By overcoming the “server box” barrier, resource disaggregation in data centers (DCs) can significantly improve resource utilization. This may then provide a more cost-efficient approach for resource upgrade and expansion. The advantages of resource disaggregation have been explored in earlier research to improve the efficiency of resource usage. This paper investigates the potential benefits of resource disaggregation from the aspect of reliability, which has not been considered before. Resource disaggregation gives rise to a new failure pattern. For example, in a conventional server, the failure of one type of resource leads to the failure of the entire server, so that other types of resources in the same server also become unavailable. After disaggregating, the failure of different types of resources becomes more isolated so that other resources are still available. In this paper, we model the reliability of a resource allocation request in a server-based or disaggregated DC based on whether the request is allocated with only working resources or is also provisioned with backup resources. We then consider a resource allocation problem to maximize the number of requests accepted with guaranteed reliability. This is formulated as an integer linear programming (ILP) problem, and a more straightforward heuristic approach is also proposed. Our numerical studies demonstrate that it may be possible to significantly improve service reliability with this resource disaggregation approach.

Multi-band transmission over existing fibers would be a key strategy for ongoing capacity expansion even though upgrading from conventional C-band to multi-band, such as the C+L-band transmission being deployed by operators, would be a slow and complex process. After the C+L band, which band should be upgraded first in the next stage is an open question. In this paper, we try to answer this by comparing the potential capacity increase and the investment cost to upgrade different bands. We propose an OSNR estimation model comprehensively covering various impairments to evaluate the quality of transmission of an optical channel. Along with routing and spectrum assignment, a traffic grooming algorithm is also developed to evaluate the capacity that can be achieved after upgrading different bands in an optical network. Our studies show that the E band should be the first to be upgraded next since it both expands the transmission capacity significantly using only a few additional amplifiers, and also improves the quality of transmission of the C+L band.

Data center virtualization is a flexible and efficient way to enable multiple users to share the common resources of a physical data center (DC). For efficient sharing, virtual data center (VDC) embedding is a vital problem that should be carefully addressed. However, existing studies on VDC embedding mostly assume that the capacity of each VDC is fixed, but do not consider the time-varying feature of resource demands. Considering the fact that the resource demands of most enterprise IT services exhibit the time-varying feature, resource allocation based on the fixed capacity assumption would cause a great inefficiency. To overcome this inefficiency, we propose a new VDC consolidation scheme that takes into account the time-varying feature of resource demands when embedding VDCs. We first develop a resource demand prediction model for each VDC using the Long Short-Term Memory (LSTM) neural network, which is used to predict the real-time resource demands of VDCs at different future moments. Based on the predicted resource demands, we then embed VDCs whose peaks and valleys of resource demands stagger each other onto common physical servers and links, such that the required physical resources can be minimized under the condition that all the resource demands of different VDCs are satisfied at all the different moments. An integer linear programming (ILP) model and a resource demand correlation-based heuristic algorithm are also developed for the proposed scheme. Simulation results show that the proposed consolidation scheme can significantly improve resource utilization in a DC. It can save up to 25 percent of physical servers and 29 percent of physical links used for accommodating the same requests as compared to a scheme assigning resources based on the fixed capacity assumption.

The rapidly evolving scenario around cellular networks, Internet of Things (IoT), and the associated services ecosystem has generated a wide range of expectations for the future networks. However, the unavailability of sufficient bandwidth and severe interference prohibit the existing commercially used radio-frequency (RF) bands from supporting some of these services. In this respect, the millimeter wave (mmWave)-based systems are seen as promising alternatives for supporting various high data rate enhanced mobile broadband (eMBB) services. Nevertheless, the adverse wave propagation characteristics in these bands and the resulting media access control (MAC) layer problems of beam blockage restrict these systems from operating in a reliable manner. Therefore, in this article, we propose a MAC layer-based approach of control delegation to tackle the problem of beam blockage. The mechanism uses policy-based relinquishment of access point (AP) control from the default AP to other AP capable member nodes to improve node visibility and alleviate the blockage scenario without requiring any additional network infrastructure. To account for the dynamic behavior of the network, a discrete-time Markov decision process (MDP)-based model is proposed. It uses a dynamic optimization methodology to accommodate multiple reconfigurable performance metrics, which can then be adjusted to cater to different performance criteria. Using computer simulations, we evaluate the effectiveness of our proposed solution for some alternate static and dynamic control policies. Our simulation results show that our proposed solution can significantly reduce the blockage in a network while satisfying a variety of performance objectives over different classes of indoor IoT scenarios.

The improved efficiency achieved by virtualizing data centers (DCs) has been well established. In this paper, we propose a mixed Virtual Data Center (VDC) capable of supporting both unicast and multicast services. We provide a new method to realize the embedding of these VDCs. We also provide a Mixed Integer Linear Programming (MILP) formulation and a scalable heuristic algorithm for efficiently embedding its demands. Numerical results show that mixed VDC embedding supporting both unicast and multicast services performs significantly better than existing embedding methods in terms of system cost, power consumption, link capacity utilization, and VDC acceptance ratio.

In this paper, we consider a simple relay network consisting of a source, an energy constrained decode-and-forward (DF) relay and a destination. The relay is assumed to harvest energy from radio frequency (RF) signals with a time splitting (TS) based energy harvesting (EH) architecture. The relay harvests energy from the source signal as well as from the interfering RF signal. A continuous time energy harvesting method is used where the relay harvests energy for a fraction of the total block time and the remaining time is used for information transmission. The harvested energy, in case of a linear EH model, increases linearly with increase in input power whereas in case of a nonlinear EH model it attains a maximum value and then gives diminishing returns with further increments in the input power. Therefore, the EH efficiency exhibits nonlinearity due to varying conversion efficiency for different input power. In this paper, we investigated the optimal value of the harvesting parameter by incorporating nonlinearity of EH circuit and the presence of the interfering signal. The performance is measured in terms of throughput of the DF relay network and the impact on it of different parameters e.g., interfering signal, noise variance at the relay, and nonlinearity of EH circuit. A MATLAB based simulation is performed to assess the performance.

Governments across the world have plans for a deep penetration of electric vehicles in the near future, for the transportation sector. This will require robust communications between the entities of the charging infrastructure, viz., the grid, aggregators, controllers, charging stations (CSs) and the electric vehicles (EVs). For analyzing the vehicle-to-grid and grid-to-vehicle infrastructure, it is important to model the electrical as well as the communication network together. This will help in determining the influences of the communication network in the operation of the controller and grid. In this paper, a distribution system with five CSs and sampled data transmission between the entities are modeled and simulated in MATLAB Simulink for understanding the potential impact of the networked communication system on the grid operation. A fuzzy-logic controller (FLC) is used in the model. The performance of the FLC in terms of root mean square values is found to improve when the inputs (node voltage and total energy available in CSs) are synchronized at faster sampling rates. Furthermore, it is shown that the performance of the FLC can be improved by bringing about changes in it (increasing the number of membership functions) and not merely synchronizing at a faster sampling rate.

Internet traffic demand keeps on increasing and tends to show strong bidirectional asymmetry. To tackle this asymmetry issue, we propose here a novel unidirectional design approach to alleviate the impact of asymmetry for elastic optical networks (EONs). We decouple a bidirectional transponder into an isolated unidirectional transmitter (Tx) and an isolated unidirectional receiver (Rx). Based on this, we further study how different multi-flow transmitters will affect the design performance, i.e., whether the transmitter is using an array of laser diodes or a broadband laser source with a filter to generate multiple sub-carriers. We evaluate the proposed approach by considering the routing and spectrum allocation (RSA) optimization problem, for which Integer Linear Programming (ILP) models and a SWP-based heuristic algorithm are developed. Simulation studies show that the proposed approaches are efficient to significantly improve the network capacity utilization and minimize the network cost compared to a network design limited to considering only bidirectional symmetric traffic flows.

We propose a joint routing and medium access control (MAC) protocol, named as JRAM, for reducing transmission delays in a many-to-one communication paradigm for wireless sensor networks (WSNs). Due to the wide variety of WSN applications, there is a need for protocol solutions optimized for specific application classes. JRAM is proposed for WSNs deployed for monitoring multiple events in the same geographic region which require prompt detection and response. In existing contention-based synchronous MAC protocols designed for this, a node gets only one chance to succeed in data transmission scheduling per cycle, and a sink can also only receive data packets from at most one node in a cycle. Therefore, endto-end transmission delay (E2ETD) and packet delivery ratio (PDR) of these protocols drastically degrade with the increase in event occurrence rate (EOR). In contrast, JRAM proposes a novel approach to provide k (k > 1) chances to a node to succeed in data transmission scheduling in a cycle, and also allows a sink to receive data packets from k nodes in the same cycle. This is done, in JRAM, by partitioning the network nodes into k disjoint sets and then using a novel cycle structure. We evaluate JRAM through extensive NS-2.35 simulations and compare its performance with existing pipelined data collection (PDC), adaptive data collection (ADC), and CROPMAC protocols, for different types of traffic loads and traffic patterns. Results suggest that in case of high EOR, JRAM outperforms PDC, ADC and CROPMAC both in terms of the E2ETD and the PDR.

The explosive growth of the Internet has resulted in tremendous growth of the data centers which primarily serve as the cloud computing backbones. We consider the practical architecture of a real data center where different types of services are implemented in different tiers. We use Model Predictive Control (MPC) based energy aware scheduling algorithms to address the resource allocation problem for deferrable jobs in such a tiered architecture, where the switching cost is accounted for in two different ways. We compare the performance of these two algorithms with respect to the important performance parameters of cumulative electricity cost, cumulative renewable usage and cumulative number of switchings. We discuss the results to provide some insightful understanding on these issues.

This paper deals with the design of a span-restorable (SR) elastic optical network under different spectrum conversion capabilities, including 1) no spectrum conversion, 2) partial spectrum conversion, and 3) full spectrum conversion. We develop Integer Linear Programming (ILP) models to minimize both the required spare capacity and the maximum number of link frequency slots used for each of the three spectrum conversion cases. We also consider using the Bandwidth Squeezed Restoration (BSR) technique to obtain the maximal restoration levels for the affected service flows, subject to the limited frequency slot capacity on each fiber link. Our studies show that the spectrum conversion capability significantly improves spare capacity efficiency for an elastic optical network.

Nodes in a wireless ad hoc network have to support routing using their limited battery power resource. The routing protocol involved should use battery power efficiently for good system performance. For systems where node location information is available, this study proposes an on-demand routing protocol for choosing a route based on maximising the minimum node battery power and minimising the total transmission power required to reach the destination. In addition, the routing protocol proposed is able to restrict control packet flooding during route discovery and pre-empt link breakages because of node mobility. A power and mobility aware optimisation problem is first formulated. For an actual practical implementation, we present a heuristic scheme, Power and Mobility Aware Routing or PMAR protocol. PMAR performs almost as well as the proposed optimisation approach in static networks. In mobile networks, PMAR performs very well in terms of network lifetime, the number of data packets carried within the network lifetime and delay performance. It is shown to be energy efficient, effective in restricting control packet flooding and able to substantially reduce the network overheads caused by link breakages.

This paper proposes a multicast traffic grooming scheme for efficient resource utilization in wavelength- division multiplexing (WDM) mesh networks. This Light-Tree Division -Adjacent Node Component based Grooming scheme (LTD-ANCG) is based on the idea of dividing a light-tree into smaller sub-light-trees. It improves the efficiency of resource utilization and lowers the optical- electronic-optical (OEO) conversion overhead. We use computer simulations to evaluate the performance of the scheme. Our simulations demonstrate that compared with existing algorithms, the new scheme significantly reduces the request blocking probability but can be implemented with very reasonable electronic processing.

IEEE 802.16 Wireless Broadband is a promising technology for providing last mile access. Quality of Service (QoS) is an important factor that has been addressed by the standard which defines four types of multimedia traffic classes. However resource allocation and scheduling between the traffic classes is vital in providing QoS which the standard has left undefined. In this paper we propose a Markov Chain analytical model for a queue based uplink scheduling algorithm proposed earlier. The algorithm is based on resource sharing between real time and non real time traffic depending on their queue size and latency requirements. We then compare the analytical and simulation results. We also propose an adaptive scheduling scheme based on the delay feed back for the real-time flows and compare its performance with fixed scheduling.

An ad hoc network is a wireless network constructed on a 'need-to-communicate' basis where the wireless nodes also have to support network infrastructure functions like routing. Since the nodes are likely to be power constrained, they will be reluctant to cooperate and use their limited power resources for forwarding packets for others. We propose an on-demand routing protocol that enforces cooperation by requiring nodes to forward so as to earn credits to pay for self transmissions. We also incorporate a forwarding rule that increases self transmissions in the cooperative environment. Simulation results show that, compared to pure AODV-like and pure reward-based on-demand routing, our proposed approach significantly extends the network's lifetime so that more data can be transmitted and carried during this period.

We consider WDM networks with lightpath switching where wavelengths may be converted, as required, along the lightpath. For efficient converter usage in such a network, sparse converter placement may be followed where only some of the network nodes are equipped with wavelength converters. Given the nominal network traffic pattern, we present a simple heuristic algorithm which may be used to determine the location of these converters for good network performance. For a network designed in this fashion, we consider the application of a path-metric based heuristic algorithm for lightpath routing and wavelength selection along the links of the selected route. Dynamic operation of the sparse converter network is considered using this path-metric based algorithm for lightpath routing and wavelength selection.

A limited-wavelength-interchangeable cross-connect (L-WIXC) is considered in this paper. While a (fully) wavelength-interchangeable cross-connect (WIXC) is functionally equivalent to a conventional switching matrix, the modeling of L-WIXC will differ from that of WIXC due to limitations in the wavelength interchange capability. We propose an analytical model for describing the connection setup in various L-WIXCs. Two methods for evaluating the blocking performances of L-WIXCs based on this model are introduced and applied for the analysis of four classes of L-WIXC.

In this paper we describe QNAT, a software tool developed at Indian Institute of Technology, Kanpur, India, for the analysis and simulation of queueing networks. Arbitrary configurations of open or closed networks of multi-server queues with infinite or finite capacity, fork-join queues with or without synchronization queues can be analyzed or simulated using QNAT. Queueing Networks with multiple classes of customers mall be specified with each class being a closed or an open class independently if there are finite capacity queues in the system, the type of blocking mechanism-transfer, repetitive service or rejection, can also be specified. For the applications where the accuracy of the results is important, an option to simulate the network is also provided. QNAT has proved to be a useful tool for the design of telecommunication systems, computer networks, modeling of industrial systems, design of banking systems, teaching courses and research on queueing theory etc. QNAT is a user-friendly analysis tool, developed with a Windows based Graphical User Interface (GUI). Mathematica forms the computing platform for QNAT due to its ability to perform symbolic computation.

In this paper we describe an approximate method for the analysis of an open network of finite capacity queues. Finite buffer capacities at the nodes introduce blocking of jobs that finish service at a node and find that the destination node is full at that time. When this happens, we assume that the blocked job is held at the server of the queue where it just completed service, blocking that server until the destination can accommodate it. This is called transfer blocking or blocking after service. We also assume that an external arrival that finds a full queue is lost. We consider an open queueing network with inter-arrival times of external arrivals and service times at each queue having a generalized exponential (GE) distribution. Queues can have finite buffers. To solve this system we augment the network by adding a "holding node" for every stream that can be blocked to hold the blocked jobs during the period corresponding to them blocking the server. The mean time spent in the holding node will be equal to that spent while being blocked. Also, to account for the increased service time of a blocked job as seen by customers behind it in the queue, the service times of these customers need to be increased. We thus use an iterative procedure to converge on to the parameters of the GE distributions of the inter-arrival and service time distributions. Results from our analysis are compared against simulations and they compare very well.