipment, 2021, 41(11): 205–210.
Ma Lübin, Pan Guobing, Jiang Qun, Et Al. Research on distributed pv cluster power output forecasting method based on eof-dbscan-gru [J]. Acta Energiae Solaris Sinica, 2024, 45(1): 39–46.
Asiri E C, Chung C Y, Liang X D. Day-ahead prediction of distributed regional-scale photovoltaic power [J]. IEEE Access, 2023, 11: 27303–27316.
Shan S, Ding Z T, Zhang K J, et al. ACGL-TR: a deep learning model for spatio-temporal short-term irradiance forecast [J]. Energy Conversion and Management, 2023, 284: 116970.
Liu J C, Li T. Multi-step power forecasting for regional photovoltaic plants based on ITDE-GAT model [J]. Energy, 2024: 130468.
Wang Z L, Zhu H Y, Zhang D D, et al. Modelling of wind and photovoltaic power output considering dynamic spatio-temporal correlation [J]. Applied Energy, 2023, 352: 121948.
Yue H, Ali M M, Lin Y Z, et al. Ultra-short-term forecasting of large distributed solar PV fleets using sparse smart inverter data [J]. IEEE Transactions on Sustainable Energy, 2024, 15(3): 1968–1980.
Ouyang Yongjian, Miao Xiren, Lin Weiqing, et al. Small area PV ultra-short-term prediction method using stratified digraph and dynamic spatial-temporal correlation [J]. Power System Technology, 2024, 48(6): 2458–2468.
Verdonea, Scardapane S, Panella M. Explainable spatio-temporal graph neural networks for multi-site photovoltaic energy production [J]. Applied Energy, 2024, 353: 122151.
Simeunović J, Schubnel B, Alet P J, et al. Spatio-temporal graph neural networks for multi-site PV power forecasting [J]. IEEE Transactions on Sustainable Energy, 2022, 13(2): 1210–1220.
Wang Y Q, Fu W J, Zhang X D, et al. Dynamic directed graph convolution network based ultra-short-term forecasting method of distributed photovoltaic power to enhance the resilience and flexibility of distribution network [J]. IET Generation, Transmission & Distribution, 2024, 18(2): 337–352.
https://aeeeuropeenergy.com/
