This incredibly rapid adoption of Internet of Things (IoT) and e-learning technology, a smart campus provides many innovative applications, such as ubiquitous learning, smart energy, and security services to campus users via numerous IoT devices. However, as more and more IoT devices are integrated and imported, the inadequate campus network resource caused by the sensor data transport and video streaming is also a significant problem. This paper proposes a campus edge computing network in the hardware-software co-design process. The system employs street lighting as the IoT network communication node device. The campus platform integrates campus courses service, regulatory networks, mobile wireless networks, and other computing services. Neural network learning algorithms are employed to analyze the network and compute resource required by each network node operates as a whole network resource allocation service. Moreover, the learning algorithms will be adjusted as the bidirectional IoT communication to avoid inadequate resources with many IoTs service and data streams in the overall campus network service quality. The experimental results show that the proposed mechanism that the edge computing reduces the cloud loading and predicts and adjusts the distribution of the overall network can efficiently allocate resources and maintain load balance.

中文翻译：

---

基于物联网路灯节点的校园边缘计算网络

智能园区以令人难以置信的速度迅速采用了物联网（IoT）和电子学习技术，从而通过众多IoT设备为园区用户提供了许多创新应用，例如无所不在的学习，智能能源和安全服务。然而，随着越来越多的物联网设备被集成和导入，由传感器数据传输和视频流引起的校园网络资源不足也是一个重大问题。本文提出了一种在软硬件协同设计过程中的校园边缘计算网络。该系统采用路灯作为IoT网络通信节点设备。校园平台集成了校园课程服务，监管网络，移动无线网络和其他计算服务。神经网络学习算法用于分析网络并计算每个网络节点作为整体网络资源分配服务所需的资源。此外，学习算法将被调整为双向物联网通信，以避免在整个校园网络服务质量中拥有许多物联网服务和数据流的资源不足。实验结果表明，所提出的边缘计算减少云负载并预测和调整整个网络分布的机制可以有效地分配资源并保持负载平衡。学习算法将被调整为双向物联网通信，以避免在整个校园网络服务质量中拥有许多物联网服务和数据流的资源不足。实验结果表明，所提出的边缘计算减少云负载并预测和调整整个网络分布的机制可以有效地分配资源并保持负载平衡。学习算法将被调整为双向物联网通信，以避免在整个校园网络服务质量中拥有许多物联网服务和数据流的资源不足。实验结果表明，所提出的边缘计算减少云负载并预测和调整整个网络分布的机制可以有效地分配资源并保持负载平衡。