Soft Deadlines Research Articles

Integrated Quality of Service for Offline and Online Services in Edge Networks via Task Offloading and Service Caching.

Edge servers frequently manage their own offline digital twin (DT) services, in addition to caching online digital twin services. However, current research often overlooks the impact of offline caching services on memory and computation resources, which can hinder the efficiency of online service task processing on edge servers. In this study, we concentrated on service caching and task offloading within a collaborative edge computing system by emphasizing the integrated quality of service (QoS) for both online and offline edge services. We considered the resource usage of both online and offline services, along with incoming online requests. To maximize the overall QoS utility, we established an optimization objective that rewards the throughput of online services while penalizing offline services that miss their soft deadlines. We formulated this as a utility maximization problem, which was proven to be NP-hard. To tackle this complexity, we reframed the optimization problem as a Markov decision process (MDP) and introduced a joint optimization algorithm for service caching and task offloading by leveraging the deep Q-network (DQN). Comprehensive experiments revealed that our algorithm enhanced the utility by at least 14.01% compared with the baseline algorithms.

Average delay analysis of soft deadline messages scheduled in the dynamic segment of FlexRay protocol

The FlexRay communication protocol provides high bandwidth for supporting both hard deadline and soft deadline traffic in in-vehicle communication networks. In this paper, we carry out delay analysis of soft deadline traffic which is handled by the dynamic segment of FlexRay. We model the arrival of these messages as Poisson processes, and use queuing theory to evaluate the average delay that they experience. Initially, we consider three nodes competing for service, assuming that two out of three can transmit messages in any FlexRay cycle and obtain expressions for the evolution of the corresponding queues. We also determine the range of message arrival rates for which the queues are stable. These results are then extended to the general case of N queues. The analytical results are compared with those obtained by simulation for a typical system.

Setbacks, Shutdowns, and Overruns

We investigate optimal project management in a setting plagued by an indefinite number of setbacks that are discovered en route to project completion. The contractor can cover up delays in progress due to shirking either by making false claims of setbacks or by postponing the reports of real ones. The sponsor optimally induces work and honest reporting via a soft deadline and a reward for completion that specifies a bonus for early delivery. Late‐stage setbacks trigger randomization between minimally feasible project extension and (inefficient) cancellation. Because extensions may be granted repeatedly, arbitrarily large overruns in schedule and budget are possible after which the project may still be canceled.

PED: Probabilistic Energy-efficient Deadline-aware scheduler for heterogeneous SoCs

Heterogeneous systems-on-chip (SoCs) integrate diverse cores with different performance and energy tradeoffs. Scheduling applications with soft deadline constraints is highly complex in such heterogeneous platforms, and the complexity is further exacerbated by the streaming jobs generated by applications from domains such as communication and radar systems. Existing deadline-aware schedulers typically first translate the job deadlines to task-level slacks before scheduling, which is the time available for a processing element (PE) to execute a specific task. Task-level slacks are critically dependent on the task-to-PE allocation of all other tasks from the same job (intra-job) or concurrent jobs (inter-job). However, this allocation is usually unknown before the start of the scheduling process. To address the problem, we propose PED, a probabilistic energy-efficient deadline-aware scheduler for heterogeneous SoCs. PED minimizes the average tardiness of streaming jobs with the least energy consumption by accurately predicting the task-to-PE allocation using Neural Network and considering intra- and inter-job contentions when scheduling tasks. Our extensive experimental results in a domain-specific SoC (DSSoC) designed for radar and communication domains show that PED can reduce tardiness by 6.9× with comparable energy consumption; and reduce energy consumption by 14% without any loss in tardiness, when compared with state-of-the-art schedulers.

Bounded model checking for interval probabilistic timed graph transformation systems against properties of probabilistic metric temporal graph logic

Cyber-physical systems often encompass complex concurrent behavior with timing constraints and probabilistic failures on demand. The analysis whether such systems with probabilistic timed behavior adhere to a given specification is essential. The formalism of Interval Probabilistic Timed Graph Transformation Systems (IPTGTSs) is often a suitable choice to model cyber-physical systems because (a) its rule-based approach to graph transformation can capture a wide range of system's structure dynamics when the states of the system can be represented by graphs while (b) it employs interval specifications for probabilistic behavior as well as lower and upper bounds on delays of steps to support systems where precise probabilities and delays are not known or may change during the runtime of the system. Probabilistic Metric Temporal Graph Logic (PMTGL) has been introduced as a powerful specification language to express worst-case/best-case probabilistic timed requirements such as actor-based soft deadlines using (a) path properties relying on its Metric Temporal Graph Logic fragment to track individual graph elements and (b) an operator inherited from Probabilistic Timed Computation Tree Logic to express worst-case/best-case probabilistic requirements identifying worst-case/best-case resolutions of non-determinism. Bounded Model Checking (BMC) support for Probabilistic Timed Graph Transformation Systems (PTGTSs) w.r.t. properties specified using PMTGL has been already presented. However, for IPTGTSs no analysis support w.r.t. PMTGL properties has been developed for stating metric temporal properties on identified subgraphs and their structural changes over time.In this paper, we adapt the BMC approach developed for PTGTSs to the case of IPTGTSs extending modeling and analysis support to the usage of probability intervals more appropriately covering cyber-physical systems where probabilistic effects cannot be specified precisely and need to be approximated instead. In our evaluation, we apply an implementation of our BMC approach in AutoGraph to a novel running example demonstrating the effect of using probability intervals instead of precise probability values.

CPU frequency scheduling of real-time applications on embedded devices with temporal encoding-based deep reinforcement learning

Small devices are frequently used in IoT and smart-city applications to perform periodic dedicated tasks with soft deadlines. This work focuses on developing methods to derive efficient power-management methods for periodic tasks on small devices. We first study the limitations of the existing Linux built-in methods used in small devices. We illustrate three typical workload/system patterns that are challenging to manage with Linux’s built-in solutions. We develop a reinforcement-learning-based technique with temporal encoding to derive an effective DVFS governor even with the presence of the three system patterns. The derived governor uses only one performance counter, the same as the built-in Linux mechanism, and does not require an explicit task model for the workload. We implemented a prototype system on the Nvidia Jetson Nano Board and experimented with it with six applications, including two self-designed and four benchmark applications. Under different deadline constraints, our approach can quickly derive a DVFS governor that can adapt to performance requirements and outperform the built-in Linux approach in energy saving. On Mibench workloads, with performance slack ranging from 0.04 s to 0.4 s, the proposed method can save 3%–11% more energy compared to Ondemand. AudioReg and FaceReg applications tested have 5%–14% energy-saving improvement. We have open-sourced the implementation of our in-kernel quantized neural network engine. The codebase can be found at: https://github.com/coladog/tinyagent.

Dynamic Multiworkflow Offloading and Scheduling Under Soft Deadlines in the Cloud-Edge Environment

Computing offloading and scheduling are emerging, accompanied by smart city services, Internet of Things, and other rich cloud services. Cloud-assisted mobile edge computing provides malleable resources but introduces considerable overhead. Due to the geographical distributions and distances of the edge, cloud, and mobile terminal, promoting cost efficiency and reducing the makespan of applications are urgent targets. For multiple mobile applications, the soft deadline constraint for each application is common in the edge-cloud environment. When multiple users initiate application requests, scheduling on the target offloaded platform commences. Some workflows, especially newly arrived workflows, might suffer from “starving to death,” which has the risk of being missed. This article describes a dynamic, multiworkflow offloading, and scheduling, adaptive heterogeneous earliest-finish-time-based algorithm, which can lightly run on a distributed network. We explore an innovative model composed of a multiobjective makespan and cost for a soft deadline constraint optimization problem. Abundant data are adopted to test the offloading and scheduling effect on a variety of platform parameters, and comparative experiments demonstrate the validity and efficiency of the adaptive system.

Deadline-Aware Task Offloading With Partially-Observable Deep Reinforcement Learning for Multi-Access Edge Computing

Over the past years, computationally-intensive mobile applications, such as interactive games and augmented reality, have gained enormous popularity. This phenomenon has placed a serious burden on mobile devices with limited computation resources and constrained battery capacity. Multi-access Edge Computing (MEC) is proposed to solve the problem by offloading part of the computation tasks from mobile devices to edge servers. The fundamental challenge in MEC is how to effectively select a subset of computation tasks to be offloaded so that the application requirements are satisfied and the total energy consumption is minimized. The existing Deep Reinforcement Learning (DRL) based offloading schemes focus on either non-real-time tasks or real-time tasks with soft deadlines. In addition, the existing schemes do not work well when the information of the system environment is not complete. In this paper, we propose an innovative DRL-based task offloading method, PDMO, which guarantees that the deadlines of real-time tasks are met even when the system environment is only partially observable. Technically, the offloading problem is formulated as a Partially Observable Markov Decision Process (POMDP). To tackle the offloading problem, we devise a Deep Deterministic Policy Gradient (DDPG) based algorithm, POTD3. Our experimental results indicate that PDMO works well in partially observable environments. In addition, it outperforms the existing offloading schemes in terms of energy consumption, deadline miss number and completion rate of non-real-time tasks.

Scheduling for Urban Air Mobility using Safe Learning

This work considers the scheduling problem for Urban Air Mobility (UAM) vehicles travelling between origin-destination pairs with both hard and soft trip deadlines. Each route is described by a discrete probability distribution over trip completion times (or delay) and over inter-arrival times of requests (or demand) for the route along with a fixed hard or soft deadline. Soft deadlines carry a cost that is incurred when the deadline is missed. An online, safe scheduler is developed that ensures that hard deadlines are never missed, and that average cost of missing soft deadlines is minimized. The system is modelled as a Markov Decision Process (MDP) and safe model-based learning is used to find the probabilistic distributions over route delays and demand. Monte Carlo Tree Search (MCTS) Earliest Deadline First (EDF) is used to safely explore the learned models in an online fashion and develop a near-optimal non-preemptive scheduling policy. These results are compared with Value Iteration (VI) and MCTS (Random) scheduling solutions.

A multi-objective quantum-inspired genetic algorithm for workflow healthcare application scheduling with hard and soft deadline constraints in hybrid clouds

Recently, the use of quantum cloud computing for different applications has been increasing. For instance, weather forecasting, financial modeling, healthcare, and automation are geographically distributed in practice. These applications are workflows and consist of compute-intensive dependent tasks with precedence constraints. However, workflow processing on quantum-based cloud services still faces issues in the literature regarding makespan and energy consumption. This study presents the Multi-objective Quantum-inspired Genetic Algorithm (MQGA) to address the problems of workflow scheduling in the hybrid cloud, attempting to reduce makespan and energy consumption simultaneously. The proposed algorithm relies on the concept and principle of quantum mechanics, which explores the computational power of quantum computing. It adopted a qubit to represent the individual chromosome for better population diversity. It also uses a quantum rotation gate to lead the schedule to better convergence and avoids classical genetic operators. The simulation results show that the proposed algorithm can effectively reduce energy consumption by 23.36% and makespan 20% on average.

Slardar: Scheduling information incomplete inter-datacenter deadline-aware coflows with a decentralized framework

Nowadays, geographically distributed edge clusters and datacenters generate large volumes of wide-area network (WAN) traffic. Therefore, it is critical to schedule inter-datacenter flows, especially coflows that imply application-level semantics, to improve the performance of geo-distributed applications. However, coflows often have a mixture of soft and hard deadline requirements, which cannot be efficiently guaranteed by existing methods. In this paper, a decentralized deadline-ware coflow scheduling framework, called Slardar, is proposed. It schedules inter-datacenter coflows while considering both hard and soft deadline requirements. However, it is challenging to design such a framework without complete coflow information. Hence, we first model the intra-coflow bandwidth allocation problem as a mean-field game where each datacenter aims to minimize its own cost with only local coflow information. We further prove its mean-field equilibrium is also the optimal bandwidth allocation strategy and propose a deep reinforcement learning based algorithm to find an approximate optimal numerical solution. Then, we investigate the offline inter-coflow bandwidth allocation problem by modeling it as a linear programming problem, and an online greedy heuristic algorithm is proposed to find an approximate optimal solution. Finally, we compare Slardar with state-of-art methods by large-scale simulation experiments. Experimental results show that our proposed method can greatly improve the transmission revenue and increase the soft and hard deadline guarantee ratios by 7.5% and 10% at least.

Optimal Speed Profile of a DVFS Processor under Soft Deadlines

Minimizing the energy consumption of embedded systems with real-time execution constraints is becoming more and more important. More functionalities and better performance/ cost tradeoffs are expected from such systems because of the increased use of real-time applications and the fact that batteries are becoming standard power supplies. Dynamically changing the speed of the processor is a common and efficient way to reduce energy consumption and remarkable gains can be obtained when considering cacheintensive and/or CPU-bound applications as the CPU energy consumption may dominate the overall energy consumption. In fact, this is the reason why modern processors are equipped with Dynamic Voltage and Frequency Scaling (DVFS) technology [7]. In the deterministic case where job sizes and arrival times are known, a vast literature addressed the problem of designing both off-line and on-line algorithms to compute speed profiles that minimize the energy consumption subject to hard real-time constraints (deadlines) on job execution times; e.g., [5]. In a stochastic environment where only statistical information is available about job sizes and arrival times, it turns out that combining hard deadlines and energy minimization via DVFS-based techniques is much more difficult. In fact, forcing hard deadlines requires to be very conservative, i.e., to consider the worst cases. Matter of fact, existing approaches work within a finite number of jobs [6, 3].

Designing Deadlines

I study how an organization should manage a project of uncertain scope, when it is advised by a privately informed expert who prefers to prolong his employment. The optimal long-term contract combines a deadline for project completion and incentive payments which decline as the deadline approaches. When the firm can additionally learn about the project's state from output, the optimal deadline exhibits variable sensitivity to output, with a hard deadline at the outset of the project and increasingly soft deadlines as the project's performance declines. (JEL D21, D82, D86, G31, J33, M52, M54)

Workload-Aware Placement Strategies to Leverage Disaggregated Resources in the Datacenter

Disaggregation of resources is a datacenter strategy that aims to decouple the physical location of resources from the place where they are accessed, as opposed to physically attached devices connected to the Peripheral Component Interconnect Express (PCIe) bus. By attaching and detaching resources through a fast interconnection network, it is possible to increase the flexibility to manage datacenter infrastructures while keeping the performance of the pooled and disaggregated devices. This article introduces workload scheduling and placement policies for environments with disaggregated memories. These policies are driven by accurate prebuilt performance degradation models. We focus on the use of nonvolatile memory to store data and/or to provide memory extensions. Following a software-defined approach, persistent memories are combined to provide higher capacity and/or bandwidth devices, or used by multiple workloads to increase the number of running workloads. Different combinations of workloads and associated soft deadlines are used to evaluate the placement policies using a system simulator. When using the first-fit policy, results show that a disaggregated system can reduce missed deadlines up to 49% when compared to a physically attached system. When our proposed policy with workload awareness is enabled in a disaggregated system, missed deadlines can be reduced up to 100% (no deadlines missed).

Generalized Exact Scheduling: A Minimal-Variance Distributed Deadline Scheduler

In this paper, we adapt tools from optimization and control theory to characterize the optimal distributed policies in a broad range of settings without any approximation. We show that Exact Scheduling minimizes both the stationary mean and variance of the service capacity subject to strict demand and deadline requirements. For more general settings, we characterize the minimal-variance distributed policies with soft demand requirements, soft deadline requirements, or both. Moreover, we derive the Pareto-optimality condition for distributed policies that balance the variance and mean square of the service capacity. The performance of the optimal distributed policies is compared with that of the optimal centralized policy by deriving closed-form bounds. Finally, we discuss a scalable partially centralized algorithm that uses centralized information to boost performance and a method to deal with missing information on service requirements. Our finding can ultimately lead to more efficient power distribution networks and cloud computing services, which optimally match the service capacity to changing demands.

Task-RM: A Resource Manager for Energy Reduction in Task-Parallel Applications under Quality of Service Constraints

Improving energy efficiency is an important goal of computer system design. This article focuses on a general model of task-parallel applications under quality-of-service requirements on the completion time. Our technique, called Task-RM , exploits the variance in task execution-times and imbalance between tasks to allocate just enough resources in terms of voltage-frequency and core-allocation so that the application completes before the deadline. Moreover, we provide a solution that can harness additional energy savings with the availability of additional processors. We observe that, for the proposed run-time resource manager to allocate resources, it requires specification of the soft deadlines to the tasks. This is accomplished by analyzing the energy-saving scenarios offline and by providing Task-RM with the performance requirements of the tasks. The evaluation shows an energy saving of 33% compared to race-to-idle and 22% compared to dynamic slack allocation (DSA) with an overhead of less than 1%.

Adaptive offloading and scheduling algorithm for big data based mobile edge computing

Big data will cause the system for business public opinion to be overburdened, and dynamic changes in computing resources will cause tasks to be delayed. To end the situation, this study assigns non-fixed execution time to each task node based on the task soft deadline and task constraints and solves the problem of difficult task scheduling caused by task dependency constraints. Aiming at the problem of task delay caused by dynamic changes of computing resources, this paper proposes an adaptive offloading and scheduling algorithm for dependent tasks in the mobile edge computing environment. This study takes the economic efficiency analysis system as an example and uses the resource allocation management algorithm based on linked lists and edge servers to study the communication resource allocation management of the economic efficiency analysis system. In addition, this study designs experiments to perform performance analysis of the algorithm proposed by this study. The research results show that the proposed algorithm has an obvious effect.

Optimal speed profile of a DVFS processor under soft deadlines

We consider a Dynamic Voltage and Frequency Scaling (DVFS) processor executing jobs with obsolescence deadlines: A job becomes obsolete and is removed from the system if it is not completed before its deadline. The objective is to design a dynamic speed policy for the processor that minimizes its average energy consumption plus an obsolescence cost per deadline miss. Under Poisson arrivals and exponentially distributed deadlines and job sizes, we show that this problem can be modeled as a continuous time Markov decision process (MDP) with unbounded state space and unbounded rates. While this MDP admits a continuous time optimality equation for its average cost, the standard uniformization approach is not applicable. Inspired by the scaling method introduced by Blok and Spieksma, we first define a family of truncated MDPs and we then show that the optimal speed profiles are increasing in the number of jobs in the system and are uniformly bounded by a constant. Finally, we show that these properties are inherited from the original (infinite) system. The proposed upper bound on the optimal speed profile is tight and is used to develop an extremely simple policy that accurately approximates the optimal average cost in heavy traffic conditions.

Water Infrastructure in Congress

In late March, President Biden outlined his first major postpandemic priority—a massive infrastructure initiative called the American Jobs Plan. The US$2.2 trillion proposal includes everything from roads and bridges to climate resilience projects and home care, but water plays a key role. The plan provides $45 billion to replace all lead service lines in the country, $56 billion to support existing programs through grants and low-cost loans, and $10 billion to monitor and remediate per- and polyfluoroalkyl substances (PFAS) in drinking water and wastewater. Congress has begun turning the American Jobs Plan into legislative language, and each chamber is working separately on a water infrastructure component. The Senate has already passed a bipartisan bill, the Drinking Water and Wastewater Infrastructure Act of 2021 (DWWIA). DWWIA doubles funding for the Drinking Water State Revolving Fund (DWSRF) program to $2.4 billion in fiscal year (FY) 2022 and scales funding up to $3.25 billion by FY 2025. The bill also reauthorizes the Water Infrastructure Finance and Innovation Act (WIFIA) and boosts funding for small and disadvantaged communities, lead service line removal, resilience and sustainability, and research. House committees are currently considering three major pieces of legislation with significant water infrastructure components, two related to drinking water and one to wastewater. The Climate Leadership and Environmental Action for our Nation's Future Act (CLEAN Future Act) is a climate-focused bill that seeks to decarbonize entire sectors of the economy. The bill's environmental justice component includes $4.14 billion for the DWSRF in FY 2022, $5 billion over 10 years to cover capital costs associated with PFAS treatment, $45 billion over 10 years to replace lead service lines, and $500 million over 10 years to improve drinking water system resilience. The Leading Infrastructure for Tomorrow's America Act (LIFT Act) is a more targeted version of the CLEAN Future Act meant to modernize the country's infrastructure and combat climate change, and includes many of the same drinking water provisions. The primary difference as it relates to water infrastructure is that the LIFT Act authorizes programs for five years, while the CLEAN Future Act authorizes programs for 10 years. The Water Quality Protection and Job Creation Act of 2021 provides $50 billion over five years to address wastewater and water quality challenges. This includes $40 billion over five years for the Clean Water State Revolving Fund program; $2 billion to capture, treat, or reuse sewer overflows or stormwater; $1 billion to implement PFAS treatment standards; and additional funding for pollution control programs, water resource management, and climate resilience. The size of the final package will likely be determined by its route to passage. Moderate Democrats would like to see a bipartisan compromise, which may ultimately pare down the plan's price tag and scope. Senate Republicans’ first two counteroffers came in at $568 billion and $928 billion—much of which would come from repurposing COVID relief funds—and excluded many of the provisions related to climate and less traditional infrastructure. Republicans have also ruled out any tax increases or a rollback of the 2017 Tax Cuts and Jobs Act as a means to pay for the new spending. If Democrats determine that the two sides are too far apart or that further compromise would jeopardize the legislation's timeline and overall impact, they may decide to bypass the filibuster and pass the American Jobs Plan through budget reconciliation—the same budgetary maneuver used to pass the American Rescue Plan with only a simple majority. House Speaker Nancy Pelosi (D-CA) has pointed to July 4 as a soft deadline for the House to complete its work on the American Jobs Plan, and Senate Majority Leader Chuck Schumer (D-NY) has made clear that DWWIA is just the first component of the Senate's work. As is often the case, the American Jobs Plan may look quite different from President Biden's original proposal if and when it becomes law. Nate Norris is the senior legislative analyst at the AWWA Government Affairs Office in Washington, D.C.; [email protected].

Market-oriented online bi-objective service scheduling for pleasingly parallel jobs with variable resources in cloud environments

In this paper, we study the market-oriented online bi-objective service scheduling problem for pleasingly parallel jobs with variable resources in cloud environments, from the perspective of SaaS (Software-as-as-Service) providers who provide job-execution services. The main process of scheduling SaaS services in clouds is: a SaaS provider purchases cloud instances from IaaS providers to schedule end users’ jobs and charges users accordingly. This problem has several particular features, such as the job-oriented end users, the pleasingly parallel jobs with soft deadline constraints, the online settings, and the variable numbers of resources. For maximizing both the revenue and the user satisfaction rate, we design an online algorithm for SaaS providers to optimally purchase IaaS instances and schedule pleasingly parallel jobs. The proposed algorithm can achieve competitive objectives in polynomial run-time. The theoretical analysis and simulations based on real-world Google job traces as well as synthetic datasets validate the effectiveness and efficiency of our algorithm.