多用户与多边缘节点之间计算卸载数据集

本数据集《无线算力网络的实时边缘智能技术》着眼于通过深度强化学习（DDTO）算法在无线算力网络中实现实时边缘智能，旨在优化任务卸载决策和算力资源分配，显着降低端到端时延。数据集通过仿真算法生成，在不同算法下进行模拟，任务的端到端平均处理时延，旨在为无线算力网络中的实时边缘智能技术。采集方案包括采用深度强化学习算法中的动态调度策略考虑，通过计算不同算法下的任务最终平均处理时延，数据采集通过环境模拟生成。为了符合无线算力网络的实时边缘智能技术试验环境规范，该数据集的生成过程严格遵守了相关标准和规范，保证数据的科学性和有效性。在采集过程中，通过基于Matlab和Python设计的自定义仿真环境，模拟了不同的网络配置，得到了边缘节点数、用户数、任务数据大小以及。数据集中包含了关于不同网络配置算法和决策下的任务处理时延数据，为研究人员提供了丰富的数据实验数据，有助于评估和优化无线算力网络的边缘。该数据集主要适用于无线计算力网络、边缘计算、深度强化学习优化以及节能技术研究，特别是对于分析和优化无线通信系统中的实时智能决策和资源分配具有重要的研究价值。通过该数据集，研究人员探索如何进一步提高无线可以。

This dataset, titled *Real-Time Edge Intelligence Technologies for Wireless Computing Power Networks*, focuses on implementing real-time edge intelligence in wireless computing power networks via deep reinforcement learning (DDTO) algorithms, aiming to optimize task offloading decisions and computing resource allocation, and significantly reduce end-to-end latency. The dataset is generated through simulation algorithms, with simulations conducted under different algorithm configurations to collect the average end-to-end processing latency of tasks. The data collection scheme adopts the dynamic scheduling strategy in deep reinforcement learning algorithms, calculates the final average processing latency of tasks under various algorithms, and generates data via environmental simulation. To comply with the test environment specifications for real-time edge intelligence technologies in wireless computing power networks, the dataset generation process strictly follows relevant standards and specifications, ensuring the scientific validity and reliability of the data. During the data collection process, a custom simulation environment designed using Matlab and Python was utilized to simulate diverse network configurations, including the number of edge nodes, number of users, task data size, and [the original text has an incomplete trailing phrase]. The dataset contains task processing latency data under different network configurations, algorithms and decision-making scenarios, providing researchers with abundant experimental data to support the evaluation and optimization of edge computing in wireless computing power networks. This dataset is primarily applicable to research on wireless computing power networks, edge computing, deep reinforcement learning optimization and energy-saving technologies, and holds significant research value, particularly for analyzing and optimizing real-time intelligent decision-making and resource allocation in wireless communication systems. With this dataset, researchers can explore ways to further improve [the original text has an incomplete trailing segment].

搜集汇总

背景与挑战

背景概述

该数据集聚焦于无线算力网络中的实时边缘智能技术，通过深度强化学习算法模拟多用户与多边缘节点间的计算卸载过程，旨在优化任务卸载决策和资源分配以降低端到端时延。它由仿真生成，包含不同网络配置下的任务处理时延数据，适用于无线计算力网络、边缘计算和深度强化学习优化等研究领域。