A Mathematical Approach to Load Balancing in Multi ECU Configuration

Electronic Control Units (ECUs) are nowadays employed in automotives for discharging various functionalities within the vehicle. It has become the fundamental building block of any automotive subsystem and is interfaced with electro mechanical counterparts. To meet the system wide requirements, these ECUs are interconnected using the communication infrastructure. Although the communication infrastructure in terms of, predominantly, the CAN based vehicle network took its birth to enable ECUs to work in a coordinated manner, this infrastructure was also viewed as a potential means to incorporate extensibility in terms of addition of newer ECUs which are built for implementing additional requirements. With this paradigm, the number of ECUs started growing in a steep manner, uncontrolled. Today, high segment automotives have ECUs as large as 75-80, connected by multiple communication buses and running millions of lines of software. In order to distribute load equally among these enormous number of ECUs, load balancing mechanisms are needed. It also enables efficient utilization of CPU power in these ECUs. In this paper, a mathematical approach has been developed for achieving load balance across ECUs on the basis of CPU utilization. In the proposed method, five ECUs have been considered for demonstration purpose and it can be extended to N number of ECUs. The simulation was done using MATLAB and result obtained showed the balanced load across each ECU after three iterations. Index Terms—AUTOSAR, ECU, Load balancing, OEM.

[1]  Cheng-Zhong Xu,et al.  Iterative Dynamic Load Balancing in Multicomputers , 1994 .

[2]  Creating Test Patterns for Model-based Development of Automotive Software , 2006 .

[3]  H Fennel,et al.  Achievements and exploitation of the AUTOSAR development partnership , 2006 .

[4]  Wolf G. H. Günther,et al.  The Impact of Automotive Standardization to Liability Risks Arising from Defective Software, Especially under European Law , 2008 .

[5]  J. D. Teresco,et al.  New challanges in dynamic load balancing , 2005 .

[6]  Rajeshwari Hegde,et al.  Model Based Approach for the Integration of ECUs , 2008 .

[7]  Luciano Lavagno,et al.  Automotive virtual integration platforms: why's, what's, and how's , 2002, Proceedings. IEEE International Conference on Computer Design: VLSI in Computers and Processors.

[8]  D. R. Emerson,et al.  An optimal migration algorithm for dynamic load balancing , 1998, Concurr. Pract. Exp..

[9]  Karen D. Devinea,et al.  New Challenges in Dynamic Load Balancing , 2004 .

[10]  R. K. McConnell,et al.  Load Balancing , 2021, Encyclopedia of Algorithms.

[11]  Wooyoung Jung,et al.  AUTOSAR migration from existing automotive software , 2008, 2008 International Conference on Control, Automation and Systems.

[12]  R. Diekman,et al.  Load balancing strategies for distributed memory machines , 2000 .

[13]  Ajay Kumar,et al.  Computer-aided Architecture Design & Optimized Implementation of Distributed Automotive EE Systems , 2007, 2007 44th ACM/IEEE Design Automation Conference.

[14]  Arndt Bode Load balancing in distributed memory multiprocessors , 1991, [1991] Proceedings, Advanced Computer Technology, Reliable Systems and Applications.