The standard beam management procedure in 5G requires the user equipment (UE) to periodically measure the received signal reference power (RSRP) on each of a set of beams proposed by the basestation (BS). It is prohibitively expensive to measure the RSRP on all beams and so the BS should propose a beamset that is large enough to allow a high-RSRP beam to be identified, but small enough to prevent excessive reporting overhead. Moreover, the beamset should evolve over time according to UE mobility. We address this fundamental performance/overhead trade-off via a Bayesian optimization technique that requires no or little training on historical data and is rooted on a low complexity algorithm for the beamset choice with theoretical guarantees. We show the benefits of our approach on 3GPP compliant simulation scenarios.

We provide the reader with an accessible yet rigorous introduction to Bayesian optimisation with Gaussian processes (BOGP) for the purpose of solving a wide variety of radio resource management (RRM) problems. We believe that BOGP is a powerful tool that has been somewhat overlooked in RRM research, although it elegantly addresses pressing requirements for fast convergence, safe exploration, and interpretability. BOGP also provides a natural way to exploit prior knowledge during optimization. After explaining the nuts and bolts of BOGP, we delve into more advanced topics, such as the choice of the acquisition function and the optimization of dynamic performance functions. Finally, we put the theory into practice for the RRM problem of uplink open-loop power control (OLPC) in 5G cellular networks, for which BOGP is able to converge to almost optimal solutions in tens of iterations without significant performance drops during exploration.

In the framework of queuing theory with multiclass jobs, trunk-reservation is an admission control technique to handle job class priority in an online fashion, and serve as many high priority jobs as possible. This is achieved by rejecting jobs with sufficiently low priority when the buffer space becomes a scarce resource, i.e., when the queue may soon overflow. Mathematically, the objective is to maximize the long-term reward of the admitted jobs, where each job is assigned a reward which is monotonic with respect to the priority class it belongs to. In this paper we study online learning of optimal trunk-reservation policies when the system parameters, i.e., class arrival rates and service time, are unknown. Starting from a Markov Decision Process (MDP) formulation, we leverage the stairway structure of the optimal policy to define Integer Gradient Ascent (IGA), a reinforcement learning (RL) algorithm based on policy-gradient methods, specifically tailored to the mathematical properties of the problem at hand. We provide theoretical results on the convergence properties of IGA. Extensive numerical experiments characterize its behavior and confirm that it outperforms standard RL techniques in terms of convergence rate.

Whether it is for network engineering or business intelligence insight purposes, it is crucial for an Internet Service Provider (ISP) to infer the Quality of Experience (QoE) perceived by the end user during a video streaming session. Specifically, it is important to detect video stalls as soon as they occur, to rapidly take counter-measures such as re-allocating resources more fairly among users. Video stalls fall into two different classes: (i) those caused by poor network conditions and (ii) those caused directly by the user when scrubbing or dragging the video playback forwards or backwards. However, only the former type of stalls degrade the QoE perceived by the end user. Therefore, in this paper we propose a technique to detect and classify stall events by observing the packets associated to a streaming session. We solve a least squares problem to minimize the distance between the estimated chunk's bitrate and the potential bitrate sequence that a plausible playback buffer dynamics would produce. This amounts to finding the maximally likely state sequence for a properly defined Hidden Markov Model. We propose two polynomial dynamic programming algorithms, one of which running in online fashion, computing the exact solution in the ideal case of complete and exact measurement set. We claim that our method is also applicable in an encrypted scenario, since it is robust with respect to the estimation error of a number of parameters, as we show via simulations.

Classic network control techniques have as sole objective the fulfillment of Quality-of-Service (QoS) metrics, being quantitative and network- centric. Nowadays, the research community envisions a paradigm shift that will put the emphasis on Quality of Experience (QoE) metrics, which relate directly to the user satisfaction. Yet, assessing QoE from QoS measurements is a challenging task that powerful Software Defined Network controllers are now able to tackle via machine learning techniques. In this paper we focus on a few crucial QoE factors and we first propose a Bayesian Network model to predict re- buffering ratio. Then, we derive our own novel Neural Network search method to prove that the BN correctly captures the discovered stalling data patterns. Finally, we show that hidden variable models based and context information boost performance for all QoE related measures.

To optimize routing of flows in datacenters, SDN controllers receive a packet-in message whenever a new flow appears in the network. Unfortunately, flow arrival rates can peak to millions per second, impairing the ability of controllers to treat them on time. Flow scheduling copes with such sheer numbers by segmenting the traffic between elephant and mice flows and by treating elephant flows in priority, as they disrupt short lived TCP flows and create bottlenecks. We propose a learning algorithm called SOFIA and able to perform optimal online flow segmentation. Our solution, based on stochastic approximation techniques, is implemented at the switch level and updated by the controller, with minimal signaling over the control channel. SOFIA is blind, i.e., it is oblivious to the flow size distribution. It is also adaptive, since it can track traffic variations over time. We prove its convergence properties and its message complexity. Moreover, we specialize our solution to be robust to traffic classification errors. Extensive numerical experiments characterize the performance of our approach in vitro. Finally, results of the implementation in a real OpenFlow controller demonstrate the viability of SOFIA as a solution in production environments.

The performance of computer networks relies on how bandwidth is shared among different flows. Fair resource allocation is a challenging problem particularly when the flows evolve over time. To address this issue, bandwidth sharing techniques that quickly react to the traffic fluctuations are of interest, especially in large-scale settings with hundreds of nodes and thousands of flows. In this context, we propose a distributed algorithm based on the alternating direction method of multipliers (ADMM) that tackles the multi-path fair resource allocation problem in a distributed SDN control architecture. Our ADMM-based algorithm continuously generates a sequence of resource allocation solutions converging to the fair allocation while always remaining feasible, a property that standard primal-dual decomposition methods often lack. Thanks to the distribution of all computer intensive operations, we demonstrate that we can handle large instances at scale.

Software‐Defined Networking and Network Function Virtualization are two paradigms that offer flexible software‐based network management. Service providers are instantiating Virtualized Network Functions, for example, firewalls, DPIs, gateways—to highly facilitate the deployment and reconfiguration of network services with reduced time‐to‐value. They use Service Function Chaining technologies to dynamically reconfigure network paths traversing physical and virtual network functions. Providing a cost‐efficient virtual function deployment over the network for a set of service chains is a key technical challenge for service providers, and this problem has recently caught much attention from both Industry and Academia. In this article, we propose a formulation of this problem as an Integer Linear Program that allows one to find the best feasible paths and virtual function placement for a set of services with respect to a total financial cost, while taking into account the (total or partial) order constraints for Service Function Chains of each service and other constraints such as end‐to‐end latency, anti‐affinity rules between network functions on the same physical node and resource limitations in terms of network and processing capacities. Furthermore, we propose a heuristic algorithm based on a linear relaxation of the problem that performs close to optimum for large scale instances. © 2017 Wiley Periodicals, Inc. NETWORKS, Vol. 71(2), 97–106 2018

We consider a multi‐domain network scenario and we study the Inter‐Domain Path Computation problem under the Domain Uniqueness constraint ( ‐ ), that is, a path cannot visit a domain twice. It is known that hierarchical Path Computation Element (h‐PCE) architecture, that is commonly used to solve ‐ , shows poor scalability with respect to the number of domains. For this reason, we devise a new domain clustering concept allowing one to artificially reduce the number of domains in an offline phase, in order to solve ‐ with lower complexity at run‐time. More specifically, we first prove the ‐completeness of the feasibility problem associated with ‐ and the inapproximability of ‐ itself. Yet, we show that the number of domains is the real computational bottleneck for the solution of ‐ . Then we provide a necessary and sufficient condition for a domain clustering to be proper, that is, without loss of optimality. Such a condition can be verified offline on the inter‐domain graph. We finally show via numerical experiments the impact of the inter‐domain treewidth on the computational speed‐up brought by proper clustering.

Content Delivery Networks (CDN) are witnessing the outburst of video streaming (e.g., personal live streaming or Video-on-Demand) where the video content, produced or accessed by mobile phones, must be quickly transferred from a point to another of the network. Whenever a user requests a video not directly available at the edge server, the CDN network must (1) identify the best location in the network where the content is stored, (2) set up a connection and (3) deliver the video as quickly as possible. For this reason, existing CDNs are adopting an overlay structure to reduce latency, leveraging the flexibility introduced by the Software Defined Networking (SDN) paradigm. In order to guarantee a satisfactory Quality of Experience (QoE) to users, the connection must respect several Quality of Service (QoS) constraints. In this paper, we focus on the sub-problem (2), by presenting an approach to efficiently compute and maintain paths in the overlay network. Our approach allows to speed up the transfer of video segments by finding minimum delay overlay paths under constraints on hop count, jitter, packet loss and relay node capacity. The proposed algorithm provides a near-optimal solution, while drastically reducing the execution time. We show on traces collected in a real CDN that our solution allows to maximize the number of fast video transfers.

Software-Defined Network (SDN) controllers include mechanisms to globally reconfigure the network in order to respond to a changing environment. While iterative methods are employed to solve flow optimization problems, demands arrive or leave the system changing the optimization instance and requiring further iterations. In this paper, we focus on the general class of iterative solvers considering an exponential decrease over time in the optimality gap. Assuming dynamic arrivals and departures of demands, the computed optimality gap at each iteration Q(t) is described by an auto-regressive stochastic process. At each time slot the controller may choose to apply the current iteration to the network or not. Applying the current iteration improves the optimality gap but requires flow reconfiguration which hurts QoS and system stability. To limit the reconfigurations, we propose two control policies that minimize the flow allocation cost while respecting a network reconfiguration budget. We validate our model by experimenting with a realistic network setting and using standard Linear Programming tools used in the SDN industry. We show that our policies provide a practical means of keeping the optimally gap small within a given reconfiguration constraint.

By offloading the control plane to powerful computing platforms running on commodity hardware, Software Defined Networking (SDN) unleashes the potential to operate computation intensive machine learning tools and solve complex optimization problems in a centralized fashion. This paper studies such an opportunity under the framework of the centralized SDN Admission Control (AC) problem. We first review and adapt some of the key AC algorithms from the literature, and evaluate their performance under realistic settings. We then propose to take a step further and build an AC meta-algorithm that is able to track the best AC algorithm under unknown traffic conditions. To this aim, we exploit a machine learning technique called Strategic Expert meta-Algorithm (SEA).

SDN unleashes the potential to perform computational intensive machine learning algorithms to solve complex routing problems. This demo presents an architecture for the SDN controller that integrates several online routing algorithms for the real-time admission control of new connection requests. The demonstrator permits to compare the evolution of the network according to the admission decisions taken by different online algorithms and to simulate future scenarios to support strategic decisions aimed at improving the infrastructure.

We consider a Dial-a-ride scenario in which one on-demand bus has to find an efficient route to serve different users willing to reach different destinations. We implemented in MATLAB a shortest path algorithm that minimizes a linear combination of an environmental cost and of the total waiting plus travel time experienced by the travellers. We demonstrate the outcome of the algorithm on the map of Dublin with the software SUMO.

In this paper we study mobile ad hoc wireless networks by using the notion of evolving connectivity graphs. In such systems, the connectivity changes over time due to the intermittent contacts of mobile terminals. In particular, we are interested in studying the expected flooding time when full connectivity cannot be ensured at each point in time. Even in this case, due to finite contact times durations, connected components may appear in the connectivity graph. Hence, this represents the intermediate case between extreme cases of fully mobile ad hoc networks and fully static ad hoc networks. By using a generalization of edge-Markovian graphs, we extend the existing models based on sparse scenarios to this intermediate case and calculate the expected flooding time. We also propose bounds that have reduced computational complexity.

We deal with interference channels with (i) delayed channel state information at the transmitter (CSIT), and (ii) delayed output feedback at the receiver and no CSIT. We extend the algorithm by Maleki et al. [8] for M = 3 users to any M ≥ 3 under the constraint that all the transmitter/receiver pairs are active simultaneously. We propose a retrospective interference alignment algorithm achieving M2/(M2-1) degrees of freedom (DoF) in the case (i) and an algorithm attaining [M/2]M/([M/2](M-1) + 1) DoF in the case (ii). However, larger DoF - 9/8 in (i) and 6/5 in (ii) - are easily achievable, for any M, when orthogonal channels (e.g. in time, frequency, etc.) are shared by triplets of transmitter/receiver pairs, and within each subchannel the algorithm by Maleki et al. [8] is applied. Hence, our work suggests that, for all M and both in the case (i) and in the case (ii), the strategy maximizing the DoF entails that three transmitter/receiver pairs are simultaneously active on the same channel.