Non-preemptive Scheduling of Real-time Tasks Under Precedence and Resource Constraints

Background: Real Time Wireless Sensor Networks (RT-WSN) have hard real time packet delivery requirements. Due to resource constraints of sensors, these networks need to trade-off energy and latency. Objective: In this paper, a routing protocol for RT-WSN named “SPREAD” has been proposed. The underlying idea is to reserve laxity by assuming tighter packet deadline than actual. This reserved laxity is used when no deadline-meeting next hop is available. Objective: As a result, if due to repeated transmissions, energy of nodes on shortest path is drained out, then time is still left to route the packet dynamically through other path without missing the deadline. Results: Congestion scenarios have been addressed by dynamically assessing 1-hop delays and avoiding traffic on congested paths. Conclusion: Through extensive simulations in Network Simulator NS2, it has been observed that SPREAD algorithm not only significantly reduces miss ratio as compared to other similar protocols but also keeps energy consumption under control. It also shows more resilience towards high data rate and tight deadlines than existing popular protocols.

Download Full-text

Power-Based Non-Intrusive Condition Monitoring for Terminal Device in Smart Grid

Sensors ◽

10.3390/s20133635 ◽

2020 ◽

Vol 20 (13) ◽

pp. 3635 ◽

Cited By ~ 1

Author(s):

Guoming Zhang ◽

Xiaoyu Ji ◽

Yanjie Li ◽

Wenyuan Xu

Keyword(s):

Smart Grid ◽

Power Consumption ◽

Real Time ◽

Condition Monitoring ◽

Resource Constraints ◽

Detection System ◽

Stable Operation ◽

Detection Accuracy ◽

Monitoring Method ◽

Dsp Processors

As a critical component in the smart grid, the Distribution Terminal Unit (DTU) dynamically adjusts the running status of the entire smart grid based on the collected electrical parameters to ensure the safe and stable operation of the smart grid. However, as a real-time embedded device, DTU has not only resource constraints but also specific requirements on real-time performance, thus, the traditional anomaly detection method cannot be deployed. To detect the tamper of the program running on DTU, we proposed a power-based non-intrusive condition monitoring method that collects and analyzes the power consumption of DTU using power sensors and machine learning (ML) techniques, the feasibility of this approach is that the power consumption is closely related to the executing code in CPUs, that is when the execution code is tampered with, the power consumption changes accordingly. To validate this idea, we set up a testbed based on DTU and simulated four types of imperceptible attacks that change the code running in ARM and DSP processors, respectively. We generate representative features and select lightweight ML algorithms to detect these attacks. We finally implemented the detection system on the windows and ubuntu platform and validated its effectiveness. The results show that the detection accuracy is up to 99.98% in a non-intrusive and lightweight way.

Download Full-text

Context-aware Adaptive Surgery

Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies ◽

10.1145/3478073 ◽

2021 ◽

Vol 5 (3) ◽

pp. 1-22

Author(s):

Hongli Wang ◽

Bin Guo ◽

Jiaqi Liu ◽

Sicong Liu ◽

Yungang Wu ◽

...

Keyword(s):

Real Time ◽

Large Scale ◽

Resource Constraints ◽

Search Algorithm ◽

Search Time ◽

State Graph ◽

Context Aware ◽

Optimal Partition ◽

Research Attention ◽

Neighbor Effect

Deep Neural Networks (DNNs) have made massive progress in many fields and deploying DNNs on end devices has become an emerging trend to make intelligence closer to users. However, it is challenging to deploy large-scale and computation-intensive DNNs on resource-constrained end devices due to their small size and lightweight. To this end, model partition, which aims to partition DNNs into multiple parts to realize the collaborative computing of multiple devices, has received extensive research attention. To find the optimal partition, most existing approaches need to run from scratch under given resource constraints. However, they ignore that resources of devices (e.g., storage, battery power), and performance requirements (e.g., inference latency), are often continuously changing, making the optimal partition solution change constantly during processing. Therefore, it is very important to reduce the tuning latency of model partition to realize the real-time adaption under the changing processing context. To address these problems, we propose the Context-aware Adaptive Surgery (CAS) framework to actively perceive the changing processing context, and adaptively find the appropriate partition solution in real-time. Specifically, we construct the partition state graph to comprehensively model different partition solutions of DNNs by import context resources. Then "the neighbor effect" is proposed, which provides the heuristic rule for the search process. When the processing context changes, CAS adopts the runtime search algorithm, Graph-based Adaptive DNN Surgery (GADS), to quickly find the appropriate partition that satisfies resource constraints under the guidance of the neighbor effect. The experimental results show that CAS realizes adaptively rapid tuning of the model partition solutions in 10ms scale even for large DNNs (2.25x to 221.7x search time improvement than the state-of-the-art researches), and the total inference latency still keeps the same level with baselines.

Download Full-text

Model-Driven Configuration of Distributed Real-time and Embedded Systems

Model-Driven Domain Analysis and Software Development ◽

10.4018/978-1-61692-874-2.ch006 ◽

2011 ◽

pp. 115-135 ◽

Cited By ~ 1

Author(s):

Brian Dougherty ◽

Jules White ◽

Douglas C. Schmidt

Keyword(s):

Real Time ◽

Resource Constraints ◽

System Configuration ◽

Modeling Tools ◽

Model Driven ◽

Design Paradigm ◽

Reduce Development Time ◽

Commercial Off The Shelf ◽

System Configurations

Distributed real-time and embedded (DRE) systems are increasingly being constructed with commercial-off-the-shelf (COTS) components to reduce development time and effort. The configuration of these components must ensure that real-time quality-of-service (QoS) and resource constraints are satisfied. Due to the numerous QoS constraints that must be met, manual system configuration is hard. Model-Driven Architecture (MDA) is a design paradigm that incorporates models to provide visual representations of design entities. MDAs show promise for addressing many of these challenges by allowing the definition and automated enforcement of design constraints. This chapter presents MDA techniques and tools that simplify and automate the configuration of COTS components for DRE systems. First, the challenges that make manual DRE system configuration infeasible are presented. Second, the authors provide an incremental methodology for constructing modeling tools to alleviate these difficulties. Finally, the authors provide a case study describing the construction of the Ascent Modeling Platform (AMP), which is a modeling tool capable of producing near-optimal DRE system configurations.

Download Full-text

Efficient Semantic Segmentation Using Multi-Path Decoder

Applied Sciences ◽

10.3390/app10186386 ◽

2020 ◽

Vol 10 (18) ◽

pp. 6386

Author(s):

Xing Bai ◽

Jun Zhou

Keyword(s):

Neural Network ◽

Real Time ◽

Network Architecture ◽

Resource Constraints ◽

Cost Effective ◽

Semantic Segmentation ◽

Classification Model ◽

Neural Network Architecture ◽

Great Progress ◽

Different Types

Benefiting from the booming of deep learning, the state-of-the-art models achieved great progress. But they are huge in terms of parameters and floating point operations, which makes it hard to apply them to real-time applications. In this paper, we propose a novel deep neural network architecture, named MPDNet, for fast and efficient semantic segmentation under resource constraints. First, we use a light-weight classification model pretrained on ImageNet as the encoder. Second, we use a cost-effective upsampling datapath to restore prediction resolution and convert features for classification into features for segmentation. Finally, we propose to use a multi-path decoder to extract different types of features, which are not ideal to process inside only one convolutional neural network. The experimental results of our model outperform other models aiming at real-time semantic segmentation on Cityscapes. Based on our proposed MPDNet, we achieve 76.7% mean IoU on Cityscapes test set with only 118.84GFLOPs and achieves 37.6 Hz on 768 × 1536 images on a standard GPU.

Download Full-text

Modeling Fixed Priority Non-Preemptive Scheduling with Real-Time Calculus

2008 14th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications ◽

10.1109/rtcsa.2008.28 ◽

2008 ◽

Cited By ~ 5

Author(s):

Devesh B. Chokshi ◽

Purandar Bhaduri

Keyword(s):

Real Time ◽

Preemptive Scheduling ◽

Fixed Priority

Download Full-text

ENPP: Extended Non-preemptive PP-aware Scheduling for Real-time Cloud Services

International Journal of Electrical and Computer Engineering (IJECE) ◽

10.11591/ijece.v6i5.10640 ◽

2016 ◽

Vol 6 (5) ◽

pp. 2291

Author(s):

Fereshteh Hoseini ◽

Mostafa Ghobaei Arani ◽

Alireza Taghizadeh

Keyword(s):

Resource Allocation ◽

Real Time ◽

Processing Time ◽

Resource Constraints ◽

Cloud Services ◽

Scheduling Problems ◽

Hard Problems ◽

Real Time Applications ◽

Simulation Results ◽

Np Hard Problems

<p class="Abstract">By increasing the use of cloud services and the number of requests to processing tasks with minimum time and costs, the resource allocation and scheduling, especially in real-time applications become more challenging. The problem of resource scheduling, is one of the most important scheduling problems in the area of NP-hard problems. In this paper, we propose an efficient algorithm is proposed to schedule real-time cloud services by considering the resource constraints. The simulation results show that the proposed algorithm shorten the processing time of tasks and decrease the number of canceled tasks.</p>

Download Full-text

Towards Fully Jitterless Applications: Periodic Scheduling in Multiprocessor MCSs Using a Table-Driven Approach

Applied Sciences ◽

10.3390/app10196702 ◽

2020 ◽

Vol 10 (19) ◽

pp. 6702

Author(s):

Eugenia Ana Capota ◽

Cristina Sorina Stangaciu ◽

Mihai Victor Micea ◽

Daniel-Ioan Curiac

Keyword(s):

Real Time ◽

Multiprocessor Systems ◽

Preemptive Scheduling ◽

Algorithm Performance ◽

Safety Critical ◽

Time Table ◽

Scheduling Method ◽

Embedded Applications ◽

Special Case ◽

Mixed Criticality

In mixed criticality systems (MCSs), the time-triggered scheduling approach focuses on a special case of safety-critical embedded applications which run in a time-triggered environment. Sometimes, for these types of MCSs, perfectly periodical (i.e., jitterless) scheduling for certain critical tasks is needed. In this paper, we propose FENP_MC (Fixed Execution Non-Preemptive Mixed Criticality), a real-time, table-driven, non-preemptive scheduling method specifically adapted to mixed criticality systems which guarantees jitterless execution in a mixed criticality time-triggered environment. We also provide a multiprocessor version, namely, P_FENP_MC (Partitioned Fixed Execution Non-Preemptive Mixed Criticality), using a partitioning heuristic. Feasibility tests are proposed for both uniprocessor and homogenous multiprocessor systems. An analysis of the algorithm performance is presented in terms of success ratio and scheduling jitter by comparing it against a time-triggered and an event-driven method in a non-preemptive context.

Download Full-text