• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.8
• /
• pp.2783-2804
• /
• 2021

In the network function virtualization environment, dynamic changes in network traffic will lead to the dynamic changes of service function chain resource demand, which entails timely dynamic adjustment of service function chain resource configuration. At present, most researches solve this problem through virtual network function migration and link rerouting, and there exist some problems such as long service interruption time, excessive network operation cost and high penalty. This paper proposes a dynamic adjustment method of service function chain resource configuration for the dynamic changes of network traffic. First, a dynamic adjustment request of service function chain is generated according to the prediction of network traffic. Second, a dynamic adjustment strategy of service function chain resource configuration is determined according to substrate network resources. Finally, the resource configuration of a service function chain is pre-adjusted according to the dynamic adjustment strategy. Virtual network functions combination and virtual machine reusing are fully considered in this process. The experimental results show that this method can reduce the influence of service function chain resource configuration dynamic adjustment on quality of service, reduce network operation cost and improve the revenue of service providers.

• KNOM Review
• /
• v.21 no.2
• /
• pp.35-45
• /
• 2018

As Network Slicing functionality gets applied to mobile networking, a mechanism that enables the selection of network slices becomes indispensable. Following the 3GPP Technical Specification for the 5G Architecture, the inclusion of the Network Slice Selection Function (NSSF) in order to leverage the process of slice selection is apparent. However, actual implementation of this network function needs to deal with the dynamic changes of network instances, due to this, a platform that supports the orchestration of Virtual Network Functions (VNF) is required. Our proposed solution include the use of the Central Office Rearchitected as a Data Center (CORD) platform, with the specified profile for mobile networks (M-CORD) that integrates a service orchestrator (XOS) alongside solutions oriented to Software Defined Networking (SDN), Network Function Virtualization (VNF) and virtual machine management through OpenStack, in order to provide the right ecosystem where our implementation of NSSF can obtain slice information dynamically by relying on synchronization between back-end services and network function instances.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.05a
• /
• pp.65-68
• /
• 2001

RBFN has some problem that because the basis function isnt orthogonal to each others the number of used basis function goes to big. In this reason, the Wavelet Neural Network which uses the orthogonal basis function in the hidden node appears. In this paper, we propose the composition method of the actual function in hidden layer with the scaling function which can represent the region by which the several wavelet can be represented. In this method, we can decrease the size of the network with the pure several wavelet function. In addition to, when we determine the parameters of the scaling function we can process rough approximation and then the network becomes more stable. The other wavelets can be determined by the global solutions which is suitable for the suggested problem using the genetic algorithm and also, we use the back-propagation algorithm in the learning of the weights. In this step, we approximate the target function with fine tuning level. The complex neural network suggested in this paper is a new structure and important simultaneously in the point of handling the determination problem in the wavelet initialization.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.16-16
• /
• 2000

This paper describes a new structure re create a pseudo Gaussian function network (PGFN). The activation function of hidden layer does not necessarily have to be symmetric with respect to center. To give the flexibility of the network, the deviation of pseudo Gaussian function is changed according to a direction of given input. This property helps that given function can be described effectively with a minimum number of center by PGFN, The distribution of deviation is represented by level set method and also the loaming of deviation is adjusted based on it. To demonstrate the performance of the proposed network, general problem of function estimation is treated here. The representation problem of continuous functions defined over two-dimensional input space is solved.

• Journal of the Korean Data and Information Science Society
• /
• v.16 no.4
• /
• pp.815-821
• /
• 2005

Among the various artificial neural networks the backpropagation network (BPN) has become a standard one. One of the components in a neural network is an activating function or a transfer function of which a representative function is a sigmoid. We have discovered that by updating the slope parameter of a sigmoid function simultaneous with the weights could improve performance of a BPN.

• Journal of Families and Better Life
• /
• v.20 no.4
• /
• pp.149-164
• /
• 2002

The purpose of this study was to identify the types of social networks of urban housewives according to different network composition patterns and to analyze the structural and functional characteristics of identified types. The data used in this study were collected from 589 full-time housewives residing in Taejeon city. The major findings are as follows: 1) The social networks of housewives in urban nuclear families were classified into eight types: the kin network, the non-kin network, the kin-centered network, the friend-centered network, the neighbor-centered network, the associate-centered network, the parallel network, and the decentralized network. 2) The structual characteristics (size, density, homogeneity, duration, proximity, frequency, closeness, direction) varied according to the type. The kin network type and the non-kin network type showed extreme degrees in network characteristics. The parallel network type and the decentralized network type showed an average level of network characteristics. The kin-, friend-, neighbor-, and the associate-centered types showed network characteristics of an intermediate level between the single-category types and the decentralized type. 3) The average levels of function of social network types were different in only two(service support, interference) of the six function areas(emotional support, service support, material support, information support, social companionship support, interference). The average level of service support by the non-kin network type was higher than other types. The average level of interference by the kin-centered network type was higher than other types, and that of the neighbor-centered network type was lower than other types. On the other hand, the total amount of function performance of social network types was different in all function areas. The total amount of social support given by the decentralized network type was greater than the other types. The total amount of interference given by the non-kin network type was smaller than the other types.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.300-302
• /
• 2006

Middleware offers function that user application program can transmit data independently of network device. Connection management about network connection of module is important for normal service of module base personal robot. Unpredictable network disconnection is influenced to whole robot performance in module base personal robot. For this, Middleware must be offer two important function. The first is function of error detection and reporting about abnormal network disconnection. Therefore, middleware need method for network error detection and module management to consider special quality that each network device has. The second is the function recovering that makes the regular service possible. When the module closed from connection reconnects, as this service reports connection state of the corresponding module, the personal robot resumes the existing service. In this paper proposed method of network connection management for to support fault tolerant about network error of network module based personal robot.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.12
• /
• pp.1914-1924
• /
• 2016

In this paper, considering virtualized Evolved Packet Core(vEPC) network for 5G mobile network, we propose architecture for supporting Service Function Chaining(SFC) in 5G mobile network. Using SFC in 5G network, dynamic path configuration and providing network services based on subscriber and traffic information. SFC technology provides logical ordered set of network functions and delivers packet through providing logical path over the physical network. Based on the perspective of 5G core network in distributed manner, we design hierarchical SFC architecture to manage SFC for global path including vEPC and SGi-LAN network, and internal path between virtualized network functions in each cloud. In this paper, we define architecture and call flow for establishing data path using SFC. Finally, we design testbed architecture for real implementation based on open source software.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.45 no.4
• /
• pp.602-611
• /
• 1996

In this paper, radial basis function networks with two hidden layers, which employ the K-means clustering method and the hierarchical training, are proposed for improving the short-term predictability of chaotic time series. Furthermore the recursive training method of radial basis function network using the recursive modified Gram-Schmidt algorithm is proposed for the purpose. In addition, the radial basis function networks trained by the proposed training methods are compared with the X.D. He A Lapedes's model and the radial basis function network by nonrecursive training method. Through this comparison, an improved radial basis function network for predicting chaotic time series is presented. (author). 17 refs., 8 figs., 3 tabs.

• Journal of Korean Society on Water Environment
• /
• v.27 no.5
• /
• pp.661-669
• /
• 2011

The purpose of this study is quantitative analysis of the effects of the interactions between stream network and hillslope to hydrologic response functions. To this end general formulation of hydrologic response function is performed based on width function and grid framework. Target basins are Ipyeong and Tanbu basins. From the results of width function estimation even similar sized and closely located basins could have very different hydrologic response function. It is found out that the interactions between stream network and hillslope are essential factors of rainfall-runoff processes because their difference can make the hydrologic response function with positive skewness. The change of velocities of stream network and hillslope might influence the magnitude of peak but time to peak tends to more sensitively respond to velocities of stream network. Lag time of basin would be the result of complex interaction between drainage structures and dynamic properties of river basin.