The Clos network has been studied for decades as a class of nonblocking switching networks. However, the structure is based on assumptions made at the time of its design, and the assumptions may not remain entirely valid. For instance, an optimal Clos network usually consists of non-square switches (numbers of input and output ports differ), though the switches available today are square ones. In addition, all paths have to be of the same length in Clos networks (presumably to simplify signal setting), but this assumption is no longer valid since signals can be dynamically established nowadays. This paper carefully identifies the implicit assumptions of the Clos network and redesigns it to increase its capacity. Although the conventional Clos network using square switches has to leave several ports unused to realize the nonblocking property, our network has almost no unused ports, which greatly increases network capacity. In addition, our network does not fix the path length and well utilizes shortcut connections if available. Comprehensive theoretical analyses show that our network has a larger capacity than the Clos network under most conditions. Numerical evaluations demonstrate that our network increases the capacity 15% on average and up to 50% at most.
There are many applications which cannot be executed by mobile devices due to their limitations in memory, processing, battery, among others. One solution to this would be offloading heavy tasks to cloud servers in the edge of the network, in a service model called Edge Cloud Computing. The main Quality of Service requirement of this model is a low Service Delay, which can be achieved by lowering Transmission Delay and Processing Delay. Works in literature focus on either one of those two types of delay. This paper, however, argues that an approach which combines transmission and processing technologies to lower Service Delay would be more efficient. This idea is defended by an analysis of the service model and existing stochastic modeling of the Edge Cloud Computing system. We conclude that a dual focus approach would be the only way of truly minimizing the Service Delay, therefore being the desired method to improve Quality of Service. We conclude by laying the foundation for a future model that follows such concept.
Building optimal virtual networks across multiple domains is an essential technology to offer flexible network services. However, existing research is founded on an unrealistic assumption; providers will share their private information including resource costs. Providers, as is well known, never actually do that to remain competitive. Technically, secure multiparty computation, which is a computational technique based on the cryptography, can be used to secure optimization, but it is too time-consuming. This paper presents a novel method to optimize virtual networks built over multiple domains, with great efficiency but without revealing any private information. Our method employs secure multi-party computation but only for masking sensitive values; it can optimize virtual networks under limited information without any time-consuming technique. It is solidly based on the theory of optimality, and is assured of finding reasonably optimal solutions. Experiments show that our method is fast and optimal in practice even concealing private information; it finds nearly optimal solutions in just a few minutes for large virtual networks with tens of nodes. This is the first work that can be implemented in practice for building optimal virtual networks across multiple domains.
Distributed large scale neural networks are widely used in complicated image recognition and natural language processing among several organizations, but it takes much maintenance cost for keeping the nodes (i.e, computation servers) performance and their network topology in a churn environment that nodes insertion/deletion occurs frequency. To reduce the cost in the environment, we proposed Distributed Skip Mesh List Architecture, which can provide high stability against node insertion/deletion and automatic node management to a distributed large scale neural network management. In the evaluation, we confirmed that it reduces the maintenance cost (e.g., transmission messages for managing nodes) with high stability.
Large-scale mobile traffic data analysis is important for efficiently planning mobile base station deployment plans and public transportation plans. However, the storage costs of preserving mobile traffic data are becoming much higher as traffic increases enormously population density of target areas. To solve this problem, schemes to generate a large amount of mobile traffic data have been proposed. In the state-of-the-art of the schemes, generative adversarial networks (GANs) are used to transform a large amount of traffic data into a coarse-grained representation and generate the original traffic data from the coarse-grained data. However, the scheme still involves a storage cost, since the coarse-grained data must be preserved in order to generate the original traffic data. In this paper, we propose a scheme to generate the mobile traffic data by using conditional-super-resolution GAN (CSR-GAN) without requiring a coarse-grained process. Through experiments using two real traffic data, we assessed the accuracy and the amount of storage data needed. The results show that the proposed scheme, CSR-GAN, can reduce the storage cost by up to 45% compared to the traditional scheme, and can generate the original mobile traffic data with 94% accuracy. We also conducted experiments by changing the architecture of CSR-GAN, and the results show an optimal relationship between the amount of traffic data and the model size.
25 February 2024 in IEEJ Transactions on Electrical and Electronic Engineering