Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userFlexState: Enabling Innovation in Network Function State Management
290
0
0.0
(
0
)
Added by
Matteo Pozza
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Network function (NF) developers need to provide highly available solutions with diverse packet processing features at line rate. A significant challenge in developing such functions is to build flexible software that can be adapted to different operating environments, vendors, and operator use-cases. Today, refactoring NF software for specific scenarios can take months. Furthermore, network operators are increasingly adopting fast-paced development practices for continuous software delivery to gain market advantage, which imposes even shorter development cycles. A key aspect in NF design is state management, which can be optimized across deployments by carefully selecting the underlying data store. However, migrating to a data store that suits a different use-case is time consuming because it requires code refactoring while revisiting its application programming interfaces, APIs. In this paper we introduce FlexState, a state management system that decouples the NF packet processing logic from the data store that maintains its state. The objective is to reduce code refactoring significantly by incorporating an abstraction layer that exposes various data stores as configuration alternatives. Experiments show that FlexState achieves significant flexibility in optimizing the NF state management across several scenarios with negligible overhead.
rate research
Read More
Technical advances in ubiquitous sensing, embedded computing, and wireless communication are leading to a new generation of engineered systems called cyber-physical systems (CPS). CPS promises to transform the way we interact with the physical world just as the Internet transformed how we interact with one another. Before this vision becomes a reality, however, a large number of challenges have to be addressed. Network quality of service (QoS) management in this new realm is among those issues that deserve extensive research efforts. It is envisioned that wireless sensor/actuator networks (WSANs) will play an essential role in CPS. This paper examines the main characteristics of WSANs and the requirements of QoS provisioning in the context of cyber-physical computing. Several research topics and challenges are identified. As a sample solution, a feedback scheduling framework is proposed to tackle some of the identified challenges. A simple example is also presented that illustrates the effectiveness of the proposed solution.
Network slicing is born as an emerging business to operators, by allowing them to sell the customized slices to various tenants at different prices. In order to provide better-performing and cost-efficient services, network slicing involves challenging technical issues and urgently looks forward to intelligent innovations to make the resource management consistent with users activities per slice. In that regard, deep reinforcement learning (DRL), which focuses on how to interact with the environment by trying alternative actions and reinforcing the tendency actions producing more rewarding consequences, is assumed to be a promising solution. In this paper, after briefly reviewing the fundamental concepts of DRL, we investigate the application of DRL in solving some typical resource management for network slicing scenarios, which include radio resource slicing and priority-based core network slicing, and demonstrate the advantage of DRL over several competing schemes through extensive simulations. Finally, we also discuss the possible challenges to apply DRL in network slicing from a general perspective.
Integrating Internet of Things (IoT) and edge computing for Edge-IoT systems, converged with machine intelligence, has the potentials of enabling a wide range of applications in smart homes, factories and cities. Edge-IoT can connect many diverse devices and the IoT asset owners can run heterogeneous IoT systems supported by various vendors or service providers (SPs), using either cloud or local edge computing (or both) for resource assistance. The existing methods typically manage the systems as separate vertical silos, or in a vendor/SP-centric way, which suffers from significant challenges. In this paper, we present a novel owner-centric management paradigm named ORCA to address the gaps left by the owner-centric paradigm and empower the IoT assets owners to effectively identify and mitigate potential issues in their own network premises, regardless the vendors/SPs situations. ORCA aims to be scalable and extensible in assisting IoT owners to perform intelligent management through a behavior-oriented and data-driven approach. ORCA is an ongoing project and the preliminary results indicate that it can significantly empower the IoT systems owners to better manage their IoT assets.
In recent years, many techniques have been developed to improve the performance and efficiency of data center networks. While these techniques provide high accuracy, they are often designed using heuristics that leverage domain-specific properties of the workload or hardware. In this vision paper, we argue that many data center networking techniques, e.g., routing, topology augmentation, energy savings, with diverse goals actually share design and architectural similarity. We present a design for developing general intermediate representations of network topologies using deep learning that is amenable to solving classes of data center problems. We develop a framework, DeepConfig, that simplifies the processing of configuring and training deep learning agents that use the intermediate representation to learns different tasks. To illustrate the strength of our approach, we configured, implemented, and evaluated a DeepConfig-Agent that tackles the data center topology augmentation problem. Our initial results are promising --- DeepConfig performs comparably to the optimal.
Data centres are growing in numbers and size, and their networks expanding to carry larger amounts of traffic. The traffic profile is constantly varying, particularly in cloud data centres where tenants arrive, leave, and may change their resource requirements in between, and so the network configuration must change at a commensurate rate. Software-Defined Networking - programmatic control of network configuration - has been critical to meeting the demands of modern data centre network management, and has been the subject of intense focus by the research community, working in conjunction with industry. In this survey, we review Software-Defined Networking research targeting the management and operation of data centre networks.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
