Rearrangeable Nonblocking Conditions for Four Elastic Optical Data Center Networks

Four variants of elastic optical data center network (DCN) architectures based on optical circuit switching were proposed in an earlier study. The necessary and sufficient values of frequency slot units (FSUs) per fiber required for these four DCNs in the sense of there being strictly nonblocking (SNB) were derived, but no results in the sense of being rearrangeable nonblocking (RNB) were presented. In reality, only limited bandwidths are available, and reducing the value of FSUs per fiber has become a critical task to realize nonblocking optical DCN architectures in practice. In this paper, we derive the sufficient value of FSUs per fiber required for the four DCNs to be RNB by two multigraph approaches. Our results show that the proposed RNB conditions in terms of FSUs per fiber for a certain two of the four DCNs reduce their SNB results down to at least half for most cases, and even down to one-third.

The Construction of High-Performance Optoelectronic Interconnection Network and the Realization of Cloud Computing for Traffic Data Recognition

Due to the problems of congestion, insufficient scalability, and high cost in the network core layer link, the network interconnection architecture needs to be optimized. The photoelectric interconnection technology has attracted the attention of many researchers with its high bandwidth, low latency, and low power consumption. In this study, after fully considering the requirements of optoelectronic switching on network node degree and processing delay and corresponding to different transmission characteristics of circuit switching and optical circuit switching, an optoelectronic interconnection architecture supporting heterogeneous network topology, namely THtop, is proposed. According to the optical circuit switching/circuit switching characteristics of the Internet, the corresponding topology structure is designed respectively in this architecture to enhance the system integration and reduce the cost. At the same time, in order to meet the requirements of wavelength and number of hops of optical circuit switching, distributed control is designed in THtop, and the design method of heterogeneous optical switching unit is introduced in the switching equipment, so that the optical switching node can further reduce the cost while playing its role. The use of high-speed optoelectronic networks will cause a large amount of traffic on the channel. In this study, the traffic identification is analyzed on the proposed THtop architecture. The Map Reduce framework in cloud computing is used as the identification model, and the K-means algorithm is taken as the identification algorithm. According to its characteristics, the W_K-means algorithm is proposed for the type identification of traffic. The results show that under the OpenNet Internet simulation environment, when the traffic is set to a certain level, more than 90% of the non-blocking network switching can be realized under the THtop architecture, and the completion time of the mouse flow and elephant flow can be significantly improved. Therefore, under the Map Reduce model, the proposed W_K -means algorithm can quickly identify different traffic types.

Data Processing Platform of Cloud Computing and Its Performance Analysis Based on Photoelectric Hybrid Interconnection Architecture

Data processing platform is the core support platform of cloud computing. The use of electric interconnection architecture will increase the complexity of network topology, while optical interconnection architecture is ideal, so cloud computing platform based on optical interconnection has become a research hotspot. The distributed optical interconnection architecture of cloud computing data processing platform is focused on. Combining the hybrid mechanism of optical circuit switching and electric packet switching, it can meet a variety of traffic requirements. Meanwhile, it improves the switching mechanism, communication strategy, and router structure. Moreover, considering that the hybrid optoelectronic interconnection architecture can improve the network delay and throughput, but there is still a problem of network consumption. Combined with the network characteristics of the data processing platform (wireless mesh structure) of cloud computing, the network topology algorithm is studied, and the relationship between the topology and the maximum number of allocable channels is analyzed. Furthermore, the equation of topological reliability calculation is defined, and the optimization model of topological design is proposed, according to which the data processing platform of cloud computing is further optimized under the photoelectric hybrid interconnection architecture. During the experiment, before topology optimization, by changing the message length, it is found that adding optical circuit switching can help achieving large capacity and new type of transmission, and can effectively reduce the time delay. After topology optimization structure is adopted, the photoelectric hybrid-data processing platform of cloud computing without topology optimization is compared. It is found that under different reliability constraints, the throughput and end-to-end delay of the network are significantly improved, which proves that the data processing platform of cloud computing based on the photoelectric hybrid interconnection architecture is a feasible cloud computing platform.

A Brief Review on the Methods that Improve Optical Burst Switching Network Performance

In this tutorial, we give an introduction to optical burst switching (OBS) networks and compare different methods that have been given to improve performance of these networks. OBS is an alternative to optical circuit switching and optical packet switching by separating data from control packets and sending them in a different wavelength. OBS networks suffer from an issue based on their bufferless nature, burst contentions. In these networks, when two data bursts are competing on the same wavelength, one of them is dropped and it leads to a significant reduction on the performance of the network. A lot of researches have been done to solve this problem. Some of them are addressed in this paper.