Wyniki wyszukiwania - BazTech

1

The IoT gateway with active queue management

Domański Adam, Domańska Joanna, Czachórski Tadeusz, Klamka Jerzy, Szyguła Jakub, Marek Dariusz

International Journal of Applied Mathematics and Computer Science

|

2021

|

Vol. 31, no. 1

165--178

EN

As the traffic volume from various Internet of things (IoT) networks increases significantly, the need for adapting the quality of service (QoS) mechanisms to the new Internet conditions becomes essential. We propose a QoS mechanism for the IoT gateway based on packet classification and active queue management (AQM). End devices label packets with a special packet field (type of service (ToS) for IPv4 or traffic class (TC) for IPv6) and thus classify them as priority for real-time IoT traffic and non-priority for standard IP traffic. Our AQM mechanism drops only non-priority packets and thus ensures that real-time traffic packets for critical IoT systems are not removed if the priority traffic does not exceed the maximum queue capacity. This AQM mechanism is based on the PIα controller with non-integer integration order. We use fluid flow approximation and discrete event simulation to determine the influence of the AQM policy on the packet loss probability, queue length and its variability. The impact of the long-range dependent (LRD) traffic is also considered. The obtained results show the properties of the proposed mechanism and the merits of the PIα controller.

2

Algorytmy kolejkowania : algorytm RED (Random Early Detection)

Iljaszewicz Paweł

Biuletyn Naukowy Wrocławskiej Wyższej Szkoły Informatyki Stosowanej. Informatyka

|

2018

|

vol. 8, nr 1

4--8

PL

Artykuł omawia algorytm Losowego Wczesnego Wykrywania RED (ang. Random Early Detection) pozwalający bramce unikania przeciążeń w sieciach z komutacją pakietów. Brama wykrywa początkowe przeciążenie, obliczając średni rozmiar kolejki. Brama może powiadamiać o przeciążonych połączeniach lub o upuszczeniu pakietów przybywających do bramy, ustawiając bit w nagłówkach pakietów. Kiedy rozmiar średniej kolejki przekracza ustawiony próg, brama opada lub zaznacza każdy przybywający pakiet z pewnym prawdopodobieństwem, gdzie dokładny rozkład prawdopodobieństwa jest funkcją średniego rozmiaru kolejki. Bramki RED utrzymują średnią wielkość kolejki na niskim poziomie, jednocześnie zezwalając na sporadyczne impulsy pakietów w kolejce. Podczas przeciążenia prawdopodobieństwo, że brama powiadamia o konkretnym połączeniu, by zmniejszyć jego okno, jest mniej więcej proporcjonalne do udziału tego w przepustowości przez bramę. Bramki RED są zaprojektowane tak, aby dostarczyć protokół taki jak TCP, przeciążając warstwę transportową. Symulacje sieci TCP / IP są używane do zilustrowania wydajności bramki.

EN

The subject of the study is to present the Random Early Detection (RED) algorithm that allows the gateway to avoid overloading in packet switched networks. The gateway detects the initial overload by calculating the average size of the queue. The gateway can notify about overload connections or by dropping packets arriving at the gate by setting a bit in the packet headers. When the size of the average queue exceeds the set threshold, the gate descends or marks each arriving packet with a certain probability, where the exact probability distribution is a function of the average queue size. RED gates maintain the average queue size at a low level, while allowing occasional packet bursts in the queue. During overload, probability that the gateway informs about a specific connection to reduce its window is more or less proportional to this connection involved in bandwidth through the gate. The RED gateways are designed to provide a protocol such as TCP to overload the transport layer. TCP / IP network simulations are used to illustrate the performance of the gateway.

3

The use of a non-integer order PI controller with an active queue management mechanism

Domański A., Domańska J., Czachórski T., Klamka J.

International Journal of Applied Mathematics and Computer Science

|

2016

|

Vol. 26, no. 4

777--789

EN

In this paper the performance of a fractional order PI controller is compared with that of RED, a well-known active queue management (AQM) mechanism. The article uses fluid flow approximation and discrete-event simulation to investigate the influence of the AQM policy on the packet loss probability, the queue length and its variability. The impact of self-similar traffic is also considered.

4

A RED modified weighted moving average for soft real-time application

Domańska J., Domański A., Augustyn D. R., Klamka J.

International Journal of Applied Mathematics and Computer Science

|

2014

|

Vol. 24, no. 3

697--707

EN

The popularity of TCP/IP has resulted in an increase in usage of best-effort networks for real-time communication. Much effort has been spent to ensure quality of service for soft real-time traffic over IP networks. The Internet Engineering Task Force has proposed some architecture components, such as Active Queue Management (AQM). The paper investigates the influence of the weighted moving average on packet waiting time reduction for an AQM mechanism: the RED algorithm. The proposed method for computing the average queue length is based on a difference equation (a recursive equation). Depending on a particular optimality criterion, proper parameters of the modified weighted moving average function can be chosen. This change will allow reducing the number of violations of timing constraints and better use of this mechanism for soft real-time transmissions. The optimization problem is solved through simulations performed in OMNeT++ and later verified experimentally on a Linux implementation.

5

Wykorzystanie logiki rozmytej w algorytmach AQM

Płachecki K.

Pomiary Automatyka Kontrola

|

2009

|

R. 55, nr 2

98-100

PL

W obecnych czasach wymagania stawiane sieciom TCP/IP zostały znacznie zróżnicowane poprzez aplikacje wymagające odmiennych poziomów usług sieciowych QoS (ang. Quality of Service). Dodatkowo, wzrastający udział transmisji czasu rzeczywistego RTP wymusza poszukiwanie nowych metod aktywnego zarządzania obsługą pakietów w węzłach sieci. Autor wskazuje możliwość wykorzystania logiki rozmytej w mechanizmach adaptacyjnych AQM (ang. Active Queueing Management), w celu poprawy wydajności układów zarządzania przepływem pakietów.

EN

Active Queue Management (AQM) is the name given to router mechanisms used in congestion control. AQM mechanisms manage queue lengths by dropping (or marking) packets during building up congestion, that is, before the queue is full. End-systems can then react to such losses by reducing their packet rate, hence avoiding severe congestion. AQM mechanisms are also relevant in the context of DiffServ. The DiffServ architecture has been defined to provide IP networks with scalable quality of service (QoS) processing of traffic aggregates, based on a special field in the IP header. This paper presents new active queue management mechanisms to provide congestion control in TCP/IP best-effort networks. The author propose how to use fuzzy logic to better solve the drop tail problem in the basic AQM mechanism (REM) with one buffer and a server. The objective of the fuzzy controller is to determine the optimal admission policies so as to maximise the average profit (reward minus cost). The proposed fuzzy logic approach for congestion control allows using linguistic knowledge to capture the dynamics of nonlinear probability marking functions. In the introduction the author defines a structure of Supervisory Expert Control System [10, 12, 14] and the project aims illustrated in Figs. 2 and 3 [15]. In Section 3 the author presents implementation of a new algorithm FREM that uses a Fuzzy Logic Controller. The model of FREM algorithm [8] is shown in Fig. 5. In Section 5 the author shows the plan on future works: a project of the FLC controller and verification of the FREM algorithm performance. The paper presents the FREM algorithm with nonlinear probability marking functions. There is shown a conception of applying Supervisory Expert Control System to congestion control in TCP/IP networks. The author proposes how to ensure the adaptation ability of the REM algorithm. The presented solution requires an additional FLC supervisory module. The objective of fuzzy controller is to determine the optimal admission policies so as to maximise the average profit (reward minus cost). The proposed fuzzy logic approach to congestion control allows using linguistic knowledge to capture the dynamics of nonlinear probability marking functions.