Edge computing enables data processing closer to the source, significantly reducing latency, an essential requirement for real-time vision-based analytics such as object detection in surveillance and smart city environments. However, these tasks place substantial demands on resource-constrained edge devices, making the joint optimization of energy consumption and detection accuracy critical. To address this challenge, we propose ECORE , a framework that integrates multiple dynamic routing strategies, including a novel estimation-based techniques and an innovative greedy selection algorithm, to direct image processing requests to the most suitable edge device–model pair. ECORE dynamically balances energy efficiency and detection performance based on object characteristics. We evaluate our framework through extensive experiments on real-world datasets, comparing against widely used baseline techniques. The evaluation leverages established object detection models (YOLO, SSD, EfficientDet) and diverse edge platforms, including Jetson Orin Nano, Raspberry Pi 4 and 5, and TPU accelerators. Results demonstrate that our proposed context-aware routing strategies can reduce energy consumption and latency by 35% and 49%, respectively, while incurring only a 2% loss in detection accuracy compared to accuracy-centric methods.

Efficient job scheduling in high-performance computing (HPC) systems necessitates the simultaneous consideration of system-centric objectives, such as maximizing resource utilization, and user-centric objectives, such as minimizing job waiting times. In practice, the relative importance of these objectives is not static, but shifts dynamically in response to fluctuations in workload characteristics and system state. However, existing scheduling frameworks — including both traditional workload managers and reinforcement learning (RL)-based methods — typically rely on fixed policies or fixed reward functions that encode a predetermined combination of objectives. As a result, they lack the flexibility to adjust their scheduling priorities as workload intensity or system conditions change. In this work, we propose MetaPilot, a deep reinforcement learning-based controller designed to enable dynamic adaptation to shifting scheduling objectives. MetaPilot functions as an adaptive decision layer, continuously monitoring real-time system state and workload characteristics in order to select the most appropriate scheduling objective prior to each scheduling event. The selected objective is subsequently optimized by established scheduling frameworks, ensuring seamless integration with existing systems. Comprehensive experiments conducted on real-world HPC workload traces from both CPU-based (Physical) and GPU-enabled (Deeplearn) clusters demonstrate that MetaPilot achieves substantial improvements in both maximum and average job waiting times, as well as in resource utilization across CPU, GPU, and memory dimensions, relative to state-of-the-art baseline schedulers. Notably, MetaPilot reduces maximum waiting time by up to 19% on the Physical partition and achieves best-in-class utilization and balanced waiting times on the Deeplearn partition, thereby demonstrating robust adaptability and effectiveness across heterogeneous HPC workloads.

The transition from monolithic architecture to microservices has enhanced flexibility in application design and its scalable execution. This approach typically uses a computing cluster managed by a container orchestration platform to deploy microservices. However, this shift introduces significant challenges, particularly in the efficient scheduling of containerized services. These challenges are compounded by unpredictable scenarios such as dynamic incoming workloads with various execution traffic and variable communication delays among cluster nodes. Existing works often overlook the real-time traffic impacts of dynamic requests on running microservices, as well as the varied communication delays across cluster nodes. Consequently, even optimally deployed microservices could suffer from significant performance degradation over time. To address these issues, we propose a network and traffic-aware adaptive scheduling framework,TraDE, which can adaptively redeploy microservice instances to maintain desired performance amid changing traffic and network conditions within the hosting cluster. We have implementedTraDEas an extension to the Kubernetes platform. Additionally, we deployed realistic microservice applications in a real compute cluster and conducted extensive experiments to assess our framework's performance in various scenarios. The results demonstrate the effectiveness ofTraDEin rescheduling running microservices to enhance end-to-end performance while maintaining a high goodput ratio. Compared with the existing method NetMARKS,TraDEoutperforms it by reducing the average response time of the application by up to 48.3%, and improving the throughput by up to 1.2-1.5× across workloads while maintaining a goodput ratio of 95.36%, and showing robust adaptive capability to meet QoS targets under sustained workloads and dynamic networking conditions.

Edge computing environments host increasingly complex microservice-based IoT applications, which are prone to performance anomalies that can propagate across dependent services. Identifying the true source of such anomalies—known as Root Cause Localization (RCL)—is essential for timely mitigation. However, existing RCL approaches are designed for cloud environments and rely on centralized analysis, which increases latency and communication overhead when applied at the edge. This paper proposes a decentralized RCL approach that executes localization directly at the edge device level using the Personalized PageRank (PPR) algorithm. The proposed method first groups microservices into communication- and colocation-aware clusters, thereby confining most anomaly propagation within cluster boundaries. Within each cluster, PPR is executed locally to identify the root cause, significantly reducing localization time. For the rare cases where anomalies propagate across clusters, we introduce an inter-cluster peer-to-peer approximation process, enabling lightweight coordination among clusters with minimal communication overhead. To enhance the accuracy of localization in heterogeneous edge environments, we also propose a novel anomaly scoring mechanism tailored to the diverse anomaly triggers that arise across microservice, device, and network layers. Evaluation results on the publicly available edge dataset, MicroCERCL, demonstrate that the proposed decentralized approach achieves comparable or higher localization accuracy than its centralized counterpart while reducing localization time by up to 34%. In addition, scalability experiments conducted on large-scale datasets generated using the iAnomaly framework show that the proposed decentralized approach consistently outperforms the centralized baseline in terms of localization efficiency under increasing system scale.

High-Performance Computing systems frequently undergo architectural changes, such as hardware upgrades or the deployment of new clusters, to meet evolving computational demands. Traditional static schedulers and machine-learning-based approaches struggle to adapt efficiently to these changes, often requiring manual adjustments or extensive retraining. In this paper, we propose a novel approach combining Separate Feature Extraction and Selective Transfer Learning to enable rapid adaptation of Reinforcement Learning-based HPC sched-ulers to new or modified cluster architectures. We evaluate our approach using three real-world HPC clusters, including both CPU and GPU architectures. Our experiments simulate scheduler transitions between these clusters, capturing a wide range of architectural changes and workload variations found in practice. Applied to a state-of-the-art hierarchical RL-based scheduler, our method demonstrates rapid adaptation across diverse system configurations and workloads. In the six transition experiments, the schedulers enhanced with our approach not only quickly outperformed all 21 baseline heuristic methods in terms of jobs' average and maximum waiting time but also achieved performance comparable to schedulers trained from scratch. Notably, even in the most time-consuming transition case, integrating our approach reduced the required training timesteps to just 1.76% of the total timesteps needed for training a scheduler from scratch - representing a 56.8× reduction in training effort. This demonstrates its ability to efficiently adapt existing schedulers to evolving HPC architectures with minimal cost, providing a practical solution for real-world HPC operations.

Serverless platforms are increasingly being used to process continuous streams of data. However, data processing units (expressed as serverless 'functions') in such platforms cannot maintain state internally and, instead, rely on remote storage. Stateful serverless is an emerging paradigm that seeks to reduce the latency associated with remote storage access by introducing state servers on worker nodes, i.e., where the serverless functions run. While existing stateful serverless frameworks are successful in reducing latency compared to their stateless counterparts, there are multiple challenges that still need to be addressed in order to meet the real-time data processing requirements of streaming applications. As a result, this paper proposes ScalaSSC, a novel framework for data processing request scheduling and operator state management tailored to stream processing applications within stateful serverless computing. ScalaSSC co-locates requests with the state they act upon to avoid cross-worker state access. To reduce state access contention among executors, ScalaSSC not only introduces the concept of state parallelism to serverless computing, but also processes requests acting upon the same state in the same batch. During batch execution, when multiple states are required, batch APIs are provided to access all states in a single operation. Experimental results show that ScalaSSC achieves up to 845 times higher throughput than another stateful serverless system while maintaining similar end-to-end latency. It also achieves a throughput 14 times higher than that of Amazon Lambda while maintaining end-to-end latency at the microsecond level, in contrast to Lambda's latency at the second level.

This paper presents HPCsim, a modular and extensible simulation framework designed to support research in High-Performance Computing workload management. HPCsim focuses on modeling the full scheduling cycle — including job submission, queuing, job selection, resource allocation, execution, and evaluation — using real traces and structured cluster metadata. Most of the existing simulation tools focus on low-level system behavior but lack the abstractions needed for HPC workload management research. They do not natively support multi-resource job models, batch queuing, or system-level scheduling policies. Moreover, their focus on low-level execution details, such as hardware timing, message passing, and architectural interactions, introduces significant computational overhead, making them inefficient for large-scale experiments in high-level workload management, especially in learning-based scheduling where rapid simulation and frequent policy updates are critical. The framework is built based on Slurm, one of the most widely deployed workload managers, and introduces a structured workload data schema encompassing job traces, node configurations, and switch-based topologies. HPCsim is fully compatible with Gymnasium, enabling integration with reinforcement learning workflows, while also supporting other scheduling strategies. We validate HPCsim through experiments using real traces from a GPU-accelerated HPC cluster and demonstrate its utility for comparing scheduling policies and visualizing topology-sensitive placement behavior. HPCsim is released as an open-source tool to facilitate reproducibility and accelerate research in HPC scheduling.

Microservice architectures are increasingly used to modularize IoT applications and deploy them in distributed and heterogeneous edge computing environments. Over time, these microservice-based IoT applications are susceptible to performance anomalies caused by resource hogging (e.g., CPU or memory), resource contention, etc., which can negatively impact their Quality of Service and violate their Service Level Agreements. Existing research on performance anomaly detection for edge computing environments focuses on model training approaches that either achieve high accuracy at the expense of a time-consuming and resource-intensive training process or prioritize training efficiency at the cost of lower accuracy. To address this gap, while considering the resource constraints and the large number of devices in modern edge platforms, we propose two clustering-based model training approaches: (1) intra-cluster parameter transfer learning (ICPTL)-based model training and (2) cluster-level model (CM) training. These approaches aim to find a tradeoff between the training efficiency of anomaly detection models and their accuracy. We compared the models trained under ICPTL and CM to models trained for specific devices (most accurate, least efficient) and a single general model trained for all devices (least accurate, most efficient). Our findings show that ICPTL’s model accuracy is comparable to that of the model per device approach while requiring only 40% of the training time. In addition, CM further improves training efficiency by requiring 23% less training time and reducing the number of trained models by approximately 66% compared to ICPTL, yet achieving a higher accuracy than a single general model.

Cloud platforms commonly exploit workload temporal flexibility to reduce their carbon emissions. They suspend/resume workload execution for when and where the energy is greenest. However, increasingly prevalent delay-intolerant real-time workloads challenge this approach. To this end, we present a framework to harvest green renewable energy for real-time workloads in cloud systems. We useRenewables-driven coresin servers to dynamically switch CPU cores between real-time and low-power profiles, matching renewable energy availability. We then develop a VM Execution Model to guarantee running VMs are allocated with cores in thereal-time power profile. If such cores are insufficient, we conduct criticality-aware VM evictions as needed. Furthermore, we develop a VM Packing Algorithm to utilize available cores across the servers. We introduce theGreen Coresconcept in our algorithm to convert renewable energy usage into a server inventory attribute. Based on this, we jointly optimize for renewable energy utilization and reduction of VM eviction incidents. We implement a prototype of our framework in OpenStack asopenstack-gc. Using an experimentalopenstack-gccloud and a large-scale simulation testbed, we expose our framework to VMs running RTEval, a real-time evaluation program, and a 14-day Azure VM arrival trace. Our results show: i) a 6.52× reduction in coefficient of variation of real-time latency over an existing workload temporal flexibility-based solution, and ii) a joint 79.64% reduction in eviction incidents with a 34.83% increase in energy harvest over the state-of-the-art packing algorithms. We open sourceopenstack-gcat https://github.com/tharindu-b-hewage/openstack-gc.

During times of crisis, social media platforms play a crucial role in facilitating communication and coordinating resources. In the midst of chaos and uncertainty, communities often rely on these platforms to share urgent pleas for help, extend support, and organize relief efforts. However, the overwhelming volume of conversations during such periods can escalate to unprecedented levels, necessitating the automated identification and matching of requests and offers to streamline relief operations. Additionally, there is a notable absence of studies conducted in multilingual settings despite the fact that any geographical area can have a diverse linguistic population. Therefore, we proposecrisisresponsematcher (CReMa), a systematic approach that integrates textual, temporal, and spatial features to address the challenges of effectively identifying and matching requests and offers on social media platforms during emergencies. Our approach utilizes a crisis-specific pretrained model and a multilingual embedding space. We emulate human decision-making to compute temporal and spatial features and nonlinearly weigh the textual features. The results from our experiments are promising, outperforming strong baselines. Additionally, we introduce a novel multilingual dataset, simulating help-seeking and offering assistance on social media in 16 languages, and conduct comprehensive cross-lingual experiments. Furthermore, we analyze a million-scale geotagged global dataset to understand patterns in seeking help and offering assistance on social media. Overall, these contributions advance the field of crisis informatics and provide benchmarks for future research in the area.

Abstract High-performance computing (HPC) systems face increasing challenges in job scheduling due to the evolving complexity of computational tasks and the growing diversity and heterogeneity of resources. Job allocation is a critical aspect in contemporary HPC systems, due to compute nodes possessing an increased capacity in terms of physical resources and having the capability to execute multiple jobs simultaneously. However, job allocation is often overlooked in existing reinforcement learning (RL)-based schedulers that mainly focus on selecting suitable jobs from the job queue and leave allocation to overly simplistic policies, such as first-available allocation. The bin-packing nature at the node level of modern HPC necessitates more refined and intelligent allocation strategies. This paper introduces HeraSched, a novel hierarchical reinforcement learning (HRL)-based scheduler, adept at intelligent job selection without separate backfilling and heterogeneity-aware allocation, tailored for modern HPC environments. It efficiently manages diverse workloads across CPU and GPU cluster partitions. We evaluate HeraSched using real-world workloads, demonstrating significant improvements in reducing job waiting times and preventing job starvation compared to 27 scheduling combinations. In validation, the best maximum waiting time among compared methods is 78% higher than HeraSched’s result in overloaded CPU partitions. This performance demonstrates HeraSched’s ability to manage intensely stressed workloads and adapt to previously unseen, high-demand scenarios, thereby establishing a new standard in HPC job scheduling.

Modern data processing workloads often have highly unpredictable end-to-end latency characteristics that are caused by heterogeneity, time-variation, and parallelized processing. The increase in unpredictability is in part attributable to job "straggling", and is symptomatic of a new class of stochastic scheduling challenges that will degrade the performance of current and future applications at scale. While the job scheduling literature for data processing frameworks is rich with ideas; there is little coordination between research groups on methodology and presentation, stunting the ability for designers to survey a collection of results and draw generalizable conclusions about good design patterns. We introduce an abstract system model for data processing on warehouse scale machines that aids in eliminating ambiguity in the job scheduling research by categorizing schedulers based on where they act on the system in the job processing data pathway. Furthermore, we demonstrate that although the scheduling problem is NP-Hard in the general case, it is still possible to derive scheduler design principles using bounds and asymptotics.

Streaming applications are expected to process an ever-increasing amount of data with high throughput and stringent latency requirements. Flooding these applications with incoming data may overload the stream processing engine, leading to a system with unstable queues and infinitely growing latencies. Existing stream processing systems are equipped to deal with such overload scenarios reactively, either through back pressure or load shedding mechanisms. These mechanisms, however, have considerable drawbacks as they consume additional system resources, incur in non-negligible performance overheads, and may compromise the quality of application-level results. To address this gap, we propose a strategy based on reinforcement learning to throttle the input rate of data sources in streaming applications. The proposed strategy mitigates overload scenarios by addressing the source of the problem, thus allowing resources to be better utilized by application and system components and mitigating the performance overhead of system-level reactive mechanisms. Through our experiments with two different applications, we demonstrate that our proposed approach reduces end-to-end latencies by up to 82% and increases throughput by up to 10% compared to back pressure mechanisms implemented in state-of-the-art stream processing engines.

Social media platforms play an essential role in crisis communication, but analyzing crisis-related social media texts is challenging due to their informal nature. Transformer-based pre-trained models like BERT and RoBERTa have shown success in various NLP tasks, but they are not tailored for crisis-related texts. Furthermore, general-purpose sentence encoders are used to generate sentence embeddings, regardless of the textual complexities in crisis-related texts. Advances in applications like text classification, semantic search, and clustering contribute to the effective processing of crisis-related texts, which is essential for emergency responders to gain a comprehensive view of a crisis event, whether historical or real-time. To address these gaps in crisis informatics literature, this study introduces CrisisTransformers, an ensemble of pre-trained language models and sentence encoders trained on an extensive corpus of over 15 billion word tokens from tweets associated with more than 30 crisis events, including disease outbreaks, natural disasters, conflicts, and other critical incidents. We evaluate existing models and CrisisTransformers on 18 crisis-specific public datasets. Our pre-trained models outperform strong baselines across all datasets in classification tasks, and our best-performing sentence encoder improves the state-of-the-art by 17.43% in sentence encoding tasks. Additionally, we investigate the impact of model initialization on convergence and evaluate the significance of domain-specific models in generating semantically meaningful sentence embeddings. The models are publicly available at: https://huggingface.co/crisistransformers.

Abstract Cloud computing environment simulators enable cost‐effective experimentation of novel infrastructure designs and management approaches by avoiding significant costs incurred from repetitive deployments in real Cloud platforms. However, widely used Cloud environment simulators compromise on usability due to complexities in design and configuration, along with the added overhead of programming language expertise. Existing approaches attempting to reduce this overhead, such as script‐based simulators and graphical user interface (GUI) based simulators, often compromise on the extensibility of the simulator. Simulator extensibility allows for customization at a fine‐grained level, thus reducing it significantly affects flexibility in creating simulations. To address these challenges, we propose an architectural framework to enable human‐readable script‐based simulations in existing Cloud environment simulators while minimizing the impact on simulator extensibility. We implement the proposed framework for the widely used Cloud environment simulator, the CloudSim toolkit, and compare it against state‐of‐the‐art baselines using a practical use case. The resulting framework, called CloudSim Express, achieves extensible simulations while surpassing baselines with over a % reduction in code complexity and an 89.42% reduction in lines of code.

Function-as-a-Service (FaaS) introduces a lightweight, function-based cloud execution model that finds its relevance in a range of applications like IoT-edge data processing and anomaly detection. While cloud service providers (CSPs) offer a near-infinite function elasticity, these applications often experience fluctuating workloads and stricter performance constraints. A typical CSP strategy is to empirically determine and adjust desired function instances or resources, known asautoscaling, based on monitoring-based thresholds such as CPU or memory, to cope with demand and performance. However, threshold configuration either requires expert knowledge, historical data or a complete view of the environment, making autoscaling a performance bottleneck that lacks an adaptable solution. Reinforcement learning (RL) algorithms are proven to be beneficial in analysing complex cloud environments and result in an adaptable policy that maximizes the expected objectives. Most realistic cloud environments usually involve operational interference and have limited visibility, making them partially observable. A general solution to tackle observability in highly dynamic settings is to integrate Recurrent units with model-free RL algorithms and model a decision process as a Partially Observable Markov Decision Process (POMDP). Therefore, in this paper, we investigate model-free Recurrent RL agents for function autoscaling and compare them against the model-free Proximal Policy Optimisation (PPO) algorithm. We explore the integration of aLong-Short Term Memory(LSTM) network with the state-of-the-art PPO algorithm to find that under our experimental and evaluation settings, recurrent policies were able to capture the environment parameters and show promising results for function autoscaling. We further compare a PPO-based autoscaling agent with commercially used threshold-based function autoscaling and posit that a LSTM-based autoscaling agent is able to improve throughput by 18%, function execution by 13% and account for 8.4% more function instances.

Fog and Edge computing extend cloud services to the proximity of end users, allowing many Internet of Things (IoT) use cases, particularly latency-critical applications. Smart devices, such as traffic and surveillance cameras, often do not have sufficient resources to process computation-intensive and latency-critical services. Hence, the constituent parts of services can be offloaded to nearby Edge/Fog resources for processing and storage. However, making offloading decisions for complex services in highly stochastic and dynamic environments is an important, yet difficult task. Recently, Deep Reinforcement Learning (DRL) has been used in many complex service offloading problems; however, existing techniques are most suitable for centralized environments, and their convergence to the best-suitable solutions is slow. In addition, constituent parts of services often have predefined data dependencies and quality of service constraints, which further intensify the complexity of service offloading. To solve these issues, we propose a distributed DRL technique following the actor-critic architecture based on Asynchronous Proximal Policy Optimization (APPO) to achieve efficient and diverse distributed experience trajectory generation. Also, we employ PPO clipping and V-trace techniques for off-policy correction for faster convergence to the most suitable service offloading solutions. The results obtained demonstrate that our technique converges quickly, offers high scalability and adaptability, and outperforms its counterparts by improving the execution time of heterogeneous services.

Cloud computing has become an important driving force in the economy and the fundamental facility for digitization transformation. Due to its rapid development and increasing demands, accurate resource usage prediction for the cloud has been a long-term challenge. To address this challenge, this paper introduces RCorrPolicy for resource metrics selection and proposes EN-Beats, an efficient ensemble learning-based approach, for predicting multiple resource usages in the cloud. The paper presents trace-driven experiments conducted on a real-world dataset, demonstrating notable improvements in predicting multiple resource metrics. Ablation experiments conducted on existing methods for RCorrPolicy indicate that the proposed policy enhances the performance of these methods across different evaluated metrics. Furthermore, EN-Beats outperforms existing methods by achieving the lowest NRMSE (lower values indicate better performance) for CPU util rate (up to 8% lower), memory usage (up to 6% lower), and network incoming traffic (up to 3% lower). Additionally, EN-Beats attains the highest R2 score (higher values indicate better performance) for predicting CPU util rate (up to 1.39 higher), memory usage (up to 0.57 higher), and network incoming traffic (up to 0.62 higher).

The Internet of Things (IoT) driven latency-critical applications are deployed on lightweight Micro-Clouds at the network's edge. Renting physical space from geographically distributed colocation datacenters connected via a Wide Area Network (WAN) is a cost-effective way of deploying Micro-Clouds, despite WANs' dynamic communication latency from traffic congestion. However, this deployment approach can limit Micro-Clouds to operate within a soft power budget, as colocation datacenter providers utilize it to add more servers and lower capital costs through oversubscribing power infrastructure. As a result, Micro-Clouds use extreme energy reduction measures like power capping and task throttling to address power overdraw events, where power consumption exceeds soft power budget limits, which reduces the performance of latency-critical applications. We propose a solution where a dynamic power budget can be achieved by adding renewable energy sources to the existing soft power budget without upgrading power delivery systems. To take advantage of this, we propose a dynamic, decentralized task-scheduling algorithm called DEMOTS. DEMOTS effectively utilizes the available dynamic power budget in a WAN with varying degrees of network traffic congestion, thereby avoiding the need for extreme energy reduction measures. We implement DEMOTS on a simulation test-bed. Compared to state-of-the-art baseline using MCOP for decentralized task-scheduling in Micro-Clouds, DEMOTS reduces Power Overdraw Impact up to 19%, Task Latency Increase Impact up to 47 %, and Task Schedule Time Impact up to 49%.

Public conversations on Twitter comprise many pertinent topics including disasters, protests, politics, propaganda, sports, climate change, epidemics/pandemic outbreaks, etc., that can have both regional and global aspects. Spatial discourse analysis rely on geographical data. However, today less than 1% of tweets are geotagged; in both cases—point location or bounding place information. A major issue with tweets is that Twitter users can be at location A and exchange conversations specific to location B, which we call the Location A/B problem. The problem is considered solved if location entities can be classified as either origin locations (Location As) or non-origin locations (Location Bs). In this work, we propose a simple yet effective framework—the True Origin Model—to address the problem that uses machine-level natural language understanding to identify tweets that conceivably contain their origin location information. The model achieves promising accuracy at country (80%), state (67%), city (58%), county (56%) and district (64%) levels with support from a Location Extraction Model as basic as the CoNLL-2003-based RoBERTa. We employ a tweet contexualizer (locBERT) which is one of the core components of the proposed model, to investigate multiple tweets’ distributions for understanding Twitter users’ tweeting behavior in terms of mentioning origin and non-origin locations. We also highlight a major concern with the currently regarded gold standard test set (ground truth) methodology, introduce a new data set, and identify further research avenues for advancing the area.

High performance distributed systems such as distributed stream processing systems and message-passing parallel programs are often deployed on platforms that make use of vanilla TCP/IP communication, which in turn uses the conventional Nagle’s algorithm for congestion control. Recent research in Reinforcement Learning (RL) techniques to either replace or control the conventional TCP approach shows promise in achieving a greater degree of performance, especially when the demand for network resources in a multi-tenant platform is highly dynamic and infeasible to model. Existing results are, however, focused on RL for general Internet communication, with the learning objective being some combination of throughput, loss, and latency, and predominately use a continuous action space to adjust the packet rate at the sender. In this work, we propose a coefficient-free RL objective that perfectly matches the data transmission rate to the underlying communication system’s bottleneck, which naturally deters packet loss and thereby converges to the ideal throughput even in lock-free and latency-constrained Big Data applications where packets are dropped due to load shedding or exceeding latency thresholds. Our results compare favorably to other state-of-the-art objective functions using an RL framework, e.g., providing up to 48% reduction in packet loss while obtaining up to a 4% increase in overall throughput when packet latency is highly constrained.

The use of cloud computing for delivering application services over the Internet has gained rapid traction. Since the beginning of the COVID-19 global pandemic, the work from home scheme and increased business presence online have created more demand for computing resources. Many enterprises and organizations are expanding their private data centres and utilizing hybrid or multi-cloud environments for their IT infrastructure. Because of the ever-increasing demand for computing resources, energy consumption and carbon emission have become a pressing issue. Renewable energy sources have been recognized as clean and sustainable alternatives to fossil-fuel based brown energy. However, due to the intermittent nature of availability of renewable energy sources, it brings many challenges to automatically and efficiently schedule tasks under renewable energy constraints and deadlines. Task scheduling with traditional heuristic algorithms are not able to adapt quickly with changing energy availability and stochastic task arrival. In this regard, this work aims at building a novel scheduling policy with deep reinforcement learning, which automatically applies scheduling techniques like workload shifting and cloud -bursting in a geographically distributed hybrid multi-cloud environment consists of multiple private and public clouds. Our primary goals are maximizing renewable energy utilization and avoiding deadline constraint violations. We also introduce user configurable hyper-parameters to enable multi-objective scheduling on cloud cost, makespan and utilization. Our experiment results show that the proposed scheduling approach can achieve the aforementioned objectives dynamically to varying renewable energy availability.

Serverless computing is an event-driven cloud computing architecture for processing requests on-demand, using light weight function containers and a micro-services model. A variety of applications like Internet of Things (IoT) services, edge computing, and stream processing have been introduced to the serverless paradigm. These applications are characterized by their stringent response time requirements, therefore expecting a quick and fault tolerant feedback from the application. The serverless, or Function-as-a-Service (FaaS), paradigm suffers from function `cold start' challenges, where the serverless platform takes time to set up the dependencies, prepare the runtime environment and code for execution before serving the incoming workload. Most of the current works address the problem of cold start by (1) reducing the start-up or preparation time of function containers, or (2) reducing the frequency of function cold starts on the platform. Recent industrial research has identified that factors such as runtime environment, CPU and memory settings, invocation concurrency, and networking requirements, affect the cold start of a function. Therefore, we propose a Reinforcement Learning (Q-Learning) agent setting, to analyze the identified factors such as function CPU utilization, to ascertain the function-invocation patterns and reduce the function cold start frequency by preparing the function instances in advance. The proposed Q-Learning agent interacts with the Kubeless serverless platform by discretizing the environment states, actions and rewards with the use of per-instance CPU utilization, available function instances and success or failure rate of response, respectively. The workload is replicated using the Apache JMeter non-GUI toolkit and our agent is evaluated against the baseline default auto-scale feature of Kubeless. The agent demonstrates the capability of learning the invocation pattern, make informed decisions by preparing the optimal number of function instances over the period of learning, under controlled environment settings.

The performance of a distributed stream processing engine is traditionally considered in terms of fundamental measurements of latency and throughput. Recently, Apache Storm has demonstrated sub-millisecond latencies for inter-component tuple transmission, though it does so through aggressive throttling that leads to strict throughput limitations in order to keep tuple queues near empty. On the other hand, Apache Heron has excellent throughput characteristics, especially when operating near unstable conditions, but its inter-component latencies typically start around 10 milliseconds. Both of these systems require roughly 650MB of installation space. We have developed Dragon, loosely based on the same API as Storm and Heron, that is both lightweight, requiring just 7.5MB of installation space, and competitive in performance to Storm and Heron. In this paper we show experiments with all three systems using the Word Count benchmark. Dragon achieves throughput characteristics near to that of Heron and inter-component latencies less than 10ms under high load. In particular, Dragon's maximum latency is significantly less that Storm's maximum latency under high load. Finally Dragon managed to remain stable at higher effective throughput than Heron. We believe Dragon is a good "allrounder" solution and is particularly suitable for Edge computing applications, given its small installation footprint.

Although cloud computing became a mainstream industrial computing paradigm, low resource utilization remains a common problem that most warehouse-scale datacenters suffer from. This leads to a significant waste of hardware resources, infrastructure investment, and energy consumption. As the diversity in application workloads grows into an essential characteristic in modern datacenters, task co-location of different workloads to the same compute cluster has gained immense popularity as a heuristic solution for resource utilization optimization. Although the existing co-location methodologies manage to improve resource efficiency to a certain degree, application QoS is usually sacrificed as a trade-off when dealing with resource interference between different applications. This paper proposes a containerized task co-location (CTCL) scheduler to improve resource utilization and minimize task eviction rate. Our CTCL scheduler (1) applies an elastic task co-location strategy to improve resource utilization; and (2) supports a dynamic task rescheduling mechanism to prevent severe QoS degradation from frequent task evictions. We evaluate our approach in terms of resource efficiency and rescheduling cost through the ContainerCloudSim simulator. Our experiments with the Alibaba 2018 workload traces demonstrate that CTCL could improve overall resource efficiency and reduce rescheduling rate by 38% and 99% respectively.

Summary Containers, enabling lightweight environment and performance isolation, fast and flexible deployment, and fine‐grained resource sharing, have gained popularity in better application management and deployment in addition to hardware virtualization. They are being widely used by organizations to deploy their increasingly diverse workloads derived from modern‐day applications such as web services, big data, and internet of things in either proprietary clusters or private and public cloud data centers. This has led to the emergence of container orchestration platforms, which are designed to manage the deployment of containerized applications in large‐scale clusters. These systems are capable of running hundreds of thousands of jobs across thousands of machines. To do so efficiently, they must address several important challenges including scalability, fault tolerance and availability, efficient resource utilization, and request throughput maximization among others. This paper studies these management systems and proposes a taxonomy that identifies different mechanisms that can be used to meet the aforementioned challenges. The proposed classification is then applied to various state‐of‐the‐art systems leading to the identification of open research challenges and gaps in the literature intended as future directions for researchers.

The use of cloud computing, particularly of Infrastructure as a Service clouds, for the execution of largescale scientific workflows has been a topic of interest in recent years. These environments offer on-demand access to all of the infrastructure required for the deployment of workflows, allowing users to pay only for what they use. This leads to schedulers having to find a trade-off between two conflicting quality of service requirements: time and cost. The majority of research in this area has focused on developing scheduling algorithms that have as objective minimizing the infrastructure cost while meeting a deadline constraint. Few algorithms, however, have addressed the problem of minimizing the execution time of the workflow while meeting a budget constraint. This paper focuses on the latter case. We propose a budget-distribution algorithm that assigns a portion of the overall workflow budget to the individual tasks. This task-level budget then guides the dynamic scheduling process and is continuously refined to reflect any unexpected costs. When compared to the state-of-the-art algorithm, the performance evaluation results demonstrate that in 88% of the cases, our proposal achieves equal or better performance in terms of meeting the budget constraint and achieves lower execution times in 84% of the cases.

Summary Large‐scale scientific problems are often modeled as workflows. The ever‐growing data and compute requirements of these applications has led to extensive research on how to efficiently schedule and deploy them in distributed environments. The emergence of the latest distributed systems paradigm, cloud computing, brings with it tremendous opportunities to run scientific workflows at low costs without the need of owning any infrastructure. It provides a virtually infinite pool of resources that can be acquired, configured, and used as needed and are charged on a pay‐per‐use basis. However, along with these benefits come numerous challenges that need to be addressed to generate efficient schedules. This work identifies these challenges and studies existing algorithms from the perspective of the scheduling models they adopt as well as the resource and application model they consider. A detailed taxonomy that focuses on features particular to clouds is presented, and the surveyed algorithms are classified according to it. In this way, we aim to provide a comprehensive understanding of existing literature and aid researchers by providing an insight into future directions and open issues.

With the advent of cloud computing and the availability of data collected from increasingly powerful scientific instruments, workflows have become a prevailing mean to achieve significant scientific advances at an increased pace. Scheduling algorithms are crucial in enabling the efficient automation of these large-scale workflows, and considerable effort has been made to develop novel heuristics tailored for the cloud resource model. The majority of these algorithms focus on coarse-grained billing periods that are much larger than the average execution time of individual tasks. Instead, our work focuses on emerging finer-grained pricing schemes (e.g., per-minute billing) that provide users with more flexibility and the ability to reduce the inherent wastage that results from coarser-grained ones. We propose a scheduling algorithm whose objective is to optimize a workflow’s execution time under a budget constraint; quality of service requirement that has been overlooked in favor of optimizing cost under a deadline constraint. Our proposal addresses fundamental challenges of clouds such as resource elasticity, abundance, and heterogeneity, as well as resource performance variation and virtual machine provisioning delays. The simulation results demonstrate our algorithm’s responsiveness to environmental uncertainties and its ability to generate high-quality schedules that comply with the budget constraint while achieving faster execution times when compared to state-of-the-art algorithms.

Scientific workflows are used to process vast amounts of data and to conduct large-scale experiments and simulations. They are time consuming and resource intensive applications that benefit from running in distributed platforms. In particular, scientific workflows can greatly leverage the ease-of-access, affordability, and scalability offered by cloud computing. To achieve this, innovative and efficient ways of orchestrating the workflow tasks and managing the compute resources in a cost-conscious manner need to be developed. We propose an adaptive, resource provisioning and scheduling algorithm for scientific workflows deployed in Infrastructure as a Service clouds. Our algorithm was designed to address challenges specific to clouds such as the pay-as-you-go model, the performance variation of resources and the on-demand access to unlimited, heterogeneous virtual machines. It is capable of responding to the dynamics of the cloud infrastructure and is successful in generating efficient solutions that meet a user-defined deadline and minimise the overall cost of the used infrastructure. Our simulation experiments demonstrate that it performs better than other state-of-the-art algorithms.

Cloud computing is the latest distributed computing paradigm and it offers tremendous opportunities to solve large-scale scientific problems. However, it presents various challenges that need to be addressed in order to be efficiently utilized for workflow applications. Although the workflow scheduling problem has been widely studied, there are very few initiatives tailored for cloud environments. Furthermore, the existing works fail to either meet the user's quality of service (QoS) requirements or to incorporate some basic principles of cloud computing such as the elasticity and heterogeneity of the computing resources. This paper proposes a resource provisioning and scheduling strategy for scientific workflows on Infrastructure as a Service (IaaS) clouds. We present an algorithm based on the meta-heuristic optimization technique, particle swarm optimization (PSO), which aims to minimize the overall workflow execution cost while meeting deadline constraints. Our heuristic is evaluated using CloudSim and various well-known scientific workflows of different sizes. The results show that our approach performs better than the current state-of-the-art algorithms.