Jonathan Vestin

Industrial Internet of Things (I-IoT) applications require a large number of sensor data to be processed under tight delay and jitter constraints. In such applications, flexible event detection and fast reaction to critical events is an important building block. Traditional approaches use either proprietary networks and dedicated hardware or transmit sensor data towards processing elements in the Cloud or at the Network Edge, using distributed stream processing frameworks. For scalability, a large number of servers are needed and processing on commodity CPUs typically involves high and unpredictable latency. In this paper, we explore how programmable data planes can be used to detect events flexibly and trigger customized and programmable actions directly from the switch program or the programmable network interface card (SmartNIC). We present FastReact-PS, an event-based publish/subscribe I-IoT processing framework in P4 language, which can be flexibly customized from the control plane. Together with stateful processing, FastReact-PS supports windowed time series analysis as well as complex event detection and processing based on boolean logic directly in the data plane of newly emerging programmable networking devices. The logic can be adjusted dynamically from the control plane without the need for recompilation. We implement FastReact-PS in P4 and evaluate it on both a SmartNIC and a DPDK-based software switch running in user space. Our evaluation shows that the latency is reduced by one order of magnitude compared to end-host based approaches at significantly lower jitter while being scalable to processing up to 11 million events per second.

In 5G, network densification is a major concern for operators. When a massive amount of small cells are deployed, the backhaul capacity is crucial and researchers are exploring the use of high frequency bands such as 28, 60 or even 140 GHz because of the large portion of spectrum that is available. Unfortunately, such mmWave links frequently change their capacity due to blocking and weather phenomena which makes it challenging to design stable multihop backhaul networks using those frequency bands. In this paper, we investigate the use of Software Defined Networking (SDN) for the operation and control of wireless backhaul networks. We explore different ways how SDN resiliency mechanisms such as FastFailover Groups can be used to mitigate disruptive connectivity in the multihop operation due to mmWave links frequently failing. We also demonstrate a clear benefit for using low frequency assist mode, where the small cell has an additional stable LTE uplink to the eNB that is used should the mmWave backhaul links fail. Our experiments using a network emulator show that such SDN based local repair mechanisms can significantly reduce the packet loss rate inside the mmWave backhaul mesh, which can be further reduced with an LTE assisted Failover.

As mobile data usage increases dramatically, new architectures and technologies for wireless communication are required. Next generation of mobile networks are expected to be augmented by a massive amount of small cells that will be densely deployed. In order to connect the small cells, new high capacity wireless backhauling technologies are required. A promising solution is to use frequencies in the mmWave band, which allows for much greater capacity due to the massive amount of free spectrum. However, the special characteristics of the mmWave bands such as high path loss and atmospheric absorption lead to unstable links. In this paper, we investigate using Software Defined Networking principles for the operation and control of wireless backhaul networks. We demonstrate how SDN resiliency mechanisms can be used to mitigate disruptive connectivity due to mmWave links frequently failing. For assisting the small cell backhauling, we propose to also use the LTE uplinks of the small cells as backup links, should the mmWave mesh forwarding link break. Our experiments using a network emulator show that using SDN-based local repair mechanisms can significantly reduce the packet loss rate inside the mmWave backhaul mesh, which can be further reduced with an LTE assisted Failover.

Due to the tremendous increase in traffic demand, current mobile access and backhaul networks face a capacity problem. To increase the capacity, one can deploy many small cells, which may be dynamically powered on where traffic demand arises. As a consequence, the backhaul network for dense small cell deployments needs to cope with the massive increase in user demands but rolling out fiber to each small cell is economically not viable. Recently, mmWave based mobile backhaul networks have raised a lot of interest because of the large chunk of available spectrum in the 60 GHz, and 70/80 GHz band. However, due to the specific propagation characteristic of mmWave spectrum, such links may face frequent outage. In addition, a more flexible design of the backhaul network is desired in order to cope with the diversification of service requirements. In this paper, we propose a small cell backhaul network architecture which is based on the concept of Software Defined Networking. In order to cope with the dynamics of mmWave links, we propose that the SDN control plane calculates for each backhaul link a set of backup links. Using OpenFlow Fast Failover groups, a fast local repair of a mmWave backhaul link can be achieved leading to a resilient backhaul mesh architecture. An evaluation of our concept in a network emulator demonstrates the effectiveness of our approach. Particularly how it leads to lower packet loss and consequently higher throughput.

Software Defined Networking (SDN) is currently a hot topic in the area of Datacenter Networking or Enterprise Networks as it has the promise to radically simplify network management and operation. However, it has not been considered so far as a promising candidate for Industrial Control Networks mainly because of the deterministic performance requirements and the dedicated design of those networks to fulfil strict performance guarantees. In this paper, we propose a resilient SDN based architecture for Industrial Control Networks and show that by combining several SDN based fast failover technologies using per-link Bidirectional Forwarding Detection (BFD), preconfigured primary and backup paths and flexible packet duplication orchestrated by an SDN controller, we can reduce significantly the control latency and provide more stringent performance guarantees even under lossy and failing links.

We present a demo of Quality of Service Management for CloudMAC, which combines SDN with NFV for processing WLAN MAC layer management frames in the Cloud. With CloudMAC, enterprise WLANs can be managed in the cloud which enables simple support for authentication, authorization and accounting, or mobility management. With CloudMAC, clients are associated with Virtual Machines and mobility management is simplified by updating OpenFlow forwarding rules. This enables seamless mobility. While CloudMAC works with standard WLAN clients, CloudMAC APs are very lightweight. In this demo, we show how we can manage different QoS classes in SDN enabled networks which allows a flexible WLAN MAC frame prioritisation. As an example, we implement 802.11ae based WLAN MAC management frame priorization in both the SDN network and the CloudMAC lightweight APs.

The Configuration and Management of large WLAN deployments is a challenge and available tools to ease such deployments and introduce new services are either commercial or very inflexible. In this paper, we present a different approach to such challenges called QoS enabled CloudMAC, which is to the best of our knowledge the first step towards QoS enabled WiFi MAC layer processing as an example of Network Function Virtualization. By moving the MAC layer processing to the cloud and integrating our architecture with QoS aware OpenFlow deployment, a software defined networking approach, we achieve a new level of flexibility, control and reconfigurability. CloudMAC Access Points (AP) just forward MAC layer frames towards a set of VMs (Virtual Access Points - VAP) that are responsible for processing MAC layer data and management frames (such as beacons, probe requests, etc). We have extended the SDN that connects the VAPs with the physical APs to support different packet prioritisation strategies such as HTB, SFQ, or FQ_CoDel. Our SDN controller is based on OpenDaylight which creates layer 2 forwarding rules that effectively prioritise CloudMAC traffic over legacy traffic. Our evaluation in a real testbed shows that packet prioritization strategies, especially FQ_CoDel, lead to good throughput and low latency for CloudMAC traffic while at the same time maintaining low latency for background traffic.

IEEE 802.11 WLANs are a very important technology to provide high speed wireless Internet access. Especially at airports, university campuses or in city centers, WLAN coverage is becoming ubiquitous leading to a deployment of hundreds or thousands of Access Points (AP). Managing and configuring such large WLAN deployments is a challenge. Current WLAN management protocols such as CAPWAP are hard to extend with new functionality. In this paper, we present CloudMAC, a novel architecture for enterprise or carrier grade WLAN systems. By partially offloading the MAC layer processing to virtual machines provided by cloud services and by integrating our architecture with OpenFlow, a software defined networking approach, we achieve a new level of flexibility and reconfigurability. In Cloud-MAC APs just forward MAC frames between virtual APs and IEEE 802.11 stations. The processing of MAC layer frames as well as the creation of management frames is handled at the virtual APs while the binding between the virtual APs and the physical APs is managed using OpenFlow. The testbed evaluation shows that CloudMAC achieves similar performance as normal WLANs, but allows novel services to be implemented easily in high level programming languages. The paper presents a case study which shows that dynamically switching off APs to save energy can be performed seamlessly with CloudMAC, while a traditional WLAN architecture causes large interruptions for users.