Earticle

Intelligent Transportation Systems (ITS) is one of the important application areas of the Internet of Things (IoT). The key issue is how to process the huge events generated by IoT system to support ITS. In this paper a proactive parallel complex event processing method is proposed for congestion control in large-scale ITS. A Bayesian model averaging method is used to obtain accurate predictions under different event context. Based on the predictive analysis, a parallel Markov decision processes model is designed to support decision making for large-scale ITS. An optimized parallel policy iteration algorithm is proposed based on state partition and policy decomposition. The experimental evaluations show that this method has good accuracy and scalability when used to process congestion control in large-scale ITS.

Events are crammed with numerous basic elements in today’s management and manufacturing system. Especially, for a large-scale system, there are thousands of independent messages (events) happening every second. How to integrate the information and how to deal with such massive events are faced by most of the system. Event monitoring and processing has been posed in manufacturing corporations to tackle this challenge. However, well-prepared methodology and processing are lack for this challenge. In this article, we propose an extensible event-driven manufacturing platform for handling those massive events. First, holistic architecture of the platform is depicted. Next, the principle of primitive and complex event is detailed. Eventually, Complex Event Processing (CEP) approach is applied to the platform.

Events are crammed with numerous basic elements in today’s management and manufacturing system. Especially, for a large-scale system, there are thousands of independent messages (events) happening every second. How to integrate the information and how to deal with such massive events are faced by most of the system. Event monitoring and processing has been posed in manufacturing corporations to tackle this challenge. However, well-prepared methodology and processing are lack for this challenge. In this article, we propose an extensible event-driven manufacturing platform for handling those massive events. First, holistic architecture of the platform is depicted. Next, the principle of primitive and complex event is detailed. Eventually, Complex Event Processing (CEP) approach is applied to the platform.

Complex Event Processing (CEP) is a promising technology that deals with event stream in a cenralized manner. But in some application scenario such as the express delivery business, business-related data is scattered in the network and must be obtained by request. For the purpose of resolving the difficulty to utilize and process such distributed infomation, the paper comprehensively utilizes various advanced technologies to design an automation Internet of Things (IoT) framework which can provide the rich-semantic complex events to the senior application. Firstly, this paper proposes the framework which can realize the automatic recognition of the parcel and positive request for the associated semantic data. Secondly, a hierarchical modularized ontology is established for the sake of sharing the background knowledge. Finally, we have implemented a prototype system with the proposed object and semantic event model and detection method. Test results from simulation data indicate that the system can operation stably and response quickly to express delivery business.

웹이 성장함에 따라 데이터처리 기술도 발전하고 있다. 차세대 웹 환경에서는 다양한 유무선 사용자, USN, RFID를 위한 고속, 대용량데이터 처리기술 또한 발전하고 있다. 본 논문에서는 CEP(Complex Event Processing) 엔진을 이용하여 대용량데이터를 처리하는 기술을 제안한다. CEP는 복잡한 이벤트를 처리하는 기술로 CEP 엔진은 다음과 같은 특정이 있다. 첫째 대용량의 이벤트(데이터)를 받는 작업, 둘째 이를 분석하는 작업, 최종적으로 새로운 액션으로 연결시키는 작업으로 나눌 수 있다. 즉 대용량데이터를 수집하고 이벤트들을 분석, 필터링한다. 또한 이벤트 엔진에 미리 등록해 놓은 이벤트와 새로운 이벤트를 패턴매칭하여 데이터를 추출한다. 추출된 결과를 다른 작업의 입력 이벤트로 사용하거나 요청된 이벤트에 대해 실시간으로 응답할 수 있고 유효한 데이터만 데이터베이스에 트리거할 수도 있다.

According to growth of web, data processing technology is developing. In the Web of next generation, high-speed or high-volume data processing technologies for various wire-wireless users, USN and RFID are developing too. In this paper, we propose a high-volume data processing technology using Complex Event Processing(CEP) engine. CEP is the technology to process complex events. CEP Engine is the following characteristics. First it collects a high-volume event(data). Secondly it analyses events. Finally it lets event connect to new actions. In other words, CEP engine collects, analyses, filters high-volume events. Also it extracts events using pattern-matching for registered events and new events. As the results extracted. We use it by an input event of other work, real-time response for demanded event and can trigger to database for only valid data.

최근 다양한 응용에서 실시간으로 발행하는 이벤트들을 신속하고 효율적으로 처리하기 위해 복합 이벤트 처리 시스템을 도입하고 있다. 기존 복합 이벤트 처리 연구는 연산자의 유사성과 중복성을 고려하지 않기 때문에 많은 연산과 많은 메모리를 소비하는 문제점이 있다. 이러한 문제점을 해결하기 위하여 본 논문에서는 유사 연산과 중복 연산을 고려한 효율적인 복합 이벤트 처리 기법을 제안한다. 제안하는 기법은 동일한 기본 이벤트들이 유사한 연산을 가지면 그 연산들을 하나의 가상 연산자로 결합한다. 중복된 연산을 가질 경우에는 우선 하나의 연산만을 처리하고 이후에 같은 연산이 나오면 먼저 처리된 연산의 결과를 이용하여 처리한다. 기존 기법과의 성능 비교를 통하여 전체 연산 처리량 측면에서 제안하는 기법의 성능이 우수함을 보인다.

Recently, a complex event processing system has been introduced to quickly and efficiently process real-time events in various applications. Since the existing complex event processing schemes do not consider the similarity and duplication of operators, they perform a lot of computations and consume memory. To solve such problems, this paper proposes an efficient complex event processing scheme considering similar operators and duplication operations. When the same primitive events have similar operations, the proposed scheme combines them into one virtual operator. For duplicated operations, the proposed scheme processes only one of them first, and then processes the others using the results of the already processed operation when the same operation is subsequently performed. It is shown through performance comparison that the proposed scheme outperforms the existing scheme in terms of the whole operation throughput.