ID	原文	译文
3073	针对未来网络中出现的多智能设备协作计算场景，提出了一种基于深度强化学习的多智能体联合计算卸载策略。	A joint network computation offloading strategy based on multi-agent deep reinforcement learning was proposed to meet the requirement of the multi-device cooperative computing scenario in the future network.
3074	所提策略通过多智能体强化学习值分解方法将多智能体联合动作策略函数拆解到各智能体设备上，达成系统的联合卸载决策，使系统在联合计算卸载任务中能够根据当前时刻智能体设备的计算能力、通信能力等状态和任务的时延需求、通信数据量以及所需的计算量等特点自适应地调整上传边缘侧或进行本地计算的策略选择。	Through a value decomposition process the multi-agent joint value function was factorized to obtain the joint offloading decision of the system. Based on the proposed strategy, offloading or local computing decision could be adjusted adaptively according to the present condition of the agents as computation capacity or communication capacity and the corresponding properties of the offloading tasks as data size, delay requirement and computation requirement.
3075	仿真结果表明，针对多种场景下不同用户数和业务需求，所提策略能够有效兼顾任务的时延和能耗需求，系统成本指标较对比策略降低16%。	Simulation results indicate the proposed strategy reduce 16% of the system cost which including time delay and energy consumption compared to the comparing strategy in different scenarios with different amount of the agents.
3076	为了提高联邦学习的通信效率,针对用户计算能力和信道状态异构的场景,提出了一类基于时分多址接入的用户调度策略,在满足给定单轮模型训练所需计算的样本数量约束下,最小化单轮模型更新的系统时延。	To improve the communication efficiency in FL(federated learning), for the scenario with heterogeneous edge user's computing capacity and channel state, a class of time division multiple access(TDMA) based user scheduling policies were proposed for FL. The proposed policies aim to minimize the system delay in each round of model training subject to a given sample size constraint required for computing in each round.
3077	理论分析了该调度策略的预期收敛速度,探究收敛性能与系统总时延的均衡关系,并进一步分析最优批大小的选择问题。	In addition, the convergence rate of the proposed scheduling algorithms was analyzed from a theoretical perspective to study the tradeoff between the convergence performance and the total system delay. The selection of the optimal batch size was further analyzed.
3078	仿真结果显示,所提算法与基准算法相比,模型收敛速率提升30%以上。	Simulation results show that the convergence rate of the proposed algorithm is at least 30% higher than all the considered benchmarks.
3079	针对付费信道网络交易成功率低及网络失衡问题,提出区块链付费信道网络高效路由策略。	In order to solve the problems of the low transaction success rate and network imbalance of the paymentchannel network, an efficient routing strategy of blockchain-based payment channel network was proposed.
3080	该策略根据业务类型及业务优先级为高优先级业务建立专用付费信道,并将常规业务划分为多个交易单元,	This strategyestablished a dedicated payment channel for the high-priority services according to the service type and service priority, and divided the conventional business into multiple transaction unit.
3081	通过信道均衡选路算法为各交易单元选路,减少链上交易次数,维持付费信道的长时间稳定性运行,提高交易成功率。	Furthermore, a channel balanced routing algorithm was de-signed to route each transaction unit, which could reduce the number of transactions on the blockchain and maintainlong-term stable operation of the off-chain payment channel, as well as improve the transaction success rate.
3082	为了避免多个交易同时使用某一链路导致资金暂时性短缺、信道不可用,设计付费信道网络交易排队机制。	In addition, inorder to avoid the temporary shortage of funds and unavailability of channels due to a certain link occupied by multiple transactions simultaneously, a transaction queuing mechanism in the payment channel network was designed.