Democratizing the Network Edge

Abstract

The cloud and telecommunications industry is in the midst of a transition towards the edge. There is a tremendous opportunity for the research community to influence this transformation, but doing so requires understanding industry momentum, and making a concerted effort to align with that momentum. We believe there are three keys to doing this: (1) focus on the intersection of the cloud and access networks, (2) contribute to the relevant open source projects, and (3) address the challenge of operationalizing the results. The paper puts forward a concrete proposal for all three, and discusses the opportunity to influence how the Internet evolves at the edge and enable innovative edge applications.

Hierarchical Scheduling Mechanisms in Multi-Level Fog Computing

“…Fog-aware mechanisms to implement efficient resource management for applications with different levels of latency requirements is indeed a challenging task [5]. Several efforts have addressed this body of work to provide a latencydriven fog computing environment for IoT applications using one fog layer only between the edge and the cloud (as illustrated the fog-cloud topology in Figure 1) [3], [4], [8]- [10], [14], [15]. Effective mechanisms addressing stacked fog layers (also known as cloudlet, micro data centers, or fog nodes) is still an open issue [2].…”

“…The new vision of mobile computing in mid-2009 has endeavored to free mobile devices from a severe limitation of computing capabilities, allowing resource-hungry applications to use cloud-like computing service that would be free of delay, instability, congestion and WAN failures. Since then, Satyanarayananet al have been advancing this body of work to emphasize the importance of having cloudlets at the network edge to emerge the industry investment and research interest in edge computing [4]. Still, none of them has discussed the importance of deploying multi-layers of fog nodes between the edge and the cloud to manage the requirements of applications with heterogeneous tolerance levels of latency.…”

“…This action significantly improves the computing resources of IoT devices facing high computation demands [2]. Particularly, offloading has been useful for resource-hungry applications that span the Big Data concept [3], which habitually generate a large volume of data at different velocity and variety [4]. However, the reliance on computation capabilities outside of edge devices is not ideal for those applications that require tightly controlled delays (latency) on the data transfer time with remote resources.…”

Implementasi net neutrality di indonesia ditinjau dari undang-undang ite

“…Internet menghadirkan titik fokus aktivitas inovasi yang terletak di inti ekosistem yang berkembang pesat.Namun, modifikasi pada rangkaian protokol dasar Internet, dan penerapan di seluruh Internet berikutnya menghadapi banyak kesulitan. Masalah koordinasi dan perselisihan antara pelaku pasar yang berbeda yang bersaing telah mengakibatkan penurunan kemampuan untuk berkembang (Peterson et al, 2019) Dari sudut pandang ekonomi, masalah yang terkait dengan Net Neutrality adalah bahwa broadband memungkinkan teknik manajemen lalu lintas web. Teknik ini dapat digunakan misalnya untuk diskriminasi kualitas paket data atau penggunaan biaya penghentian untuk lalu lintas data.…”

Pruning Edge Research with Latency Shears

“…Some [27] see edge taking over from the cloud; others see a combination [55]. Peterson et al [52] see edge and the democratization it offers as a cure for Internet ossification. Some argue for wide-spread in-network computation [57], Figure 1: The popularity (in red) and publications (in blue) of keywords "edge computing" (in solid line) and "cloud computing" (in dashed line) in Google web searches and Google scholar respectively.…”