AEDSMS: Automotive Embedded Data Stream Management System

Yamaguchi, Akihiro; Nakamoto, Yukikazu; Sato, Kenya; Ishikawa, Yoshiharu; Watanabe, Yousuke; Honda, Shinya; Takada, Hiroaki

doi:10.1109/icde.2015.7113377

Cited by 7 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Operators used for automotive DSMSs, such as Map, Filter, and Join, are based on Borealis, which is a general-purpose DSMS [8]. The operator functionalities and other details are described in [6,26].…”

Section: Operator Stream Queuementioning

confidence: 99%

“…Furthermore, when system properties (e.g., sensor type) must be changed, large parts of the application programs must be modified. To tackle these issues, automotive DSMSs have been developed based on the data integrated architecture [6,26] shown in Figure 1. Applications can be separated from sensor devices because data processing for multiple sensors is defined in the DSMS rather than in the sensors.…”

Section: Dsms-based Data Integrated Architecturementioning

confidence: 99%

“…Input: Application (SPG), the number of processors, and network topology Output: Assignment result for the SPG, i.e., start times and finish times are determined for all tasks and messages 1 Calculate rank, hrank, LDET CC, and HPRV CC for each task; 2 Calculate depth for each task; // if HVLB CC (B) is used 3 Enqueue tasks into a priority queue according to a nonincreasing order of HPRV CC; 4 α = 0; 5 for cycle ← 1 to k do 6 while not all tasks in the priority queue are scheduled do 7 Dequeue the task n i has the maximum HPRV CC; 8 Compute BP using Eq. 17 in all processors; 9 Compute the HVLB CC using Eq.…”

Section: Algorithm 1: Hvlb CC Algorithmmentioning

confidence: 99%

See 2 more Smart Citations

Scheduling parallel and distributed processing for automotive data stream management system

Rho

Azumi

Nakagawa

et al. 2017

Journal of Parallel and Distributed Computing

Self Cite

View full text Add to dashboard Cite

In this paper, to analyze end-to-end timing behavior in heterogeneous processor and network environments accurately, we adopt and modify a heterogeneous selection value on communication contention (HSV CC) algorithm, which can synchronize tasks and messages simultaneously, for stream processing distribution. In order to adapt the concepts of a static algorithm like HSV CC to automotive data stream management system (DSMSs), one must first address three issues: (i) previous task and message schedules might lead to less efficient resource usages in this scenario; (ii) the conventional method to determine the task scheduling order may not be best suited to deal with stream processing graphs, and; (iii) there is a need to be able to schedule tasks with time-varying computational requirements efficiently. To address (i), we propose the heterogeneous value with load balancing and communication contention (HVLB CC) (A) algorithm, which considers load balancing in addition to the parameters considered by the HSV CC algorithm. We propose HVLB CC (B) to address issue (ii). HVLB CC (B) can deal with stream processing task graphs and more various directed acyclic graphs to prevent assigning a higher priority to successor tasks. In addition, to address issue (iii), we propose HVLB CC IC. To schedule tasks more efficiently with various computation times, HVLB CC IC utilizes schedule holes left in processors. These idle time slots can be used for the execution of an optional part to generate more precise data results by applying imprecise computation models. Experimental results demonstrate that the proposed algorithms improve minimum schedule length, accuracy, and load balancing significantly compared to the HSV CC algorithm. In addition, the proposed HVLB CC (B) algorithm can schedule more varied task graphs without reducing performance, and, using imprecise computation models, HVLB CC IC yields higher precision data than HVLB CC without imprecise computation models.

show abstract

Section: Operator Stream Queuementioning

confidence: 99%

Section: Dsms-based Data Integrated Architecturementioning

confidence: 99%

Section: Algorithm 1: Hvlb CC Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Scheduling parallel and distributed processing for automotive data stream management system

Rho

Azumi

Nakagawa

et al. 2017

Journal of Parallel and Distributed Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…The evaluation results of both a database management system (DBMS) and a data stream management system (DSMS) showed advantage of the latter system because the DSMS can already efficiently handle continuous incoming data such as vehicle sensor data [12]. The above observation becomes a basis for developing a data-stream management system for an automotive embedded system (eDSMS) [13], [14]. In addition, a data-stream-based local dynamic map (LDM) was previously proposed [15].…”

Section: Autosarmentioning

confidence: 99%

Vehicle Embedded Data Stream Processing Platform for Android Devices

Akiyama¹,

Nakamoto²,

Yamaguchi³

et al. 2015

ijacsa

Self Cite

View full text Add to dashboard Cite

Abstract-Automotive information services utilizing vehicle data are rapidly expanding. However, there is currently no data centric software architecture that takes into account the scale and complexity of data involving numerous sensors. To address this issue, the authors have developed an in-vehicle datastream management system for automotive embedded systems (eDSMS) as data centric software architecture. Providing the data stream functionalities to drivers and passengers are highly beneficial. This paper describes a vehicle embedded data stream processing platform for Android devices. The platform enables flexible query processing with a dataflow query language and extensible operator functions in the query language on the platform. The platform employs architecture independent of data stream schema in in-vehicle eDSMS to facilitate smoother Android application program development. This paper presents specifications and design of the query language and APIs of the platform, evaluate it, and discuss the results.

show abstract

“…This paper is the extended version of Ref. [7] and includes additional evaluations and explanations. In particular, regarding contribution (B.c), this paper extends [8], which proposes a method of stream processing on a single node into distributed stream processing.…”

Section: Contributions and Roadmapmentioning

confidence: 99%

In-vehicle Distributed Time-critical Data Stream Management System for Advanced Driver Assistance

Yamaguchi

Watanabe

Sato

et al. 2017

Journal of Information Processing

Self Cite

View full text Add to dashboard Cite

Data stream management systems (DSMSs) are suitable for managing and processing continuous data at high input rates with low latency. For advanced driver assistance including autonomous driving, embedded systems use a variety of onboard sensor data with communications from outside the vehicle. Thus, the software developed for such systems must be able to handle large volumes of data and complex processing. We develop a platform that integrates and manages data in an automotive embedded system using a DSMS. However, because automotive data processing, which is distributed in in-vehicle networks of the embedded system, is time-critical and must be reliable to reduce sensor noise, it is difficult to identify conventional DSMSs that meet these requirements. To address these new challenges, we develop an automotive embedded DSMS (AEDSMS). This AEDSMS precompiles high-level queries into executable query plans when designing automotive systems that demand time-criticality. Data stream processing is distributed in in-vehicle networks appropriately, where real-time scheduling and senor data fusion are also applied to meet deadlines and enhance the reliability of sensor data. The main contributions of this paper are as follows: (1) we establish a clear understanding of the challenges faced when introducing DSMSs into the automotive field; (2) we propose an AEDSMS to tackle these challenges; and (3) we evaluate the AEDSMS during run-time for advanced driver assistance.

show abstract

AEDSMS: Automotive Embedded Data Stream Management System

Cited by 7 publications

References 25 publications

Scheduling parallel and distributed processing for automotive data stream management system

Scheduling parallel and distributed processing for automotive data stream management system

Vehicle Embedded Data Stream Processing Platform for Android Devices

In-vehicle Distributed Time-critical Data Stream Management System for Advanced Driver Assistance

Contact Info

Product

Resources

About