ID 原文 译文
3553 其次，从网络控制与编排、网络深度可编程、网络确定性服务、网络计算存储一体化、网络与人工智能、网络与区块链、智能安全网络、网络空天地海一体化 8 个方面阐述了当前热点网络技术的背景、进展和主要成果； Then, the current research progress and main results of each technology were expounded from eightaspects: network control and orchestration, programmable network, deterministic network, network computing and stor-age integration, network with artificial intelligence, network with blockchain, intelligent security network, space network.
3554 最后，分析了面向 2030 的未来网络发展趋势，预计到 2030 年未来网络将支撑万亿级、人机物、全时空、安全、智能的连接与服务。 Finally the development trends and challenges of each technology were analyzed. It was expected that by 2030, the futurenetwork will support trillion-level, human-machine, all-time-space, safe, and intelligent connections and services.
3555 希望能为未来网络相关领域的研究提供参考和帮助。 It is hoped that it can provide references and help for future network research.
3556 随着区块链技术的迅猛发展，区块链系统的安全问题正逐渐暴露出来，给区块链生态系统带来巨大风险。 While the security of blockchain has been the central concern of both academia and industry since the verystart, new security threats continue to emerge, which poses great risks to the blockchain ecosystem.
3557 通过回顾区块链安全方面的相关工作，对区块链潜在的安全问题进行了系统的研究。 A systematic study was conducted on the most state-of-the-art research on potential security issues of blockchain.
3558 将区块链框架分为数据层、网络层、共识层和应用层 4 层，分析其中的安全漏洞及攻击原理，并讨论了增强区块链安全的防御方案。 Specifically, a taxono-my was developed by considering the blockchain framework as a four-layer system, and the analysis on the most re-cent attacks against security loopholes in each layer was provided. Countermeasures that can strengthen the blockchainwere also discussed by highlighting their fundamental ideas and comparing different solutions.
3559 最后，在现有研究的基础上展望了区块链安全领域的未来研究方向和发展趋势。 Finally, the forefront ofresearch and potential directions of blockchain security were put forward to encourage further studies on the securityof blockchain.
3560 针对云服务器系统运行环境具有非线性、随机性和突发性的特点，提出了基于整合移动平均自回归和循环神经网络组合模型（ARIMA-RNN）的软件老化预测方法。 In view of the nonlinear, stochastic and sudden characteristics of operating environment of cloud server system,a software aging prediction method based on hybrid auto-regressive integrated moving average and recurrent neural net-work model (ARIMA-RNN) was proposed.
3561 首先，采用 ARIMA 模型对云服务器时间序列数据进行老化预测； Firstly, the ARIMA model performs software aging prediction of time seriesdata in cloud server.
3562 然后，利用灰色关联度分析法计算时间序列数据的相关性，确定 RNN 模型的输入维度； Then the grey relation analysis method was used to calculate the correlation of the time series data todetermine the input dimension of RNN model.