《工程科学学报》录用稿，htps:/doi.org/10.13374/i,issn2095-9389.2021.02.19.002©北京科技大学2020 雾辅助物联网中公平节能的计算迁移研究 陈思光1,2☒，尤子慧) 1)南京邮电大学江苏省宽带无线通信和物联网重点实验室，江苏南京210003 2)南京邮电大学江苏省通信与网络技术工程研究中心，江苏南京210003 ☒通信作者，E-mail:sgchen@njupt.edu.cn 摘要：作为云计算模式的延伸，雾计算以其能耗低、时延短、带宽节省高等优势而受到广泛关注，基于雾计算的计算迁移 机制为缓解数据处理压力、实现低时延服务及延长网络生命周期等提供了有力支撑。为了构建绿色且长生命周期的物联网， 本文提出了一种雾辅助的公平节能物联网计算迁移方案。首先，基于雾节点计算能力、带宽资源以及融合雾节点能耗公平性 的迁移决策的联合考量，构建了一个最小化所有任务完成总能耗的优化问题。其次，提出了基会量梯度和坐标协同下降的 公平性能耗最小化算法用于解决上述混合整数非线性规划问题。该算法基于雾节点的历史平均能耗距离、计算能力以及剩 余能量值设计了公平性指标以获得对于雾节点能耗公平性最优的迁移决策：通过提出的动量梯度与坐标协同下降法，联合优 化雾节点分配给各个任务的计算及带宽资源占比，达到最小化任务处理总能耗。最后仿其结果表明本文方案能够取得较快 的收敛速度，且与其他两种基准方案相比，本文方案的总能耗最低，雾节点的能耗公平性最高，且网络寿命分别平均提高了 23.6%和31.2%。进一步地，该方案在不同雾节点数量以及不同任务大小的环境下仍然能保持性能优势，体现了方案鲁棒性 高的特点。 nidatgCaarCompuB念OmadiagrgaittT 关键词：计算迁移：雾计算：公平性指标：能耗最小化：网络 分类号：TP393.0 CHEN Si-guang,YOU Zi-hui) 1)Jiangsu Key Lab of Broadband Wireless Communication and Nanjing University of Posts and Telecommunications,Nanjing,Jiangsu 210003,China 2)Jiangsu Engineering Research Center of Communications and Network Technology,Nanjing University of Posts and Telecommunications,Nanjing,Jiangsu 210003,China X ABSTRACT:As an extension of cloud computing paradigm,fog computing has attracted wide attention due to its advantages of low energy consumption,short time delay and high bandwidth saving.Meanwhile,the fog computing based computation offloading mechanism provides a strong support for alleviating the pressure of data processing,realizing low delay service and prolonging the network lifetime.In order to constfuet a green and long lifetime Interet of Things (loT),this paper proposes a faimess and energy co-aware computation offloading scheme for fog-assisted loT.First of all,based on the joint optimization consideration of fog node's computing capacity.bandwidth resource and the offloading decision with energy consumption fairess,an optimization problem is formulated to minimize the total energy consumption of all computation tasks.Secondly,a Momentum Gradient and Coordinate Collaboration Descent based Fair Energy Minimization Algorithm (MGCCD-FEM)is proposed to solve above mixed integer nonlinear programming problem.In this algorithm,based on the historical average energy consumption,distance,computing capacity and residual energy of fog node,a fair index is designed to obtain the offloading decision with the optimal energy consumption fairness.The minimization of the total energy consumption for processing all the tasks can be achieved by jointly optimizing the occupation ratios of computing and bandwidth resources with the developed momentum gradient and coordinate collaboration descent method.Finally,the simulation results show that the proposed scheme can achieve faster convergence speed.Meanwhile,as compared with other two benchmark schemes,the total energy consumption of this scheme is the lowest,the energy consumption fairness of fog 收稿日期：2021-02-19 基金项目：国家自然科学基金(Nos.61971235,61771258):江苏省“333高层次人才培养工程”资助：南京邮电大学1311'人才计划资助：中国博 士后科学基金（面上一等资助）(No.2018M630590):网络与信息安全安徽省重点实验室开放课题(No.AHN1S2020001):赛尔网络下一代互联网 技术创新项目(No.NGII20190702)_____________________________________ 收稿日期: 2021-02-19 基金项目:国家自然科学基金(Nos. 61971235, 61771258）；江苏省“333 高层次人才培养工程”资助；南京邮电大学‘1311’人才计划资助；中国博 士后科学基金（面上一等资助）（No. 2018M630590）；网络与信息安全安徽省重点实验室开放课题（No. AHNIS2020001）；赛尔网络下一代互联网 技术创新项目（No. NGII20190702） 雾辅助物联网中公平节能的计算迁移研究 陈思光 1,2)，尤子慧 1) 1) 南京邮电大学江苏省宽带无线通信和物联网重点实验室, 江苏南京 210003 2) 南京邮电大学江苏省通信与网络技术工程研究中心，江苏南京 210003  通信作者，E-mail: sgchen@njupt.edu.cn 摘 要：作为云计算模式的延伸，雾计算以其能耗低、时延短、带宽节省高等优势而受到广泛关注，基于雾计算的计算迁移 机制为缓解数据处理压力、实现低时延服务及延长网络生命周期等提供了有力支撑。为了构建绿色且长生命周期的物联网， 本文提出了一种雾辅助的公平节能物联网计算迁移方案。首先，基于雾节点计算能力、带宽资源以及融合雾节点能耗公平性 的迁移决策的联合考量，构建了一个最小化所有任务完成总能耗的优化问题。其次，提出了基于动量梯度和坐标协同下降的 公平性能耗最小化算法用于解决上述混合整数非线性规划问题。该算法基于雾节点的历史平均能耗、距离、计算能力以及剩 余能量值设计了公平性指标以获得对于雾节点能耗公平性最优的迁移决策；通过提出的动量梯度与坐标协同下降法，联合优 化雾节点分配给各个任务的计算及带宽资源占比，达到最小化任务处理总能耗。最后，仿真结果表明本文方案能够取得较快 的收敛速度，且与其他两种基准方案相比，本文方案的总能耗最低，雾节点的能耗公平性最高，且网络寿命分别平均提高了 23.6%和 31.2%。进一步地，该方案在不同雾节点数量以及不同任务大小的环境下仍然能够保持性能优势，体现了方案鲁棒性 高的特点。 关键词： 计算迁移； 雾计算； 公平性指标； 能耗最小化；网络寿命 分类号：TP393.0 Fairness and Energy Co-aware Computation Offloading for Fog-assisted IoT CHEN Si-guang1,2)  , YOU Zi-hui1) 1) Jiangsu Key Lab of Broadband Wireless Communication and Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu 210003, China 2) Jiangsu Engineering Research Center of Communications and Network Technology, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu 210003, China ABSTRACT: As an extension of cloud computing paradigm, fog computing has attracted wide attention due to its advantages of low energy consumption, short time delay and high bandwidth saving. Meanwhile, the fog computing based computation offloading mechanism provides a strong support for alleviating the pressure of data processing, realizing low delay service and prolonging the network lifetime. In order to construct a green and long lifetime Internet of Things (IoT), this paper proposes a fairness and energy co-aware computation offloading scheme for fog-assisted IoT. First of all, based on the joint optimization consideration of fog node’s computing capacity, bandwidth resource and the offloading decision with energy consumption fairness, an optimization problem is formulated to minimize the total energy consumption of all computation tasks. Secondly, a Momentum Gradient and Coordinate Collaboration Descent based Fair Energy Minimization Algorithm (MGCCD-FEM) is proposed to solve above mixed integer nonlinear programming problem. In this algorithm, based on the historical average energy consumption, distance, computing capacity and residual energy of fog node, a fair index is designed to obtain the offloading decision with the optimal energy consumption fairness. The minimization of the total energy consumption for processing all the tasks can be achieved by jointly optimizing the occupation ratios of computing and bandwidth resources with the developed momentum gradient and coordinate collaboration descent method. Finally, the simulation results show that the proposed scheme can achieve faster convergence speed. Meanwhile, as compared with other two benchmark schemes, the total energy consumption of this scheme is the lowest, the energy consumption fairness of fog 《工程科学学报》录用稿，https://doi.org/10.13374/j.issn2095-9389.2021.02.19.002 ©北京科技大学 2020 录用稿件，非最终出版稿