arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.06194cs.NI
收藏

上行小小区网络中的节能计算卸载与虚拟连接控制

Energy Efficient Computation Offloading and Virtual Connection Control in Uplink Small Cell Networks

Davoud Yousefi, Hassan Yari, Farzad Osouli, Mohammad Ebrahimi, Somayeh Esmalifalak, Morteza Johari, Abbas Azarnezhad, Fatemeh Sadeghi, Rogayeh Mirzapour

AI总结:

针对 HetNet 多层网络的非凸分层优化问题,提出融合深度学习、联合资源分配、能效与流/功率控制的算法,在保障 SLA 与吞吐量限制下显著提升能效。

摘要:

如今,在机器学习这一范畴下,软计算技术在电力系统中的应用正不断增加,并获得良好反响。本文中,我们首先提出一种深度学习方法,用于寻找 HetNet 系统的最优配置。我们使用测试系统的大量径向配置进行训练。除了确保所有用户的体验质量外,我们还研究了多层分层网络中的联合载波/功率分配问题,以实现最优功率效率。所提方法采用自适应负载均衡模型,旨在从关键性能指标的角度,在所有服务器之间实现“近乎最优”的公平性。不同于当前基于模型的能效方法,我们提出一种联合资源分配、能效与流控制算法,以解决常见的非凸分层优化问题。此外,通过参考基于 SLA 的连续资源分配,我们将所提算法扩展为通用的流/功率控制与运行功率优化算法,在确保用户吞吐量限制的同时实现最优能效。仿真结果还表明,与采用网络拓扑调整能力的传统设计相比,所提出的受控功率/流优化方法能够显著提高能效。

英文摘要:

Nowadays, the use of soft computational techniques in power systems under the umbrella of machine learning is increasing with good reception. In this paper, we first present a deep learning approach to find the optimal configuration for HetNet systems. We used a very large number of radial configurations of a test system for training purposes. We also studied the issue of joint carrier/power allocation in multilayer hierarchical networks, in addition to ensuring the quality of experience for all subscribers, to achieve optimal power efficiency. The proposed method uses an adaptive load equilibrium model that aims to achieve "almost optimal" equity among all servers from the standpoint of the key performance indicator. Unlike current model-based energy efficiency methods, we propose a joint resource allocation, energy efficiency, and flow control algorithm to solve common nonconvex and hierarchical optimization problems. Also, by referring to the allocation of continuous resources based on SLA, we extended the proposed algorithm to common flow/power control and operational power optimization algorithm to achieve optimal energy efficiency along with ensuring user's throughput limitations. Also, simulation results show that the proposed controlled power/flow optimization approach can significantly increase energy efficiency compared to conventional designs using network topology adjustment capability.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑