본 논문에서는 네트워크 온 칩(NoC: network on chip) 구조에서의 내부 데이터 통신의 성능을 최적화 할 수 있는 새로운 온 칩 네트워크 인터페이스 구조를 제안하였다. 제안하는 NoC 구조는 기본적으로 하드웨어 면적을 줄이기 위하여 XY 라우팅 알고리듬을 기반으로 구현되었으며, 전달되는 패킷의 크기 또는 플릿의 개수를 최소화하기 위하여 Golomb-Rice 인코딩/디코딩 알고리듬에 기반을 둔 하드웨어 압축기/해제기를 이용하여 통신되는 데이터의 양을 크게 줄임으로써 네트워크 지연시간을 최소화 할 수 있는 새로운 구조를 제안하였다. 즉 전송될 데이터는 전송자(sender)의 네트워크 인터페이스에서 내장된 하드웨어 인코더를 통해 압축된 형태로 패킷의 개수를 최소화하여 온 칩 네트워크상의 데이터를 업로드하게 된다. 이러한 압축된 데이터가 리시버(receiver)에 도착하면, 하드웨어 디코더를 통해서 원래의 데이터로 복원된다. 사이클 수준의 시뮬레이터를 통하여 제안된 라우터 구조가 온 칩 시스템의 네트워크 지연시간을 크게 줄일 수 있음을 증명하였다.

ITS(Intelligent Transport System) as things are used for Broadcast service using TDMB/TPEG/NAVI rather than personal seamless service. It is attaching weight to Traffic information gathering, Charging, Settlement service. This research is applied to improve DCCP(Datagram Congestion Control Protocol) which has function as protecting data and preserving message boundary. The improving method is like that we solve data trust in UDP because Connection and Transmission overhead in UDP is less than in TCP. We fix the data loss which is generated from unordered delivery section of IP base wireless service by using DCCP protocol. We guarantee of connection with OBE(On-Board Equipment) and reliance about transmission of data by complement to mapping table and multi-hoping. Finally, We evaluate the performance about transmission of IP based data. We constructed a test-bed near research center for this test.

In real-time embedded systems, the responsibility is the most important thing because it is related to human life. Context switching is a part of which can slow down the responsibility. We therefore should minimize the amount of state that needs to be saved during context switching. In this paper, we introduce a new architecture (Register Farm) for context switching which can exchange two contexts in one cycle time. Although it might increase the cost of MCU design and the complexity of circuit, it cannot miss any interrupt during context switching. Consequently, Register Farm architecture can make embedded systems spread out in human life because it can increase reliability and responsibility in real time embedded systems.

The automotive industry tries to provide infotainment systems to emerging automobiles. Since the infotainment systems require various peripheral devices and network connectivity, legacy operating systems such as Linux and Windows can be much preferred due to its plentiful device drivers and multimedia applications while the operating systems following OSEK standard are used for automotive electronic control units. Thus it is highly desired that the system software supporting infotainment applications can be portable over different legacy operating systems providing unified programming interfaces. The majority of legacy operating systems support POSIX interfaces for application development. MOST is an automotive network standard for infotainment systems. Network Service defines the protocol stacks for MOST control data, which is essential to implement infotainment applications over MOST. In this paper, we suggest a POSIX-based Network Service so that we can utilize legacy device drivers and applications for automotive infotainment systems. We measure the performance of the POSIX-based Network Service and show that its overhead is not significant.

It is highly requested that the more complicated embedded software is used for high performance and multiple functions of the systems. This is inevitably increasing the errors. Therefore the embedded software testing is getting important recently. There are not general testing methods which are able to be applied for any embedded systems, but via this research, we introduce a testing method which is based on TTCN-3, a testing standard, for embedded systems. A testing environment for network-based embedded software is implemented with considering the features of TTCN-3 testing which is based on message exchange. The testing environment has two additional parts with TTCN-3 test system, the network analyzer to access the network-based systems and the communication interface which is suggested for embedded systems in previous work, and we have implemented the whole testing environment with interacting these two parts. In addition to the normal testing domain, called single node testing as a unit testing of V-model, we suggest another concept to test multiple nodes in network. It could be achieved by adding keywords such as supervisor and object which are describing the feature of TTCN-3 testing component and generating the TTCN-3 Executable code which contains new keywords. The testing has done for embedded software which is based on CAN network and the demonstration of the testing environment has been shown in this paper.

As wireless sensor network are being deployed in a wide variety of application areas, the number of sensor nodes in a sensor filed becomes larger and larger. In the past, ISP (In-System Programming) method have been generally used for code update but the large number of sensor nodes requires a new code update method called network reprogramming. There are many challenging issues for network reprogramming since it can make an impact on the network lifetime. In this paper, a new sender selection scheme for network reprogramming protocol is proposed to decrease energy consumption for code update by minimizing overlapped area between sender nodes and reducing data contention. Simulation results show that the proposed scheme can reduce the amount of message traffic and the overall data transmission time.