Adaptive optimization is critical in federated learning, where enabling adaptivity on both the server and client sides has proven essential for achieving optimal performance. However, the scalability of such jointly adaptive systems is often hindered by resource limitations in communication and memory. In this paper, we introduce a class of efficient adaptive algorithms, named $FedAda^2$ and its enhanced version $FedAda^2$++, designed specifically for large-scale, cross-device federated environments. $FedAda^2$ optimizes communication efficiency by avoiding the transfer of preconditioners between the server and clients. Additionally, $FedAda^2$++ extends this approach by incorporating memory-efficient adaptive optimizers on the client side, further reducing on-device memory usage. Theoretically, we demonstrate that $FedAda^2$ and $FedAda^2$++ achieve the same convergence rates for general, non-convex objectives as its more resource-intensive counterparts that directly integrate joint adaptivity. Extensive empirical evaluations on image and text datasets demonstrate both the advantages of joint adaptivity and the effectiveness and efficiency of $FedAda^2$/$FedAda^2$++.

The rise of 5G mobile networks necessitated virtualized Radio Access Network (vRAN) deployment, whereby radio functions are softwarized. This involves disaggregating traditional Baseband Units (BBUs) into Radio units (RU), Distributed Units (DUs), and Centralized Units (CUs) and dynamically instantiating radio network functions onto these for efficient resource optimization. However, establishing a robust vRAN for 5 G encounters challenges due to diverse application scenarios like Ultra-Reliable Low-Latency Communication (URLLC), Enhanced Mobile Broadband (eMBB), and Massive Machine Type Communication (mMTC), each with a specific service requirement. This paper studies the challenges involved in the optimal placement of radio network functions onto the disaggregated vRAN components while slicing the network to support diverse 5 G application scenarios. The paper models a 5 G vRAN and proposes an Integer Linear Programming (ILP) framework - SliAvailRAN, which maximizes the service provider’s profit by optimally allocating virtualized network functions for 5G application scenarios. We evaluate SliAvailRAN on two realistic topologies (with multiple variants) and show results for request acceptance and achieved centralization levels.

Network Function Virtualization (NFV) is a promising technology that can transform how internet service providers deliver their services. However, recent studies have identified several challenges in adopting NFV. Two key challenges are central to the operation and capacity planning of NFV Data Centers (DCs): (i) Service Function Chain (SFC) realization —determining if a new request with a known profile can be accommodated—and (ii) Network Function Virtualization (NFV) traffic bounds estimation —estimating the total traffic that a data center can handle considering all service requests and their performance constraints. To address these challenges, we propose a model that leverages stochastic network calculus to effectively dimension an NFV DC while ensuring delay and availability bounds for all service requests. Our theoretical model provides a mathematical framework to assess the realization of a single SFC request without delving into the specifics of the realization process. We utilize established availability-aware Virtual Network Function (VNF) placement patterns to obtain traffic bounds essential to planning data center capacity. We analyze NFV data center traffic under various scenarios over a Fat-tree DC topology. The results demonstrate that data center capacity is significantly influenced by the VNF placement strategy. Additionally, for data centers hosting latency-sensitive services, Service Level Objective (SLO) constraints on availability and delay are crucial in determining the number of such requests that can be accommodated.

We present Vercel, a network verification and automatic fault rectification tool that is based on a computationally tractable, algorithmically expressive, and mathematically aesthetic domain of linear algebra. Vercel works on abstracting out packet headers into standard basis vectors that are used to create a port-specific forwarding matrix$\mathcal {A}$, representing a set of packet headers/prefixes that a router forwards along a port. By equating this matrix$\mathcal {A}$and a vector b (that represents the set of all headers under consideration), we are able to apply least squares (which produces a column rank agnostic solution) to compute which headers are reachable at the destination. Reachability now simply means evaluating if vector b is in the column space of$\mathcal {A}$, which can efficiently be computed using least squares. Further, the use of vector representation and least squares opens new possibilities for understanding network behavior. For example, we are able to map rules, routing policies, what-if scenarios to the fundamental linear algebraic form,$\mathcal {A}x=b$, as well as determine how to configure forwarding tables appropriately. We show Vercel is faster than the state-of-art such as NetPlumber, Veriflow, APKeep, AP Verifier, when measured over diverse datasets. Vercel is almost as fast as Deltanet, when rules are verified in batches and provides better scalability, expressiveness and memory efficiency. A key highlight of Vercel is that while evaluating for reachability, the tool can incorporate intents, and transform these into auto-configurable table entries, implying a recommendation/correction system.

We examine how to provide applications with dedicated bandwidth and guaranteed latency in a programmable mission-critical network. Unlike other SDN approaches such as B4 or SWAN, our system Tuneman optimizes both routes and packet schedules at each node to provide flows with sub-second bandwidth changes. Tuneman uses node-level optimization to compute node schedules in a slotted switch and does dynamic routing using a search procedure with Quality of Service– (QoS) based weights. This allows Tuneman to provide an efficient solution for mission-critical networks that have stringent QoS requirements. We evaluate Tuneman on a telesurgery network using a switch prototype built using FPGAs and also via simulations on India’s Tata Network. For mission-critical networks with multiple QoS levels, Tuneman has comparable or better utilization than SWAN while providing delay bounds guarantees.

This paper proposes Trailnet, a deep reinforcement learning approach to predict the output port (of a router) for an IP packet based on its destination IP address. Trailnet attempts to replace the forwarding table at an IP router with a computational model. To optimally learn each router’s forwarding decisions, we propose to train the Artificial Neural Network (ANN) of Trailnet with value iteration and stochastic gradient descent. Through the value iteration algorithm, Trailnet estimates the cost of IP packet forwarding along different ports of a router and eventually selects a port that optimizes a cost function. We evaluate the generalization capability of the ANN on two sufficiently large service provider’s network topologies containing millions of IP addresses. Our evaluations show that Trailnet achieves high accuracy and fast inference time for predicting the correct output ports for incoming IP packets. Our results support the claim of replacing forwarding tables and distributed protocols (for computing shortest paths) with a computation model while operating at a high line rate in IP routers.

Network slicing is a key enabler for next-generation 5G services. Slices are designed to offer different services by conjoining virtual network functions (VNFs) through a logical network. We propose a dynamic slicing algorithm, which is based on utility theory and facilitates the growth, provisioning, dimensioning and deletion of network slices. The proposed algorithm is based on a utility model that regulates the virtual topology of VNFs in data-centers. The algorithm optimizes the number of slices as well as instantiated VNFs, thereby creating/modifying and destroying network slices of appropriate granularity. In addition, we also propose a stochastic optimization formulation, which handles uncertainty in service requests. We simulate the algorithm for a multi-data-center model with a large set of slices. Our results indicate dynamism, robustness and scalability of the proposed algorithm.

We consider the availability of applications in a large provider network environment. Our primary goal is to design a service provider network for high-availability using multiple components that have different availability. Initially, we model a modern provider architecture that is spread across the access, metro and core regions. We want to answer the specific question as to what amount of over-the-top (OTT) services can be provisioned over a given network while achieving a predesired availability value. To this end, we formulate a constrained optimization model whose objective is revenue maximization subject to availability measures. Two heuristics are also proposed that fathom the breadth of the virtual network function (VNF) deployment parameters: VNF licensing cost and server utilization. A simulation model presents comparative data for efficiency and server utilization as well as validates our optimization model. The results stress the importance of our optimization model in planning the network, as well as planning VNF placement ahead in time.

Optimal path planning and smooth trajectory planning are critical for effective navigation of mobile robots working towards accomplishing complex missions. For autonomous, real time and extended operations of mobile robots, the navigation capability needs to be executed at the edge. Thus, efficient compute, minimum memory utilization and smooth trajectory are the key parameters that drive the successful operation of autonomous mobile robots. Traditionally, navigation solutions focus on developing robust path planning algorithms which are complex and compute/memory intensive. Bidirectional-RRT(Bi-RRT) based path planning algorithms have gained increased attention due to their effectiveness and computational efficiency in generating feasible paths. However, these algorithms neither optimize memory nor guarantee smooth trajectories. To this end, we propose a kinematically constrained Bi-RRT (KB-RRT) algorithm, which restricts the number of nodes generated without compromising on the accuracy and incorporates kinodynamic constraints for generating smooth trajectories, together resulting in efficient navigation of autonomous mobile robots. The proposed algorithm is tested in a highly cluttered environment on an Ackermannsteering vehicle model with severe kinematic constraints. The experimental results demonstrate that KB-RRT achieves three times (3 X) better performance in terms of convergence rate and memory utilization compared to a standard Bi-RRT algorithm.

SDNs could be a game changer for next generation provider networks. OpenFlow (OF) - the dominant SDN protocol, is rigid in its South Bound Interface (SBI) - any new protocol field that the hardware must support, must await complete OF standardization. In contrast, OF alternatives such as protocol oblivious forwarding (POF) and ForCES have simpler schemes for insertion of new protocol identifiers. Even with these there is an inherent limitation on network hardware - the tables must support specific table format and configuration at each node as per protocol semantics. We ask the question - can we design an open system - one that is carrier-class, yet able to meet the requirements of any protocol forwarding/action with a minimal set of dataplane function. We propose bitstream, a low-latency, source-routing based scheme that can support new protocols, be compatible with existing protocols and facilitate a minimum semantic set for acting on a packet. A prototype is built to show bitstream working.

Network Function Virtualization (NFV) has the potential to transform the way providers do business. In particular, NFV can be an ideal solution for the current provider situation - whereby revenue is decreasing (due to competition), bandwidth requirements are increasing and the cost of provisioning increases with the bandwidth requirements. In such a situation, NFV can be a real game-changer, in terms of providing alternate avenues towards saving CapEx and OpEx, while also facilitating a new set of portfolio services to the end user. We model a realistic service provider and measure the impact of NFV on current network deployment. We then compute price-points at which it would start to make sense for a provider to indulge in NFV. Our simulations and optimizations study has built-in robustness that facilitate stability of the results across traffic variations as well as provider types.

Current deployment of wireless community networks and wireless municipal services utilizes multi-hop backbone mesh network technology to provide ubiquitous Internet connectivity to the end users. IEEE 802.11s Wireless Mesh Network (WMN) is a promising technology to increase spatial reuse in a mesh backbone using high gain directional antennas. Uses of directional communication in a multi-interface mesh network introduce the problem of unbalanced traffic allocation among the end-to-end flows that results in inefficient channel access using the standard EDCA mechanism. Furthermore, the forwarding protocol should coordinate with the channel access to improve the network performance. In this paper, a localized distributed mechanism is proposed to share the channel bandwidth effectively among interfering interfaces based on the solution of the balanced traffic allocation problem. The standard forwarding algorithm is augmented to use the channel access information effectively in a dynamic network scenario. The performance of the proposed scheme is evaluated through the results obtained from a practical indoor IEEE 802.11n+s directional multi-interface mesh testbed.

Single channel multi-interface IEEE 802.11s Wireless Mesh Network(WMN) is a promising technology for increasing spatial reuse of wireless channel using high gain directional antennas. Use of single channel in WMN is advantageous for providing different services (like community mesh networking, vehicular mesh networking etc.) by different frequency channels so that several wireless networking services can co-exist. However, for effective use of multi-interface multi-beam directional antennas in single channel environment, proper scheduling of interfaces and prioritization among different beams are required to minimize channel interference. In this paper a distributed mechanism is proposed to share bandwidth effectively among different interfaces in a probabilistic way based on local communication and interference information. A beam prioritization mechanism is used based on IEEE 802.11s EDCA to minimize under-use or overuse of channel bandwidth by a directional beam and maximize concurrent packet transmission. Simulation result shows that the proposed scheme improves efficiency of the network over standard IEEE 802.11s EDCA based MAC protocol.

A novel technique for inserting basestations on an ad-hoc basis is investigated. Sector retraction and extension is used to reshape the network coverage area. Basestations are generally added to the network whenever there is a need to meet an increasing capacity demand. The replanning exercise can be both costly and time consuming. Situation awareness (SA) is the enabling functionality that allows a network redesign without a drain on resources. The simulation involves loading the network to capacity and evaluating the performance of adding a basestation 'on the fly'. Spectrum efficiency is the measure of performance used. Reconfiguration of the network area is performed by controlling the power level of the downlink pilot channel through the use of a genetic algorithm (GA). The performance of the algorithm is determined by its ability to reconfigure and redistribute the traffic. The technique is shown to offer a flexible and simple solution to the problem of UMTS network replanning for additional capacity.

This paper examines the implementation of an automated W-CDMA microcellular deployment and coverage reconfiguration algorithm based on the concepts of situation awareness (SA). A deterministic microcellular propagation model (Citrus) is used to provide the detailed site-specific propagation data. An initial network deployment is performed over one square kilometre of central Bristol using the combination algorithm for total optimisation (CAT). Buildings are then added or removed from the microcell to represent realistic time variations in the geographic environment. A new situation awareness (SA) algorithm is developed and applied to the modified W-CDMA microcell to automatically reconfigure the network's coverage and capacity based on the new propagation environment. Optimisation of coverage and capacity is achieved through the use of a genetic algorithm (GA). This paper presents the details of the underlying SA algorithm and the results obtained for the above scenario. These new algorithms are shown to automatically sustain a high grade of service as the microcellular environment evolves over time. Gains of up 203% in spectral efficiency were observed for the 144 kbps service.