Results 71 to 80 of about 2,973 (161)
DPU empowered intelligent congestion control mechanism for the intelligent computing center network [PDF]
Addressing the issue of frequent network congestion due to high-frequency interactions between intelligent computing center clusters, which compromised the real-time performance of intelligent services, a congestion control model driven by deep ...
CHEN Jinqian +4 more
core +1 more source
Research on deep reinforcement learning in Internet of vehicles edge computing based on Quasi-Newton method [PDF]
To address the issues of ineffective task offloading decisions caused by multitasking and resource constraints in vehicular networks, the Quasi-Newton method deep reinforcement learning dual-phase online offloading (QNRLO) algorithm was proposed.
LU Zetao +3 more
core +1 more source
广东电网遭台风泰利侵袭的输配电设备受损分析及评估 [PDF]
全球能源互联网近年来致灾台风频率呈增加趋势，以2023年影响广东电网约百万用户的第4号台风“泰利”为例，分析广东电网遭台风侵袭受灾情况，建立输配电杆塔受损预测模型，识别关键特征变量与因素，为电网防灾减灾提供支持。首先，分析台风“泰利”气象特征，具有“台前对流活跃，风力强度大，降水范围广”等特点，对输配电设备均产生一定程度破坏。其次，利用随机森林、支持向量机、梯度决策树、神经网络等4种机器学习算法建立输配电杆塔受损预测模型，并对比部分算法针对不平衡样本优化前后模型表现。算例表明，随机森林优化后提升最大 ...
侯慧 +5 more
doaj +1 more source
Graph-to-sequence deep reinforcement learning based complex task deployment strategy in MEC [PDF]
With the help of mobile edge computing (MEC) and network virtualization technology, the mobile terminals can offload the computing, storage, transmission and other resource required for executing various complex applications to the edge service nodes ...
Mintao CAO +4 more
core +1 more source
He jishu熔盐堆是第四代核反应堆的候选堆型之一，对其关键运行参数进行精准预测，不仅可以揭示反应堆的运行状态，而且能够对异常工况提前预警，为操纵员提供决策支持和技术指导。为此，本文基于深度学习算法对熔盐堆关键参数开展预测研究，以期优化熔盐堆的运行状态监测效率并辅助决策过程。采用RELAP5-TMSR程序建立生成数据集的熔盐堆系统安全分析模型，基于自编码器（Autoencoder，AE）、长短时记忆网络（Long Short-Term Memory，LSTM）和门控循环单元（Gated Recurrent Unit ...
王 超群 +4 more
doaj +1 more source
Fast deep reinforcement learning anti-jamming algorithm based on similar sample generation [PDF]
To improve the learning efficiency of anti-jamming algorithms based on deep reinforcement learning and enable them to adapt more quickly to unknown jamming environments, a fast deep reinforcement learning anti-jamming algorithm based on similar sample ...
NIU Yingtao, ZHOU Quan
core +1 more source
智能科学与技术学报, 2020 研究如何通过暖气设备自适应地调节室温，提升室内环境的舒适度，具有非常重要的意义。因此，提出了基于双深度Q网络方法的智能暖气温度控制系统，根据人的表情信息控制暖气设备的阀门开度，实时调整室温。首先，介绍针对原始输入状态的预处理算法。然后，设计通过双深度Q网络方法学习控制暖气设备阀门开度的最佳策略。最后，通过仿真结果验证提出的方法的有效性。
李涛, 魏庆来
doaj
智能科学与技术学报, 2020 六足机器人拥有多个冗余自由度，适用于复杂的非结构环境。离散环境作为非结构环境的一个苛刻特例，需要六足机器人具备更加高效可靠的运动策略。以平面随机梅花桩为例，设定随机起始点与目标区域，利用深度强化学习算法进行训练，并得到六足机器人在平面梅花桩环境中的运动策略。为了加快训练进程，采用具有优先经验重放机制的深度确定性策略梯度算法。最后在真实环境中进行验证，实验结果表明，所规划的运动策略能让六足机器人在平面梅花桩环境中高效平稳地从起始点运动到目标区域。为六足机器人在真实离散环境中的精确运动规划奠定了基础。
傅汇乔 +4 more
doaj
Reinforcement Learning Navigation Method Based on Advantage Hindsight Experience Replay [PDF]
Reinforcement learning demonstrates significant potential in the field of mobile robots. By combining reinforcement learning algorithms with robot navigation, the autonomous piloting of robots can be achieved without prior knowledge.
Shaotong WANG, Liqun KUANG, Huiyan HAN, Fengguang XIONG, Hongxin XUE
core +1 more source
Zhendong Ceshi yu Zhenduan在立铣刀铣削过程中，由于工件较硬、切削深度较大、采用摆线铣加工方式使刀具磨损较快、空刀段较多，无法准确识别刀具磨损状态。针对这种情况，提出了一种利用深度约束变分自编码器（deep‑constrained variational auto‑encoder，简称DCVAE）和极限学习机（extreme learning machine，简称ELM）的刀具磨损状态识别方法。首先，将电流有效值信号、加速度信号和声压信号进行融合，将其转化为三维彩色图像；其次，采用DCVAE模型对彩色图像中包含的数据进行降维处理 ...
doaj +1 more source