Wildcard Fields-Based Partitioning for Fast and Scalable Packet Classification in Vehicle-to-Everything

Abstract

Vehicle-to-Everything (V2X) requires high-speed communication and high-level security. However, as the number of connected devices increases exponentially, communication networks are suffering from huge traffic and various security issues. It is well known that performance and security of network equipment significantly depends on the packet classification algorithm because it is one of the most fundamental packet processing functions. Thus, the algorithm should run fast even with the huge set of packet processing rules. Unfortunately, previous packet classification algorithms have focused on the processing speed only, failing to be scalable with the rule-set size. In this paper, we propose a new packet classification approach balancing classification speed and scalability. It can be applied to most decision tree-based packet classification algorithms such as HyperCuts and EffiCuts. It determines partitioning fields considering the rule duplication explicitly, which makes the algorithm memory-effective. In addition, the proposed approach reduces the decision tree size substantially with the minimal sacrifice of classification performance. As a result, we can attain high-speed packet classification and scalability simultaneously, which is very essential for latest services such as V2X and Internet-of-Things (IoT).

Investigating the efficiency of multithreading application programming interfaces for parallel packet classification in wireless sensor networks

“…In other words, in cases where the number of available components for parallel implementation is low, the relative increase in the complexity of the timing of the threads in this library in comparison to the complexity of execution would reduce its time efficiency. This can be seen in graph b in all Figures (4)(5)(6)(7)(8)(9)(10)(11) when the number of input packets in the parallel version of the algorithms on both processors is less than or equal to 4096. In graph b in Figures 9 and 11 which address the implementation of GOT algorithm on the second processor, for example, when the number of packets is 1k and 4k, the throughput of thread is less than the serial version but this has not happened in OpenMP and TBB and, even with a small number of packets, these libraries have led to a higher throughput compared to the serial version.…”

“…The continually growing number of sensor nodes in WSN has increased the transmitted traffic and the variety of monitored parameters. This extensible complexity in the information of the WSN should be handled at the base stations [7,[10][11][12][13].…”

“…To accelerate the complex functions in analyzing high-dimensional and self-correlated data over WSN, packet classification, a primary process inherited form software-defined networking (SDN), is inevitable [7,10,11,[14][15][16][17]. This process accelerates the overall process of base stations by provisioning fast flow-based network functions instead of slow packet-based ones [18,19].…”

“…Packet classification is nothing but discriminating packets according to a set of predefined rules [20,21]. Accelerating this fundamental process directly affects the overall performance of the WSN systems so that the packet loss, delay, and buffer requirement are reduced [4,11,14,18,22,23].…”

Ingredients to enhance the performance of two-stage TCAM-based packet classifiers in internet of things: greedy layering, bit auctioning and range encoding

“…A wide range of packet processing devices in IoT including routers [1], anomaly detection systems [2], and monitoring systems [3], treat analysis systems [4], characterizing traffics in smart cities [5], and quality of service provisioning in software-defined networking [5,6] are considerably accelerated by packet classification paradigm.…”