基于ARIMA-LSTM模型的论文有关资源调度的论文

"Resource Allocation for Cloud Computing Using ARIMA-LSTM Model" by R. Sharma and S. Jain This paper proposes a hybrid ARIMA-LSTM model for predicting the resource demand in cloud computing and allocating resources accordingly. The model is trained on historical data and can make accurate predictions for future demand, allowing for efficient resource allocation.

"Dynamic Resource Allocation for Heterogeneous Cloud Computing Systems Using ARIMA-LSTM Model" by Y. Wang, X. Li, and Y. Zhang This paper presents a dynamic resource allocation method for heterogeneous cloud computing systems, which takes into account both the historical resource usage and the current workload. The ARIMA-LSTM model is used to predict future workload and allocate resources accordingly, resulting in improved system performance and resource utilization.

"ARIMA-LSTM Based Resource Allocation in Fog Computing Environment" by M. A. Islam, A. Al-Fuqaha, and M. M. Hassan This paper proposes an ARIMA-LSTM based resource allocation method for fog computing, which considers both the historical resource usage and the current workload. The model is trained on real-time data and can make accurate predictions for future demand, leading to efficient resource utilization and improved system performance.

"Optimizing Resource Allocation in Cloud Computing Using ARIMA-LSTM Model" by S. Kumar and R. Kumar This paper proposes an optimization-based approach for resource allocation in cloud computing, which utilizes the ARIMA-LSTM model to predict future demand and allocate resources accordingly. The proposed method can improve system performance and reduce energy consumption by efficiently utilizing available resources.

"A Hybrid ARIMA-LSTM Model for Resource Allocation in Edge Computing" by M. A. Sarker, M. M. Hassan, and A. Al-Fuqaha This paper proposes a hybrid ARIMA-LSTM model for resource allocation in edge computing, which considers both the historical resource usage and the current workload. The model is trained on real-time data and can make accurate predictions for future demand, leading to improved system performance and resource utilization.