Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userWide Area Network Autoscaling for Cloud Applications
188
0
0.0
(
0
)
Added by
Berta Serracanta Pujol
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Modern cloud orchestrators like Kubernetes provide a versatile and robust way to host applications at scale. One of their key features is autoscaling, which automatically adjusts cloud resources (compute, memory, storage) in order to adapt to the demands of applications. However, the scope of cloud autoscaling is limited to the datacenter hosting the cloud and it doesnt apply uniformly to the allocation of network resources. In I/O-constrained or data-in-motion use cases this can lead to severe performance degradation for the application. For example, when the load on a cloud service increases and the Wide Area Network (WAN) connecting the datacenter to the Internet becomes saturated, the application flows experience an increase in delay and loss. In many cases this is dealt with overprovisioning network capacity, which introduces additional costs and inefficiencies. On the other hand, thanks to the concept of Network as Code, the WAN exposes a set of APIs that can be used to dynamically allocate and de-allocate capacity on-demand. In this paper we propose extending the concept of cloud autoscaling into the network to address this limitation. This way, applications running in the cloud can communicate their networking requirements, like bandwidth or traffic profile, to a Software-Defined Networking (SDN) controller or Network as a Service (NaaS) platform. Moreover, we aim to define the concepts of vertical and horizontal autoscaling applied to networking. We present a prototype that automatically allocates bandwidth to the underlay network, according to the requirements of the applications hosted in Kubernetes. Finally, we discuss open research challenges.
rate research
Read More
We revisit a classic networking problem -- how to recover from lost packets in the best-effort Internet. We propose CASPR, a system that judiciously leverages the cloud to recover from lost or delayed packets. CASPR supplements and protects best-effort connections by sending a small number of coded packets along the highly reliable but expensive cloud paths. When receivers detect packet loss, they recover packets with the help of the nearby data center, not the sender, thus providing quick and reliable packet recovery for latency-sensitive applications. Using a prototype implementation and its deployment on the public cloud and the PlanetLab testbed, we quantify the benefits of CASPR in providing fast, cost effective packet recovery. Using controlled experiments, we also explore how these benefits translate into improvements up and down the network stack.
Despite the proliferation of mobile devices in various wide-area Internet of Things applications (e.g., smart city, smart farming), current Low-Power Wide-Area Networks (LPWANs) are not designed to effectively support mobile nodes. In this paper, we propose to handle mobility in SNOW (Sensor Network Over White spaces), an LPWAN that operates in the TV white spaces. SNOW supports massive concurrent communication between a base station (BS) and numerous low-power nodes through a distributed implementation of OFDM. In SNOW, inter-carrier interference (ICI) is more pronounced under mobility due to its OFDM based design. Geospatial variation of white spaces also raises challenges in both intra- and inter-network mobility as the low-power nodes are not equipped to determine white spaces. To handle mobility impacts on ICI, we propose a dynamic carrier frequency offset estimation and compensation technique which takes into account Doppler shifts without requiring to know the speed of the nodes. We also propose to circumvent the mobility impacts on geospatial variation of white space through a mobility-aware spectrum assignment to nodes. To enable mobility of the nodes across different SNOWs, we propose an efficient handoff management through a fast and energy-efficient BS discovery and quick association with the BS by combining time and frequency domain energy-sensing. Experiments through SNOW deployments in a large metropolitan city and indoors show that our proposed approaches enable mobility across multiple different SNOWs and provide robustness in terms of reliability, latency, and energy consumption under mobility.
Recent advances in Low-Power Wide-Area Networks have mitigated interference by using cloud assistance. Those methods transmit the RSSI samples and corrupted packets to the cloud to restore the correct message. However, the effectiveness of those methods is challenged by the high transmission data amount. This paper presents a novel method for interference mitigation in a Edge-Cloud collaborative manner, namely ECCR. It does not require transmitting RSSI sample any more, whose length is eight times of the packets. We demonstrate the disjointness of the bit errors of packets at the base stations via real-word experiments. ECCR leverages this to collaborate with multiple base stations for error recovery. Each base station detects and reports bit error locations to the cloud, then both error checking code and interfered packets from other receivers are utilized to restore correct packets. ECCR takes the advantages of both the global management ability of the cloud and the signal to perceive the benefit of each base station, and it is applicable to deployed LP-WAN systems (e.g. sx1280) without any extra hardware requirement. Experimental results show that ECCR is able to accurately decode packets when packets have nearly 51.76% corruption.
A virtual network (VN) contains a collection of virtual nodes and links assigned to underlying physical resources in a network substrate. VN migration is the process of remapping a VNs logical topology to a new set of physical resources to provide failure recovery, energy savings, or defense against attack. Providing VN migration that is transparent to running applications is a significant challenge. Efficient migration mechanisms are highly dependent on the technology deployed in the physical substrate. Prior work has considered migration in data centers and in the PlanetLab infrastructure. However, there has been little effort targeting an SDN-enabled wide-area networking environment - an important building block of future networking infrastructure. In this work, we are interested in the design, implementation and evaluation of VN migration in GENI as a working example of such a future network. We identify and propose techniques to address key challenges: the dynamic allocation of resources during migration, managing hosts connected to the VN, and flow table migration sequences to minimize packet loss. We find that GENIs virtualization architecture makes transparent and efficient migration challenging. We suggest alternatives that might be adopted in GENI and are worthy of adoption by virtual network providers to facilitate migration.
In this paper we advocate the use of device-to-device (D2D) communications in a LoRaWAN Low Power Wide Area Network (LPWAN). After overviewing the critical features of the LoRaWAN technology, we discuss the pros and cons of enabling the D2D communications for it. Subsequently we propose a network-assisted D2D communications protocol and show its feasibility by implementing it on top of a LoRaWAN-certified commercial transceiver. The conducted experiments show the performance of the proposed D2D communications protocol and enable us to assess its performance. More precisely, we show that the D2D communications can reduce the time and energy for data transfer by 6 to 20 times compared to conventional LoRaWAN data transfer mechanisms. In addition, the use of D2D communications may have a positive effect on the network by enabling spatial re-use of the frequency resources. The proposed LoRaWAN D2D communications can be used for a wide variety of applications requiring high coverage, e.g. use cases in distributed smart grid deployments for management and trading.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
