How to serve mobile users in rural areas by 5G networks is challenging due to the sparse distribution of base stations and poor connection to the cloud. Existing solutions focus on transmission frequency implementation such as frequency multiplexing, In this paper, we consider a decentralized caching scheme for two reasons. First, caching contents in the edge is an effective approach to reduce the transmission latency and improve the quality of service for mobile users. Second, the decentralized caching allows base stations to serve mobile users without any coordination of the cloud. Meanwhile, data privacy in the edge is critical for individual users. This paper aims to jointly determine the caching and routing policy in rural areas of 5G networks in a decentralized manner and simultaneously design a proper privacy-preserving mechanism. We tackle the challenges in two progressive steps. First, we design a decentralized algorithm with the convergence guarantee. Furthermore, we enhance the developed decentralized algorithm with a privacy-preserving mechanism based on (local) differential privacy and prove its privacy guarantee. We conduct extensive numerical simulations based on real-world traces to evaluate the proposed algorithms. Results highlight significant performance improvements compared to existing baselines.

The development of Virtual Network Functions (VNFs) migrates network functions from dedicated hardware to groups of commodity servers called network points of presence (N-PoPs). In this way, network services are redefined as interconnected VNFs called Service Function Chains (SFCs). The emerging of SFCs significantly reduces the cost of network services and improves scalability. However, the availability of SFCs brings new challenges since a failure of any N-PoP along an SFC affects its availability. In this paper, we propose two rerouting strategies to improve the availability of SFCs. First, we propose a local rerouting strategy to bypass the failed N-PoPs on SFCs using locally rerouted paths (LRPs). In the strategy, we formulate an optimization model to minimize the maximum load on links while deploying SFCs and LRPs to reduce the risk of congested links caused by local rerouting. We then propose an approximation algorithm to solve the optimization problem, preserving an approximation ratio of$\mathcal {O}(\log (|V|))$, where$|V|$is the number of N-PoPs in the network. We also propose an alternative heuristic algorithm to improve efficiency. Second, we propose a supplementary rerouting strategy with an online algorithm to provide supplementary rerouted paths when original SFCs and corresponding LRPs fail at the same time in the local rerouting strategy. The online algorithm is proved to have an$\mathcal {O}(\log (|V|))$competitive ratio to the offline optimum. Finally, our extensive simulation results show that the proposed algorithms can provide highly available SFCs with less congested links.

In this paper, we propose a novel server-centric network for data centers, called RRect. Compared to existing server-centric networks, RRect provides a more graceful degradation performance in the presence of component failure. Meanwhile, RRect enjoys a linear diameter to the network order and multiple parallel paths. We present algorithms to find paths and to construct all parallel paths between any pair of servers in RRect. We also show that without using any power-aware routing algorithm, RRect behaves more power efficient in its interconnection network. To meet today's stringent high availability requirement, RRect can be configured into redundancy and failover scheme. In particular, RRect can be configured into both symmetric and asymmetric redundancy modes to cater different applications' needs, which cannot be implemented in existing server-centric networks. Moreover, RRect gives more flexibility to adjust the network size. Given the same switches, by fine tuning the parameters, RRect provides numerous structures with different sizes, while preserving the properties of short diameter and multiple parallel paths. Our comprehensive simulations show that RRect gives much better graceful degradation performance in the presence of component failure, and RRect saves much energy in the interconnection network. Meanwhile, RRect can maintain the same performance on many critical metrics as BCube, including short diameter and excellent aggregate throughput. All these features make RRect a very empirical structure for enterprise dater center network products.

The development of Virtual Network Functions (VNFs) migrates network functions from dedicated hardware to groups of commodity servers called network points of presence (N-PoPs). Thus, network services are redefined as interconnected VNFs called Service Function Chains (SFCs). SFC has the potential to reduce costs of network services and improve scalability. However, the availability of SFC brings new challenges since a failure of any N-PoP along the SFC affects its availability. Deploying backup SFCs is a practical method to improve the availability of SFCs, but inappropriate deployments of backups may trigger the unnecessary capacity expansion of N-PoPs and thus waste VNF resources. In this paper, we solve this problem by proposing an optimization model called partial service function chain mapping. The model adopts partial SFC rerouting strategy for smaller rerouting delay and minimizes the maximum load on N- PoPs to reduce unnecessary capacity expansion of N- PoPs. We then propose a randomized rounding algorithm to solve the optimization problem, preserving the competitive ratio of O(log n), where n is the number of NPoPs in the network. Our extensive simulation results show that the proposed algorithm can significantly improve the availability of SFCs and limit the capacity expansion of N-PoPs.

In this paper, we study virtual network embedding problem in hybrid data center networks (HDCN), where each top-on-rack switch is equipped with a directional antenna. Those antennas can dynamically construct a wireless network in the on-demand way, regarding to the current traffic flow. Hence, HDCN has a great potential to alleviate the over- subscription problem suffered by traditional data centers. However, how to embed virtual networks in HDCN while fully utilizing the benefits introduced by the wireless links remains as an open topic. To this end, we jointly consider virtual network embedding and the antenna scheduling. In particular, in our model, to some extend, over-subscription in links is acceptable. We first abstract the studied problem into an integer programming problem. Then we provide a heuristic algorithm to find sub- optimal solutions to the problem. Extensive simulation based evaluation has shown the great efficiency of the proposed algorithm, which makes it a promising solution for VNE in HDCN.

The recent development of network function virtualization decouples network functions from dedicated hardware. Thus, virtual network functions (VNFs) can be distributed onto shared and virtualized platforms held by multiple data centers in various network locations. The architecture of the distributed VNFs interconnected by virtual links is denoted as the Service Function Chain (SFC). SFC has the potential to significantly reduce the opening and operating cost of the network services while improving the flexibility. However, the availability of SFC on chained up data centers is always inferior to that of network functions running on a single data center because the failure in any data center on the chain may affect its availability. To improve the availabilities of SFCs, in this paper we propose a local rerouting strategy to bypass the failed data centers on SFCs using locally rerouted paths (LRPs). Furthermore, we formulate an optimization model to minimize the maximum load on links while deploying SFCs and LRPs into the network. Thus, we reduce the potential risk of congested links caused by the local rerouting strategy. We then propose a randomized rounding approximation algorithm to solve the optimization problem, preserving the competitive ratio of O(logn) for the model. We also propose a fast heuristic algorithm to improve the efficiency. Our extensive simulation results show that the proposed algorithms can provide highly available SFCs with more balanced link load.

Designing a cost-effective network for data centers that can deliver sufficient bandwidth and provide high availability has drawn tremendous attentions recently. In this paper, we propose a novel server-centric network structure called RCube, which is energy efficient and can deploy a redundancy scheme to improve the availability of data centers. Moreover, RCube shares many good properties with BCube, a well known server-centric network structure, yet its network size can be adjusted more conveniently. We also present a routing algorithm to find paths in RCube and an algorithm to find multiple parallel paths between any pair of source and destination servers. In addition, we theoretically analyze the power efficiency of the network and availability of RCube under server failure. Our comprehensive simulations demonstrate that RCube provides higher availability and flexibility to make trade-off among many factors, such as power consumption and aggregate throughput, than BCube, while delivering similar performance to BCube in many critical metrics, such as average path length, path distribution and graceful degradation, which makes RCube a very promising empirical structure for an enterprise data center network product.

As the advanced development of directional antenna, wireless technique has been introduced into data center networks, denoted as hybrid data center networks (HDCN). HDCN shows its great potential to mitigate the over-subscription problem in higher level links in traditional data centers.However, how to implement network virtualization in HDCN such that all the wireless links can be sufficiently utilized remains a challenging problem. In this paper, we study virtual network embedding problem in HDCN, by jointly considering embedding virtual networks and scheduling the directional antennas. We first summarize this problem intoan integer programming problem, then propose a heuristic algorithm to find a near optimal solution for the studied problem. The simulation based evaluation shows the great efficiency for the proposed algorithm deriving a suboptimal solution in HDCN.

Virtual network embedding has been widely studied for decades in backbone network, as it provides a promising way to resolve the conflict between flexibility of higher layer applications and rigidity of lower layer hardware, by allowing multiple heterogeneous virtual networks designed for different big data services to coexist and share the same infrastructure underneath. On the other hand, as the advanced development of directional antenna, wireless technique has also been introduced into data center networks, denoted as hybrid data center networks (HDCN). HDCN shows its great potential to mitigate the over-subscription problem in higher level links in traditional data centers. However, how to implement network virtualization in HDCN such that all the wireless links can be sufficiently utilized remains a challenging problem. In this paper, we study virtual network embedding problem in HDCN environment, by jointly considering embedding virtual networks and scheduling the directional antennas. We first summarize this problem into an integer programming problem, then propose a heuristic algorithm to find solutions to this problem. Extensive simulations reveal that the proposed algorithm efficiently provides a near-optimal solution. These features make it a promising VNE solution to HDCN environment.

Designing a cost-effective network for data centers that can deliver sufficient bandwidth and provide high availability has drawn tremendous attentions recently. In this paper, we propose a novel server-centric network structure called RCube, which is energy efficient and can deploy a redundancy scheme to improve the availability of data centers. Moreover, RCube shares many good properties with BCube, a well known server-centric network structure, yet its network size can be adjusted more conveniently. We also present a routing algorithm to find paths in RCube and an algorithm to build multiple parallel paths between any pair of source and destination servers. In addition, we theoretically analyze the power efficiency of the network and availability of RCube under server failure. Our comprehensive simulations demonstrate that RCube provides higher availability and flexibility to make trade-off among many factors, such as power consumption and aggregate throughput, than BCube, while delivering similar performance to BCube in many critical metrics, such as average path length, path distribution and graceful degradation, which makes RCube a very promising empirical structure for an enterprise data center network product.

In this paper, we propose a novel server-centric network for data centers, called RRect. Compared to existing server-centric networks, RRect has a linear diameter to the network order and abundant parallel paths with near-equal lengths, so that traffic in RRect enjoys a short and predictable communication latency. We present an efficient routing algorithm to find paths between any pair of servers in RRect. A complete addressing scheme and recursive RRect construction procedure are also provided in this paper. Meanwhile, to meet today's stringent high availability requirement, unlike existing server-centric network structures, RRect can be configured into redundancy and failover scheme, in which the backup server can fully take the place of the corresponding malfunctioning server without losing topological advantages, such as multiple near-equal parallel paths. Our comprehensive simulations show that RRect gives a better average path lengths and a more balanced path distribution among all pairs of servers. Meanwhile, RRect can maintain the same performance on many critical metrics as BCube, including short diameter and excellent aggregate throughput. All these features make RRect a very empirical structure for enterprise dater center network products.

Designing a cost-effective network topology for data centers that can deliver sufficient bandwidth and consistent latency performance to a large number of servers has been an important and challenging problem. Many server-centric data center network topologies have been proposed recently due to their significant advantage in cost efficiency and data center agility, such as BCube, FiConn, and Bidimensional Compound Network (BCN). However, existing server-centric topologies are either not expandable or demanding prohibitive expansion cost. As the scale of data centers increases rapidly, the lack of expandability in existing server-centric data center networks imposes a severe obstacle for data center upgrade. In this paper, we present a novel server-centric data center network topology called BCube connected crossbars (BCCCs), which can provide good network performance using inexpensive commodity off-the-shelf switches and commodity servers with only two network interface card (NIC) ports. A significant advantage of BCCC is its good expandability. When there is a need for expansion, we can easily add new servers and switches into the existing BCCC with little alteration of the existing structure. Meanwhile, BCCC can accommodate a large number of servers while keeping a very small network diameter. A desirable property of BCCC is that its diameter increases only linearly to the network order (i.e., the number of dimensions), which is superior to most of the existing server-centric networks, such as FiConn and BCN, whose diameters increase exponentially with network order. In addition, there are a rich set of parallel paths with similar length between any pair of servers in BCCC, which enables BCCC to not only deliver sufficient bandwidth capacity and predictable latency to end hosts, but also provide graceful performance degradation in case of component failure. We conduct comprehensive comparisons between BCCC with other popular server-centric network topologies, such as FiConn and BCN. We also propose an effective addressing scheme and routing algorithms for BCCC. We show that BCCC has significant advantages over the existing server-centric topologies in many important metrics, such as expandability, server port utilization, and network diameter.

A new network structure called BCube Connected Crossbars (BCCC) was recently proposed. Its short diameter, good expandability and low cost make it a very promising topology for data center networks. However, it can utilize only two NIC ports of each server, which is suitable for nowadays technology, even though more NIC ports are available. Due to technology advances, servers with more NIC ports are emerging and they will become low-cost commodities some time later. In this paper, we propose a more general server-centric data center network structure, called GBC3, which can utilize inexpensive commodity off-the-shelf switches and servers with any fixed number of NIC ports and provide good network properties. Like BCCC, GBC3 has good expandability. When doing expansion, there is no need to alter the existing system but only to add new components into it. Thus the expansion cost that BCube suffers from can be significantly reduced in GBC3. We also introduce an addressing scheme and several efficient routing algorithms for one-to-one, one-to-all and one-to-many communications in GBC3 respectively. We make comprehensive comparisons between GBC3 and some popular existing structures in terms of several critical metrics, such as diameter, network size, bisection bandwidth and capital expenditure. We also conduct extensive experiments to evaluate GBC3, which show that GBC3 achieves the best flexibility to make tradeoff among all these critical metrics and it can suit for many different applications by fine tuning its parameters.

BCube Connected Crossbars (BCCC) is a recently proposed network structure with short diameter and good expandability for cloud-based networks. Its diameter increases linearly to its order (dimension) and it has multiple near-equal parallel paths between any pair of servers. These advantages make BCCC a very promising network structure for next generation cloud-based networks. An efficient routing algorithm for BCCC has also been proposed, in which a permutation is used to determine which order (or dimension) will be routed first. However, there is no discussion yet about how to choose the permutation. In this paper, we mainly focus on permutation generations for routing in BCCC. We analyze the impact of choosing different permutations in both theory and simulation and propose two efficient permutation generation algorithms which take advantage of BCCC structure and give good performance.

A new network structure called BCube Connected Crossbars (BCCC) was recently proposed. Its short diameter, good expandability and low cost make it a very promising topology for data center networks. However, it can utilize only two NIC ports of each server, which is suitable for nowadays technology, even when more ports are available. Due to technology advances, servers with more NIC ports are emerging and they will become low-cost commodities some time later. In this paper, we propose a more general server-centric data center network structure, called Advanced BCube Connected Crossbars (ABCCC), which can utilize inexpensive commodity off-the-shelf switches and servers with any fixed number of NIC ports and provide good network properties. Like BCCC, ABCCC has good expandability. When doing expansion, there is no need to alter the existing system but only to add new components into it. Thus the expansion cost that BCube suffers from can be significantly reduced in ABCCC. We also introduce an addressing scheme and an efficient routing algorithm for one-to-one communication in ABCCC. We make comprehensive comparisons between ABCCC and some popular existing structures in terms of several critical metrics, such as diameter, network size, bisection bandwidth and capital expenditure. We also conduct extensive simulations to evaluate ABCCC, which show that ABCCC achieves the best trade off among all these critical metrics and it suits for many different applications by fine tuning its parameters.

Many server-centric data center network topologies have been proposed recently due to their significant advantage in cost-efficiency and data center agility, such as BCube, FiConn and BCN. However, existing server-centric topologies are either not expandable or demanding prohibitive expansion cost. As the scale is increasing rapidly, the lack of expandability imposes a severe obstacle for data center upgrade. In this paper, we present a novel server-centric data center network topology called BCube Connected Crossbars (BCCC), which can provide good network performance and expandability using commodity off-the-shelf switches and commodity servers with only two NIC ports. BCCC can accommodate a large number of servers while keeping a very small network diameter, as a particular desirable property of BCCC is that its diameter increases only linearly to the network order, which is superior to most of existing server-centric networks, such as FiConn and BCN, whose diameters increase exponentially with network order. Additionally, we propose an effective addressing scheme and routing algorithms for BCCC. We also conduct comprehensive comparisons between BCCC and other popular server-centric networks. We show that BCCC has significant advantages over existing server-centric topologies in many important metrics, such as expandability, port utilization and network diameter.