ID	原文	译文
5464	为了分析布尔混沌系统的物理随机性，构建了基于自治布尔网络的电路混沌模型，建立了包含相位噪声特性的数学方程，研究了相位噪声对布尔混沌熵增长时间（记忆时间）的影响。	To analyze the physical randomness of Boolean chaos, the model for chaotic circuit system based on autono-mous Boolean network was established. In addition, the equations of the Boolean network with phase noise were deduced.By considering the phase noise, the time for the growth of entropy for an ensemble of trajectories, called the memorytime, was analyzed.
5465	研究结果表明，在相位噪声的影响下，布尔混沌输出将在有限的记忆时间（数十纳秒）后达到无法预测，且相位噪声越强，布尔混沌平均记忆时间越短。	It was demonstrated that Boolean chaos would be unpredictable after tens of nanoseconds, and lessaverage memory time was required as the phase noise strength increased.
5466	这证明了相位噪声是布尔混沌物理随机性的来源，且布尔混沌可以作为性能良好的真随机数物理熵源。	It is shown that Boolean chaos has physicalrandomness because of phase noise and it also lays the theoretical foundation for the entropy source of true random num-ber generator based on chaotic Boolean network.
5467	良好的负载均衡机制是有效利用数据中心网络带宽的必备条件。	A good load balance mechanism is the key to effectively use the network of the data center network.
5468	现有的等价多路径路由（ECMP）的负载均衡方法由于负载均衡粒度过粗，且不具备对路径拥塞状态感知的能力，因此负载均衡效率较低。	In current production data center, ECMP is the de facto load balancing scheme. However, it has two drawbacks. 1) the load balanceunit is too coarse-grained, 2) it's not congestion aware.
5469	为解决此问题，近年来出现了一系列细粒度且具备拥塞感知能力的负载均衡研究工作。	To solve these problems, several fine-grained and conges-tion-aware load balancing works have emerged in recent years.
5470	然而，这些研究或者需要修改交换机硬件以实时搜集网络各部位的拥塞情况，难以部署；	These works either need to modify the switch hardware to collect congestion in various parts of the network in real time, and it is difficult to deploy;
5471	或者虽不需要修改交换机硬件，仅需对端系统的软件进行修改，但由于缺乏准确的网络拥塞信息而导致负载混合效果不佳。	or only need to modify the end system, but the inaccurate sense of congestion cannot achieve a good load balancing effect.
5472	针对该问题，提出了一种实现于端系统上的软件解决方案 ELAB，该方案不需要对网络中的硬件进行修改，就可以达到良好的负载均衡效果。ELAB 创造性地采用了基于可用带宽的方式进行流量负载均衡，相比于现有的基于端系统的方法，ELAB 性能提升达 20%。	A novel edge-based load bal-ancing scheme ELAB was proposed, which addresses above existing problems and improves the network performance upto 20%.
5473	5G 网络中超密集基站的部署规划、多维资源管理、活跃/休眠切换等方面都依赖于对区域内用户数量的准确预测。	The deployment and planning for ultra-dense base stations, multidimensional resource management, and on-offswitching in 5G networks rely on the accurate prediction of crowd flows in the specific areas.