Date: Tuesday 10 March 2015
Time: 11:30 - 13:00
Location / Room: Chartreuse
Chair:
Bart Vermeulen, NXP Semiconductors, NL
Co-Chair:
Geoff Merrett, University of Southampton, GB
This session covers energy optimisation for embedded systems and emerging automotive systems and networks, including Ethernet and IP. To create effective Ethernet-enabled automotive networks, topics including service discovery, bridging and traffic shaping are addressed.
| Time | Label | Presentation Title Authors |
|---|---|---|
| 11:30 | 2.4.1 | (Best Paper Award Candidate) WORKLOAD UNCERTAINTY CHARACTERIZATION AND ADAPTIVE FREQUENCY SCALING FOR ENERGY MINIMIZATION OF EMBEDDED SYSTEMS Speakers: Anup Das1, Akash Kumar2, Bharadwaj Veeravalli2, Rishad Shafik1, Geoff Merrett1 and Bashir Al-Hashimi3 1University of Southampton, GB; 2National University of Singapore, SG; 3University of Southampton, Abstract A primary design optimization objective for multicore embedded systems is to minimize the energy consumption of applications while satisfying their performance requirement. A system-level approach to this problem is to scale the frequency of the processing cores based on the readings obtained from the hardware performance monitors. However, performance monitor readings contain uncertainty, which becomes prominent when applications are executed in a multicore environment. This uncertainty can be attributed to factors such as cache contention and DRAM access time, that are very difficult to predict dynamically. We demonstrate that such uncertainty can be controlled to make better decision on the processor frequency in order to minimize energy consumption. To achieve this, we propose a multinomial logistic regression model, which combines probabilistic interpretation with maximum likelihood (ML) estimation to classify an incoming workload, at run-time, into a finite set of classes. Every workload class corresponds to a frequency pre-determined using an appropriate training set and results in minimum energy consumption. The classifier incorporates (1) uncertainty with arbitrary probability distribution to estimate the actual frame workload; and (2) the frequency switching overhead, neither of which are considered in any of the existing approaches. The classified frequency is applied on the processing cores to execute the workload. The proposed approach is engineered into an embedded multicore system and is validated with a set of standard multimedia applications. Results demonstrate that the proposed approach minimizes energy consumption by an average 20% as compared to the existing techniques. Download Paper (PDF; Only available from the DATE venue WiFi) |
| 12:00 | 2.4.2 | FORMAL ANALYSIS OF THE STARTUP DELAY OF SOME/IP SERVICE DISCOVERY Speakers: Jan Reinke Seyler1, Thilo Streichert1, Michael Glaß2, Nicolas Navet3 and Jürgen Teich2 1Daimler AG, DE; 2Friedrich-Alexander-Universität Erlangen-Nürnberg, DE; 3Université du Luxembourg, LU Abstract An automotive network needs to start up within the millisecond range. This includes the physical startup, the software boot time, and the configuration of the network. The introduction of Ethernet into the automotive industry expanded the design space drastically and is increasing the complexity of configuring every element in the network. To add more flexibility to automotive Ethernet networks, the concept of Service Discovery was migrated from consumer electronics to AUTOSAR within the SOME/IP middleware. A network is not fully functional until every client found its service. Consequently, this time interval adds to the startup time of a network. This work presents a formal analysis model to calculate the waiting time of every client to receive the first offer from its service. The model is able to determine the worst case of a given parameter set. Based on this, a method for calculating the total startup time of a system is derived. The model is implemented in a free-to-use octave program and validated by comparing the analytical results to a timing-accurate simulation and an experimental setup. In any case, the worst-case assumption holds true and the gap between the maximum of the simulation and the presented method is less than 1.3%. Download Paper (PDF; Only available from the DATE venue WiFi) |
| 12:30 | 2.4.3 | ANALYSIS OF ETHERNET-SWITCH TRAFFIC SHAPERS FOR IN-VEHICLE NETWORKING APPLICATIONS Speakers: Sivakumar Thangamuthu1, Nicola Concer2, Pieter Cuijpers3 and Johan Lukkien3 1NXP Semiconductors, IN; 2NXP Semiconductors, NL; 3Technische Universiteit Eindhoven, NL Abstract Switched Ethernet has been proposed as network technology for automotive and industrial applications. IEEE AVB is a collection of standards that specifies (among other elements) a set of network traffic shaping mechanisms (i.e., rules to regulate the traffic flow) to have guaranteed Quality of Service for Audio/Video traffic. However, in-vehicle control applications like advanced driver-assistance systems require much lower latencies than provided by this standard. Within the context of IEEE TSN (Time Sensitive Networking), three new traffic shaping mechanisms are considered, named Burst Limiting, Time Aware and Peristaltic shaper respectively. In this paper we explain and compare these shapers, we examine their worst case end-to-end latencies analytically and we investigate their behavior through a simulation of a particular setup. We show that the shapers hardly satisfy the requirements for 100Mbps Ethernet, but can come close under further restrictions. We also show the impact the shapers have on AVB traffic. Download Paper (PDF; Only available from the DATE venue WiFi) |
| 12:45 | 2.4.4 | REAL-TIME CAPABLE CAN TO AVB ETHERNET GATEWAY USING FRAME AGGREGATION AND SCHEDULING Speakers: Christian Herber, Andre Richter, Thomas Wild and Andreas Herkersdorf, Technische Universität München, DE Abstract Ethernet is a key technology to satisfy the communication requirements of future automotive embedded systems. Audio/Video Bridging (AVB) Ethernet is a set of IEEE standards that allows synchronous and time-sensitive communication. It is the favored candidate for backbone and camera applications, but is not expected to replace Controller Area Network (CAN). Instead, both have to coexist in future architectures. No research has been conducted regarding CAN to AVB gateways, and approaches for similar protocols are either not fit or inefficient. In this paper, we present a CAN to AVB Ethernet gateway that allows efficient, real-time capable forwarding. We aggregate and schedule multiple CAN frames into a single AVB Ethernet frame to minimize bandwidth requirements. We evaluate static and dynamic scheduling approaches and determine optimal gateway configurations, showing that the necessary bandwidth reservation is reduced by 72% compared to similar approaches. Download Paper (PDF; Only available from the DATE venue WiFi) |
| 13:00 | IP1-5, 51 | INDUCTOR OPTIMIZATION FOR ACTIVE CELL BALANCING USING GEOMETRIC PROGRAMMING Speakers: Matthias Kauer1, Swaminathan Narayanaswamy1, Martin Lukasiewycz1, Sebastian Steinhorst1 and Samarjit Chakraborty2 1TUM CREATE, SG; 2TU Munich, DE Abstract This paper proposes an optimization methodology for inductor components in active cell balancing architectures of electric vehicle battery packs. For this purpose, we introduce a new mathematical model to quantitatively describe the charge transfer of a family of inductor-based circuits. Utilizing worst case assumptions, this model yields a nonlinear program for designing the inductor and selecting the transfer current. In the next step, we transform this problem into a geometric program that can be efficiently solved. The optimized inductor reduces energy dissipation by at least 20% in various scenarios compared to a previous approach which selected an optimal off-the-shelf inductor. Download Paper (PDF; Only available from the DATE venue WiFi) |
| 13:01 | IP1-6, 174 | LIGHTWEIGHT AUTHENTICATION FOR SECURE AUTOMOTIVE NETWORKS Speakers: Philipp Mundhenk1, Sebastian Steinhorst1, Martin Lukasiewycz1, Suhaib A. Fahmy2 and Samarjit Chakraborty3 1TUM CREATE, SG; 2School of Computer Engineering, Nanyang Technological University, SG; 3TU Munich, DE Abstract We propose a framework to bridge the gap between secure authentication in automotive networks and on the internet. Our proposed framework allows runtime key exchanges with minimal overhead for resource-constrained in-vehicle networks. It combines symmetric and asymmetric cryptography to establish secure communication and enable secure updates of keys and software throughout the lifetime of the vehicle. For this purpose, we tailor authentication protocols for devices and authorization protocols for streams to the automotive domain. As a result, our framework natively supports multicast and broadcast communication. We show that our lightweight framework is able to initiate secure message streams over 15 times faster than conventional frameworks, for the first time meeting the real-time requirements of automotive networks. Download Paper (PDF; Only available from the DATE venue WiFi) |
| 13:00 | End of session Lunch Break, Keynote session from 1320 - 1420 (Room Oisans) sponsored by Mentor Graphics in front of the session room Salle Oisans and in the Exhibition area Coffee Break in Exhibition AreaOn all conference days (Tuesday to Thursday), coffee and tea will be served during the coffee breaks at the below-mentioned times in the exhibition area. Lunch BreakOn Tuesday and Wednesday, lunch boxes will be served in front of the session room Salle Oisans and in the exhibition area for fully registered delegates (a voucher will be given upon registration on-site). On Thursday, lunch will be served in Room Les Ecrins (for fully registered conference delegates only). Tuesday, March 10, 2015Coffee Break 10:30 - 11:30 Lunch Break 13:00 - 14:30; Keynote session from 13:20 - 14:20 (Room Oisans) sponsored by Mentor Graphics Coffee Break 16:00 - 17:00 Wednesday, March 11, 2015Coffee Break 10:00 - 11:00 Lunch Break 12:30 - 14:30, Keynote lectures from 12:50 - 14:20 (Room Oisans) Coffee Break 16:00 - 17:00 Thursday, March 12, 2015Coffee Break 10:00 - 11:00 Lunch Break 12:30 - 14:00, Keynote lecture from 13:20 - 13:50 Coffee Break 15:30 - 16:00 |