Traffic prediction based on machine learning for elastic optical networks
Introduction
Over the last decade, optical networks have gone through a rapid evolution, starting with 16 wavelengths of 2.5 Gb/s in the late 1990s to 80 wavelengths of 100 Gb/s in 2012 [1,2]. Today, the term optical networks denote high-capacity telecommunications networks based on optical technologies and components that can provide capacity, provisioning, routing, grooming, and/or restoration at the wavelength level. With estimated exponential traffic growth, future networks have to boost their capacity. The channel capacity will need to be increased beyond 100 Gb/s per channel or higher, with an increase of spectral efficiency.
The backbone transport technique in nowadays optical networks is Wavelength Division Multiplexing (WDM). The main idea underlying the concept of WDM networks is to communicate end-users in the optical layer through all-optical WDM channels, which are named as lightpaths [3]. A connection in a wavelength-routed WDM network is supported by a lightpath which may span multiple fiber links. Also, when there are no wavelength converters, a lightpath must occupy the same wavelength on all the fiber links through which it traverses due to the wavelength-continuity constraint. Despite all benefits of conventional WDM networks, their biggest problem is a low bandwidth efficiency due to a fixed granularity [4].
Aiming to break the fixed-grid spectrum allocation limit of conventional WDM networks, a novel spectrum efficient and scalable optical transport network architecture, called Elastic Optical Networks (EONs) is introduced. The idea underlying the concept of Elastic Optical Networks is to allocate appropriate-sized, optical bandwidth to an end-to-end optical path. It is different than in fixed-sized optical bandwidth allocation in WDM. Unlike the rigid bandwidth in WDM, an optical path in EONs expands according to the traffic volume [[5], [6], [7]].
Moreover, the growing popularity of cloud and content-oriented service has led to the increased demand for the data transfers. It is inevitable that current solutions will need to be upgraded or changed shortly. Currently, the cloud data centers (DCs) are no longer a new thing - they become to be a standard resource, used by many companies. Everything is measured by the use of virtual resources and payable per hours of using it [8].
One of the key challenges in increasing the efficiency of cloud computing is to predict the bandwidth requirement in the next control time interval based on the online measurement of traffic characteristics. By using the machine learning methods, the goal is to forecast future traffic rate variations as precisely as possible, based on the measured history. In this paper, we propose a Monte Carlo Tree Search (MCTS) algorithm [9] as a mechanism for traffic prediction in cloud data center networks. Monte Carlo Tree Search is used to identify the best combination of cloud data centers and candidate path pairs for provisioning services related to specific requests. It builds a sparse search tree and selects actions using Monte Carlo sampling. These actions are used to deepen the tree in the most promising direction [10]. We then compare our results with the results achieved by the Artificial Neural Network, trained on the dataset with modeled data belonging to the last weeks.
The main contribution is the evaluation of benefits of the traffic prediction mechanisms using a specific provider-centric use case. To efficiently test the traffic prediction mechanisms, we use various dynamic routing algorithms in Wide Area Networks. The algorithms proposed in this paper do not depend on a particular implementation and, therefore, apply to other frameworks. Moreover, experiments demonstrate that the proposed methods for traffic prediction have superior performance when applied to standard heuristic algorithms used in Elastic Optical Networks and can potentially become a new direction for optimization of optical networks performance.
To the best of our knowledge, this is the first paper that introduces Monte Carlo Tree Search as a method of traffic prediction for Elastic Optical Networks. In the related works, the machine learning techniques for optimization of communication networks are mostly used for classification of IP traffic [[11], [12], [13]] or network intrusion/anomaly detection [[14], [15], [16], [17], [18], [19], [20], [21], [22]]. In this paper, the Monte Carlo Tree Search algorithm [9] is adapted to the DC resource allocation problem. The first tutorial on using the game theory in communication networks was presented in Ref. [23]. Furthermore, the [24,25] focuses on the implementation of Monte Carlo Tree Search algorithm for deflection routing in complex networks. However, the topic of a probabilistic routing/prediction in optical networks is still not widely discussed in the literature, and there is a need for further study of this topic. For details and possible further research directions, we refer to [26].
The remainder of the paper is divided as follows. In Section 2 we introduce the optimization problem and describe the network model. Section 3 contains the information about the traffic prediction mechanisms used in the paper. In Section 4 we present simulation setup and results, and finally, Section 5 concludes the work.
Section snippets
Network model
We use similar notations as in Ref. [27]. The optical network is modeled as graph G(V, E, B, L), where V denotes a set of vertices (nodes), E is a set of directed edges (fiber links), each fiber link can accommodate |B| frequency slices at most, and L = [l(1), l(2), …, l(|E|)] represents link lengths for each e ∈ E. There are |R| cloud data centers allocated at nodes of the network. The location of them is provided by Amazon Web Services. DC are characterized by five main parameters: the number
Monte Carlo Tree Search
The Monte Carlo Tree Search (MCTS) algorithm is implemented to enable traffic prediction in the network. In this approach, the DC requests are processed in batches. If the decision-making agent has access to a generative model of the system that is capable of generating samples of successor states ζ′ and rewards ι given a state ζ and an action a, it may be used to perform a sampling-based look-ahead search for rewarding actions [33].
The nodes and edges of the search tree correspond to states
Simulation scenario
We consider the Euro28 network (28 nodes, 82 unidirectional links, and 7 DCs) and the US26 network (26 nodes, 84 unidirectional links, and 10 DCs), shown in Fig. 1. The location of DCs, interconnection points, and submarine cable landing stations are obtained from the Data Center Map website [40]. In each DC location, ten m3.2 × large AWS EC2 instances are available. The pricing model for DC resources shown in Table 1 is based on the AWS.
The EON technology is used for the optical layer. In
Conclusion
In this paper, we focused on applying the machine learning techniques for traffic prediction in EONs. We showed the benefits of using them with dynamic routing algorithms, developed for cloud data center traffic. The main conclusion is that the Monte Carlo sampling adapts better and in a shorter time to all traffic changes than the Artificial Neural Network.
Acknowledgements
M. Aibin is supported by the Polish National Science Centre under grant 2016/21/N/ST7/02147.
References (40)
- et al.
Intrusion detection by machine learning: a review
Expert Syst. Appl.
(2009) - et al.
Single-player monte-carlo tree search for SameGame
Knowl. Base Syst.
(2012) - et al.
The evolution of optical networking
Proc. IEEE
(2012) Optical network design and planning
- et al.
Lightpath communications: an approach to high bandwidth optical WAN's
IEEE Trans. Commun.
(1992) On the future of wavelength routing networks
IEEE Netw.
(1996)- et al.
Concept and enabling technologies of spectrum-sliced elastic optical path network (slice)
- et al.
Dynamic optical mesh networks: drivers, challenges and solutions for the future
- et al.
A tutorial on the flexible optical networking paradigm: state of the art, trends, and research challenges
Dynamic Routing Algorithms for Cloud-ready Elastic Optical Networks
(2017)