Port-based teleportation is a variant of quantum teleportation, where the receiver can choose one of the ports in his part of the entangled state shared with the sender, but cannot apply other recovery operations.We show that the optimal fidelity of deterministic port-based teleportation (dPBT) using <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</i> = <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i> + 1 ports to teleport a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">d</i>-dimensional state is equivalent to the optimal fidelity of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">d</i>-dimensional unitary estimation using n calls of the input unitary operation. From any given dPBT, we can explicitly construct the corresponding unitary estimation protocol achieving the same optimal fidelity, and vice versa. Using the obtained one-to-one correspondence between dPBT and unitary estimation, we derive the asymptotic optimal fidelity of port-based teleportation given by 1 − <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O(d⁴)N−2</i> ≤ <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F</i> ≤ 1−Ω(<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">d</i>4)<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</i>−2, which improves the previously known result given by 1 − <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O(d⁵)N−2</i> ≤ F ≤ 1 − Ω(d2)N−2. We also show that the optimal fidelity of unitary estimation for the case n ≤ d − 1 is <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F</i> = n+1/<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">d²</i> , and this fidelity is equal to the optimal fidelity of unitary inversion with <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i> ≤ <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">d</i> − 1 calls of the input unitary operation even if we allow indefinite causal order among the calls.

Lightweight anonymity protocols provide a well-balanced anonymity and performance by encrypting and decrypting only packet headers under the active and local adversary threat model. Among them, PHI and dPHI are promising in universally providing relationship anonymity. However, when overlaid onto IP, they are susceptible to the router skipping attack, where honest routers are skipped by malicious routers. Although this attack poses a significant threat to anonymity, its prevention is challenging due to the lack of path integrity in these protocols. To address this limitation, this paper integrates path validation into dPHI. This integration is non-trivial, as anonymity and path validation are inherently contradictory requirements. This paper designs and implements pPHI, a novel protocol, and analyzes pPHI in terms of security and performance.

Although secure channels are an essential building block of data plane protocols, their realization on programmable switches remains a significant challenge. Typical approaches offload the computation of authenticated encryption to external devices, compromising either speed or flexibility. Similarly, recent efforts to implement existing constructions of authenticated encryption on the switches face performance limitations due to the numerous recirculations required. This paper presents a novel construction and implementation of authenticated encryption on the switches. It incorporates two instances of Chaskey, a PRF with high compatibility with the switches, to achieve both confid-entiality and integrity with fewer recirculations, integrated using the EtM approach. Multi-block data are handled in CCM mode, implemented through a block rotation mechanism. Furthermore, a divide-and-conquer method realized through packet multi-furcation and rendezvous further reduces recirculations. The construction is verified for security, and its implementation on a Tofino 2 switch exhibits substantial performance improvements.

Programmable switches offer a promising platform for fast and flexible in-network computing. However, a standard mechanism, packet recirculation, degrades throughput due to bandwidth consumption caused by the loopback of not only packet headers but also cumbersome payloads. This paper proposes P4QRS, a mechanism that reduces payload recirculation by retaining payloads within the switch. Specifically, P4QRS bifurcates packets into headers and payloads, which undergo the computation process through pipelines and the buffering process leveraging the switch’s queue behavior, respectively. The headers and payloads then rendezvous for reassembly into complete packets to be sent out. To validate its effectiveness, we evaluated P4QRS through both an analytical model and implementation on state-of-the-art hardware programmable switches. Our results demonstrate that P4QRS operates stably and significantly accelerates complex in-switch computations. Moreover, we address packet reordering, which is a fundamental concern arising because P4QRS performs payload buffering on a per-packet basis rather than per-flow. After identifying the mechanism for developing packet reordering in three stages, we design, implement, and evaluate mitigation strategies targeting each stage. These strategies effectively suppress packet reordering in both flow-aware and flow-unaware cases.

Secure communication relies heavily on authenticated encryption (AE). This poster implements ChaCha20Poly1305, a widely-used AE scheme, on a smartNIC, which is particularly beneficial for high-speed networks. The key design rationale is manually optimizing data layout on hierarchical memory devices on the smartNIC. Our implementation achieves$5.67 \times 10^{6}$and$0.58 \times 10^{6}$packets/s for 64-byte and 1024-byte packets, respectively. As a use case of our AE implementation, we also implement a subset of TLS.

Recent work shows that programmable switches can effectively detect attack traffic, such as denial-of-service attacks in the midst of high-volume network traffic. However, these techniques primarily rely on sampling or sketch-based data structures, which can only be used to approximate the characteristics of dominant flows in the network. As a result, such techniques are unable to effectively detect low-volume attacks that stealthily add only a few packets to the network. Our work explores how the combination of programmable switches, Smart network interface cards, and hosts can enable fine-grained analysis of every flow in a network, even those with only a small number of packets. We focus on analyzing packets at the start of each flow, as those packets often can help indicate whether a flow is benign or suspicious. We propose a unified architecture that spans the full programmable dataplane to take advantage of the strengths of each type of device. We are developing new filter data structures to efficiently track flows on the switch, dataplane-based communication protocols to quickly coordinate between devices, and caching approaches on the SmartNIC that help minimize the traffic load reaching the host. Our preliminary prototype can handle the full pipe bandwidth of 1.4 Tbps of traffic entering the Tofino switch, forward only 20 Gbps to the SmartNIC, and minimize the traffic load to 5 Gbps reaching the host due to our efficient flow filter, packet batching, and SmartNIC-based cache.

Programmable switches are promising platforms for fast and flexible in-network computation; however, a standard mechanism, packet recirculation, degrades throughput due to bandwidth consumption caused by the loopback of not only packet headers but also cumbersome payloads. This paper proposes$\mathrm{P}^{4} \text{QRS}$, a mechanism for retaining payloads within the switch, reducing payload recirculations. Specifically,$\mathrm{P}^{4}$QRS bifurcates packets into headers and payloads, which undergo the computation process through pipelines and the buffering process leveraging the switch's queue behavior, respectively; they then rendezvous for reassembly into complete packets to be sent out. To validate its effectiveness, we evaluated$\mathrm{P}^{4}$QRS using an analytical model and implementation on state-of-the-art hardware programmable switches. Our evaluation shows that$\mathrm{P}^{4}$QRS operates stably and intrinsically boosts complex in-switch computations.

Quantum networks offer the capability of transferring quantum information among remote nodes leveraging the phenomenon of quantum entanglement. A key challenge is entanglement routing, which routes quantum entanglement efficiently in a quantum network to satisfy specific objectives. We focus on an interesting hypothesis that arises from the probabilistic nature of quantum entanglement: There is a tradeoff between accommodating a higher number of quantum entanglements (performance) and serving a broader range of node pairs (fairness). To confirm this hypothesis, we formulate entanglement routing as a multi-objective optimization problem. Our numerical analysis reveals that the solutions of the model form a Pareto frontier, thereby validating the hypothesis. Furthermore, we compare the performance of existing algorithms against this Pareto frontier to understand how the algorithms balance performance and fairness. Our findings contribute to designing entanglement routing algorithms.

A large portion of Internet traffic passes through middleboxes that read or modify messages. However, as more traffic is protected with TLS, middleboxes are becoming unable to provide their functions. To leverage middlebox functionality while preserving communication security, secure middlebox channel protocols have been designed as extensions of TLS. A key idea is that the endpoints explicitly incorporate middleboxes into the TLS handshake and grant each middlebox either the read or the write permission for their messages. Because each middlebox has the least data access privilege, these protocols are resilient against the compromise of a single middlebox. However, the existing studies have not comprehensively analyzed the communication security under the scenarios where multiple middleboxes are compromised. In this paper, we present novel attacks that break the security of the existing protocols under such scenarios and then modify maTLS, the state-of-the-art protocol, so that all the attacks are prevented with marginal overhead.

Consumer privacy leakage from data names poses a serious threat to Content-Centric Networking (CCN) networks. Obfuscating names is a promising countermeasure, and anonymizers with deterministic encryption schemes have been proposed to provide data privacy while enabling CCN features, such as in-network caching. Existing studies assume a weak threat model in which anonymizers are honest, and their obfuscation schemes are not resilient against privacy attacks such as name guessing attacks. This paper designs a name obfuscation framework based on the realistic assumption that anonymizers are semi-honest. The framework strengthens data privacy using multiple keys and separates obfuscation for prefixes and suffixes, and is implemented on a P4 switch to provide Tbps forwarding speed.

The paper presents a Tbps-class anonymity router that supports both an anonymity protocol and IP by leveraging a programmable switch. The key design issue is to place both the compute-intensive header decryption function for anonymity protocol forwarding and the memory-intensive IP forwarding function on the processing pipes of a switch with satisfying its hardware requirements. A prototype router on a programmable switch achieves Tbps-scale forwarding.

Several platforms to efficiently retrieve content from Internet of Things (IoT) devices installed in various locations have been proposed for information-centric networking (ICN). However, location privacy is at stake in such platforms because consumers retrieve content by specifying the plaintext names of the locations of their interest (LOIs). Previous studies on IP have leveraged k-anonymity of location offered by a trusted proxy called an anonymizer to hide LOIs. Specifically, an anonymizer sends content requests to k locations in a location anonymity set, which comprises an LOI and the other dummy locations. This technique can be applied to ICN; however, two problems need to be solved: the adversary models are unrealistic and the requirements for a location anonymity set have been defined in ad-hoc manners. In this study, we assume a semi-honest anonymizer and define the requirements rigorously using the notions of entropy and t-closeness. Next, we design an architecture for location privacy protection and an algorithm for location anonymity set generation. Finally, we evaluate the overhead incurred by our architecture and the quality of generated location anonymity sets through experiments under a realistic scenario. Our results indicate that our architecture and algorithm offer strong location privacy with marginal overhead.

This paper proposes an IP forwarding information base (FIB) encoding leveraging an emerging data structure called a learned index , which uses machine learning to associate key-position pairs in a key-value store. A learned index for FIB lookups is expected to yield a more compact representation and faster lookups compared to existing FIBs based on tries or hash tables, at the cost of efficient FIB updates, which is difficult to support with a learned index. We optimize our implementation for lookup speed, exploiting that for efficient FIB lookups it is enough to approximate the key-position pairs with a piece-wise linear function, instead of having to learn the key-position pairs. The experiments using real BGP routing information snapshots suggest that the size of the proposed FIB is compact and lookup speed is sufficiently fast regardless of the length of matched prefixes.

Federated learning is a privacy-preserving learning system where participants locally update a shared model with their own training data. Despite the advantage that training data are not sent to a server, there is still a risk that a state-of-the-art model inversion attack, which may be conducted by the server, infers training data from the models updated by the participants, referred to as individual models. A solution to prevent such attacks is differential privacy, where each participant adds noise to the individual model before sending it to the server. Differential privacy, however, sacrifices the quality of the shared model in compensation for the fact that participants' training data are not leaked. This paper proposes a federated learning system that is resistant to model inversion attacks without sacrificing the quality of the shared model. The core idea is that each participant divides the individual model into model fragments, shuffles, and aggregates them to prevent adversaries from inferring training data. The other benefit of the proposed system is that the resulting shared model is identical to the shared model generated with the naive federated learning.

Named Data Networking (NDN) is one of promising next generation Internet architectures that aim to realize efficient content distribution. However, in terms of producer anonymity, NDN has a serious problem that adversaries can easily learn who publishes what content due to its feature that content is inherently tied to the producer by the content name and the signature. In this article, we first define producer anonymity rigorously in terms of content-producer unlinkability, and then design a system to achieve it. Our design is based on hidden service, which is an onion routing-based system in IP, however, we improve it to take full advantage of NDN. We demonstrate that our system provides a level of anonymity comparable to hidden service with lower overhead through analysis and experiment.

Verifying remote computing environments, such as computing nodes in fog and edge computing, has gained considerable attention. This poster extends an existing remote attestation method so that it can verify that obtained results are generated by trusted computing nodes as well as remote computing nodes are trusted.

This paper addresses edge computing for location-based service where location data is obtained by Internet of Things devices. A key motivation of the paper is to propose a location-based routing/forwarding framework where a computation request of location data is forwarded to an appropriated edge router. The word “appropriate” means that time of retrieving location data as an argument of the computation is minimized. As the result, computing time is minimized.

In network functions virtualization (NFV), network functions are operated in software as virtual network functions (VNFs) instead of dedicated hardware. The most important issues that need to be addressed in NFV are where the VNFs should be placed in the network, as well as what amount of resources should be assigned to each VNF. Evolvable VNF placement (EvoVNFP) is a meta-algorithm that we previously proposed for controlling an underlying iterative VNF placement method. EvoVNFP realizes better adaptability to regular demand changes by mimicking biological evolution under time-varying environments leading to faster generation of placements. We provide detailed evaluation studies about the mechanism of EvoVNFP and show that iterative placement methods combined with EvoVNFP can generate placements that adapt better to varying goals because of triggers. Numerical results verify that EvoVNFP is able to reduce the required number of calculation steps by up to 48%.

Conflict between the two TE (Traffic Engineering) techniques for EE (Energy Efficiency) and LB (Load Balancing) has been paid attention to. This is because the both objectives are difficult to simultaneously achieve due to that the both TE techniques control the routing matrix: power and link cost minimization. The goal of this paper is to show feasibility of achieving a fair tradeoff between these two inherently conflicting objectives by using a game theoretic approach and to develop an algorithm wherein EE and LB objectives are simultaneously achieved in a fair manner.

We are researching set partitioning 64APSK coded modulation for satellite transmission. We previously developed a constellation-design method based on channel capacity and evaluated the transmission performance under the condition that the constellation was restricted to circumferential arrangement. We confirmed that this conventional method exhibited better transmission performance than DVB-S2X. In this paper, we expanded the numbers of circle of 64APSK from four to seven. Especially, applying the number of five shows good channel capacity. We also applied the design scheme whose constellation points-assignment is not restricted to circumferential arrangement because of the free constellation points-assignment in the IQ plane. We show that the proposed 64APSK applying these design schemes achieved better transmission performance than conventional method through computer simulation under the AWGN model.

Crowdsourcing in cellular networks, wherein smartphone users upload sensing data pieces using their smartphones to a service provider, has become popular. However, a shortage of cellular uplink frequency resources prevents a service provider from collecting large data with reasonable costs. Incorporating collaborative upload, wherein representatives upload their sensing data pieces as well as those of others, is a promising solution. A key to make a business based on such crowdsourcing, which we call collaborative crowdsourcing, successful is how to motivate smartphone users to become representatives. In this paper, we propose a novel rewarding scheme for the users to advocate collaborative crowdsourcing.

On the one hand packet-level caching of Information-Centric Networking (ICN) is a key to accommodating Video on Demand (VoD) movies thanks to its fine granularity caching, but on the other hand it would cause degradation in cache hit probability because each of packets constituting a content object is dealt individually. This paper analytically reveals that caching large content objects by using packet-level caching degrades caching hit probability.

One of key technologies of 5th generation mobile networks is introducing small cells, such as femtocells and picocells, to supplement existing macrocells, and this results in high heterogeneity in mobile networks. Cell association, which selects a base station for each user to connect to, is a fundamental issue to optimize the performance and utilization of heterogeneous networks. This paper develops a heuristic cell association algorithm for heterogeneous networks, which adopts the minimum throughput among users as a criterion to determine user to cell associations. Through simulation experiments, we show that the proposed algorithm increases traffic accommodated in the network as well as it achieves high total and minimum throughput.

Recently, communication network services have become increasingly diverse and dynamic. Network Function Virtualization (NFV) is an effective technique to deal with these dynamic situations. Most related work on the VNF placement problem does not consider the dynamics of requests, but only static scenarios. The important goals of the dynamic VNF placement problem include accommodating new requests following the traffic dynamics and reducing the time to calculate solutions. To tackle this problem, we utilize the concept of Modularly Varying Goals (MVG), which is based on a genetic algorithm (GA) and generates solutions that can easily adapt to time-varying goals in short time. In this paper, we propose Evolvable VNF Placement (EvoVNFP) that applies the concept of MVG to the dynamic VNF placement problem to reduce the time to obtain solutions. Results from numerical evaluations show that our method is able to better follow the dynamics of VNF requests and also reduce time until adapting to successive objectives.

Internet of Things (IoT) devices deployed everywhere are expected as potential data sources for various location-based services. This paper designs an anonymous geographical routing/forwarding mechanism to support location-based IoT services, where users collect data pieces from IoT devices by specifying their locations rather than their names/addresses. A key idea of the routing/forwarding mechanism is enabling users to collect location-dependent data without locations of users' interest being leaked.

Named data networking (NDN) has received considerable attention recently, mainly due to its built-in caching, which is expected to enable widespread and transparent operator-controlled caching. One of the important research challenges is to reduce the amount of power consumed by NDN networks as it has been shown that NDN's name prefix matching and caching are power-hungry. As a first step to achieving power-efficient NDN networks, in this paper, we develop a power consumption model of a multicore software NDN router. By applying this model to analyze how caching reduces power, we report that caching can reduce power consumption of an NDN network if the power consumption of routers is in proportion to their load and the computation of caching is as light as that of forwarding.

Our research group has proposed a VNT control method that is adaptive to traffic changes. The method is based on a dynamical system, called attractor selection, which models behavior where living organisms adapt to unknown changes in their surrounding environments and recover their conditions. One of important things of our VNT control method is how to determine attractors, i.e., VNT candidates, because a VNT configured by our VNT method finally converges on one of the VNT candidates. However, since the number of VNT candidates is limited, it is crucial that the limited number of attractors have diversity so that various kinds of VNTs are searched by attractor selection. In this paper, we propose a method to decide the VNT candidates. Our approach prepares the VNT candidates whose bottleneck links (lightpaths) are different to each other. However, this approach has a problem that it takes a heavy computational time for large-scaled networks. We therefore propose a method that divides a network into clusters for which our algorithm can be applied. Evaluation results show that the VNT candidates prepared by our method can suppress maximum link utilization than the ones prepared in a random manner or by an existing heuristic algorithm.

Virtual machine live migration is a promising solution to provide low end-to-end delay for delay-sensitive applications hosted in data centers. This enables a cloud operator to minimize end-to-end delay by placing virtual machines to the nearest data centers from users. However, a network operator does routing with a different objective, e.g., minimize network resource usages. Since the both operators' objectives are contradictory to each other, we previously proposed to integrate live migration and routing in backbone networks to resolve the contradiction. However, the dominant factor of end-to-end delay for cloud services is a congestion delay at access networks, which was not taken into account in our previous work. In this paper, we apply the integration into wireless access networks prone to suffer from large end-to-end delay and validate its effectiveness in such networks by formulating it as a solvable mixed integer non-liner program. Our new integration model incorporates congestion delays due to wireless links and therefore enables cloud operators to maintain small end-to-end delays for cloud applications. The numerical results indicate that integration of live migration and routing is successful at providing low end-to-end delay to delay-sensitive applications by resolving the contradiction.

This paper proposes an NDN-based message delivery protocol over a cellular network in disasters. Collaborative communication among cellular devices is integrated into the protocol so that power consumed by battery-operated BSs (Base Stations) is reduced when a breakout occurs. A key idea is to reduce consumed radio resources by making cellular devices of which radio propagation quality is better forward messages of neighboring devices. The radio resource reduction contributes to reducing power consumed by a battery-operated BS.

In-network caching in information centric networking (ICN) is considered as a promising approach to reducing energy consumption of an entire network. However, it is also considered as an energy consuming technique. These contradictory claims lead to one research question: Does caching really reduce the energy consumption of the entire network? To answer the question, we formulate an ICN network as an optimization problem with a realistic energy consumption model for an ICN router. By solving the formulation assuming that ICN forwarding software currently under development is used as a forwarding engine of an ICN router, we reveal that in-network caching alone does not reduce much energy but it enhances a currently developed green networking technique even though the forwarding engine is not fully optimized.

How the mobile Internet accommodates a huge number of IoT devices is an important research challenge since their number grows to several billions. An important observation about IoT device communications is that IoT devices have different characteristics in mobility from traditional mobile devices such as cellular phones. Strict mobility management scheme and session mobility provided by handover functions are not required for the IoT device mobility management. In this paper, we focus on IoT communication features, and propose a routing-based mobility architecture for them. Our routing architecture uses the Bloom Filter as a data structure to store routing information. We clarify the effectiveness of our routing architecture in IoT environments.

Data-centric networking has recently been getting increased attention. A representative design of data-centric networking is CCN (Content-Centric Networking), which routes packets within a network based on their content identifiers. CCN is basically designed to be open because ease of data reuse is one of the greatest advantages of data-centric networking. However, being used for real-world networking, completely open data-centric networking is not sufficient. It is required to realize closed communication within a group of users. In this paper, we propose Virtual Content-Centric Networking (VCCN), which realizes closed communication within a group of users with CCN router virtualization. This paper presents four building blocks of VCCN: extension of the content identifier, CCN router virtualization, packet transport between virtualized CCN routers, and Social Network Services cooperative user/group identification. Moreover, we implemented VCCN's basic features by extending the CCNx software and performed a preliminary performance evaluation of our VCCN implementation.

Gradient-based routing, where each node calculates a metric that indicates how useful a node might be in relaying messages to a sink node and transmits messages according to the metric, is one of promising approaches for Delay Tolerant Mobile Sensor Networks. However, existing gradient-based routing methods do not consider node mobility to form their gradient and this may result in inefficient message relays and degradation in their performance. In this paper, we discuss how node mobility affects message delivery in gradient-based routing and propose a gradient-based routing method that incorporates node mobility into its gradient to reduce the effect of inefficient message relays. The key idea of our proposal is to distinguish nodes leaving from a sink node from nodes approaching to a sink node. Since those leaving nodes are less useful to relay messages to a sink node, our proposed method prevents nodes from transmitting messages to nodes leaving from a sink node. Through simulations, we show that our proposal decreases the average message delivery delay under various node mobility models. Moreover, our proposal reduces the average message delivery delay by up to 50% in the case that nodes move straightly.

Virtual machine live migration, which migrates a virtual machine between data centers, is studied as a way to improve quality of services hosted on clouds. Meanwhile, traffic engineering is performed in networks that connect geographically-dispersed data centers. These two controls are originally designed and operated individually. Though it is naturally expected that integrating virtual machine live migration and the traffic engineering could result in a good overall performance, the effectiveness of such an integrated control has not been well understood. In this paper, we therefore quantitatively investigate its effectiveness. We first formulate an integrated control and an individual control as mixed integer programming problems in which the objective function is minimization of the average link delay in the network. Through numerical examples, we show that the integrated control can reduce the average link delay by at most 24 % and it can accommodate as 1.3 times much as incoming traffic compared with the individual control.

Overlay networks achieve new functionality and enhance network performance by allowing routing to be controlled at the application layer. However, these approaches result in degradations of underlying networks due to the selfish behavior of overlay networks. In this paper, we investigate the stability of virtual network topology (VNT) control under the overlay networks that perform dynamic routing updates. We reveal that the dynamics of routing on overlay networks causes a high fluctuation in the traffic demand matrix, which leads to significant instability of VNT control. To overcome the instability induced by the overlay routing, we introduce hysteresis to the VNT control. Simulation results indicate that the hysteresis mechanism improves the network stability, but cannot always improve the network performance. We therefore extend the hysteresis mechanism and show that the proposed method improves both the network stability and the performance when the amount of traffic for overlay network is not large.