This page has only limited features, please log in for full access.
Due to power and space considerations, the link capacity in many Internet of Things (IoT) networks is low; however, many IoT sensors, such as high-resolution video cameras, generate huge amounts of data, which can cause congestion unless traffic engineering is applied. However, the majority of the existing network traffic engineering methods require traffic matrix information, which can be difficult to estimate in IoT networks. Instead of attempting to estimate the traffic matrix, we identify the traffic pattern using machine learning based on the Bayesian attractor model (BAM) for supervision and automation of traffic engineering in IoT networks that exhibit a limited number of traffic patterns. We propose running two BAMs in parallel: a fast-pathway BAM for fast but low-certainty identification, and a slow-pathway BAM for slow but high-certainty identification. We demonstrate that our framework enables fast and reliable identification of traffic patterns. After identifying a traffic pattern, a network configuration that is optimized for the identified pattern by traffic engineering is applied to minimize the maximum link utilization. In traffic engineering, we apply virtual network slicing, which creates an independent end-to-end logical network for each IoT sensor type on a shared physical infrastructure. We demonstrate that virtual network slicing allows for fine-grained traffic engineering in IoT networks.
Onur Alparslan; Shin’Ichi Arakawa. Fast/Slow-Pathway Bayesian Attractor Model for IoT Networks Based on Software-Defined Networking with Virtual Network Slicing. Fluctuation-Induced Network Control and Learning 2020, 135 -154.
AMA StyleOnur Alparslan, Shin’Ichi Arakawa. Fast/Slow-Pathway Bayesian Attractor Model for IoT Networks Based on Software-Defined Networking with Virtual Network Slicing. Fluctuation-Induced Network Control and Learning. 2020; ():135-154.
Chicago/Turabian StyleOnur Alparslan; Shin’Ichi Arakawa. 2020. "Fast/Slow-Pathway Bayesian Attractor Model for IoT Networks Based on Software-Defined Networking with Virtual Network Slicing." Fluctuation-Induced Network Control and Learning , no. : 135-154.
One of the models in the literature for modeling the behavior of the brain is the Bayesian attractor model, which is a kind of machine-learning algorithm. According to this model, the brain assigns stochastic variables to possible decisions (attractors) and chooses one of them when enough evidence is collected from sensory systems to achieve a confidence level high enough to make a decision. In this paper, we introduce a software defined networking (SDN) application based on a brain-inspired Bayesian attractor model for identification of the current traffic pattern for the supervision and automation of Internet of things (IoT) networks that exhibit a limited number of traffic patterns. In a real SDN testbed, we demonstrate that our SDN application can identify the traffic patterns using a limited set of fluctuating network statistics of edge link utilization. Moreover, we show that our application can improve core link utilization and the power efficiency of IoT networks by immediately applying a pre-calculated network configuration optimized by traffic engineering with network slicing for the identified pattern.
Onur Alparslan; Shin’Ichi Arakawa; Masayuki Murata. SDN-Based Control of IoT Network by Brain-Inspired Bayesian Attractor Model and Network Slicing. Applied Sciences 2020, 10, 5773 .
AMA StyleOnur Alparslan, Shin’Ichi Arakawa, Masayuki Murata. SDN-Based Control of IoT Network by Brain-Inspired Bayesian Attractor Model and Network Slicing. Applied Sciences. 2020; 10 (17):5773.
Chicago/Turabian StyleOnur Alparslan; Shin’Ichi Arakawa; Masayuki Murata. 2020. "SDN-Based Control of IoT Network by Brain-Inspired Bayesian Attractor Model and Network Slicing." Applied Sciences 10, no. 17: 5773.
According to a historical rule of thumb, which is widely used in routers, the buffer size of each output link of a router should be set to the product of the bandwidth and the average round-trip time. However, it is very difficult to satisfy this buffer requirement for ultra-high-speed dense wavelength division multiplexing (DWDM) networks with the current technology. Recently, many researchers have challenged the rule of thumb and have proposed various buffer sizing strategies requiring less buffer. Most of them were proposed for electronic routers with input and output buffering. However, shared buffering is a strong candidate for future DWDM optical packet switching (OPS) networks because of its high efficiency. As all links use the same buffer space, the wavelength count and nodal degree have a big impact on the size requirements of shared buffering. In this paper, we present a new buffer scaling rule showing the relationship between the number of wavelengths, nodal degree, and the required shared buffer size. By an extensive simulation study, we show that the buffer requirement increases with O(N0.85W0.85) for both standard TCP and paced TCP, while XCP-paced TCP’s buffer requirement increases with O(N1W0.85) for a wide range of N and W, where N is the nodal degree and W is the number of wavelengths.
Onur Alparslan; Shin’Ichi Arakawa; Masayuki Murata. Buffer scaling for optical packet switching networks with shared RAM. Optical Switching and Networking 2011, 8, 12 -22.
AMA StyleOnur Alparslan, Shin’Ichi Arakawa, Masayuki Murata. Buffer scaling for optical packet switching networks with shared RAM. Optical Switching and Networking. 2011; 8 (1):12-22.
Chicago/Turabian StyleOnur Alparslan; Shin’Ichi Arakawa; Masayuki Murata. 2011. "Buffer scaling for optical packet switching networks with shared RAM." Optical Switching and Networking 8, no. 1: 12-22.