Hierarchical Scheduler with Adaptive Time-Budget Reallocation for Time-Triggered Edge-Fog-Cloud Architectures

Execution Timing Control for Deterministic Task Offloading in the IoT-Edge-Cloud Continuum

Latency-critical IoT applications, such as autonomous mobility and industrial automation, require deterministic guarantees to ensure that tasks are completed within strict deadlines. The 6G-enabled IoT-edge-cloud continuum can support such requirements by leveraging communication, computation and intelligence resources across devices, edge, and cloud infrastructures. However, existing task offloading strategies mainly focus on selecting where tasks are executed and typically assume immediate processing upon task arrival. This leads to transient congestion when multiple tasks coincide in time and results in inefficient resource utilization under dynamic workloads. This paper addresses these limitations by introducing an execution timing control strategy for deterministic task offloading that jointly determines where tasks are executed and when their execution starts, while guaranteeing deadline compliance. The key idea is to exploit the latency budget of tasks to control their execution timing, enabling a more balanced distribution of workload over time and reducing peak congestion across the continuum. Evaluation results show that, compared to existing benchmarks, the proposed approach achieves up to 70% higher satisfaction ratio, reduces the communication resources usage by 40%, lowers peak computing resource utilization by 15%, and decreases average execution time by up to 77%.

Beyond the Limits: Flexible and Congestion-Aware Cluster Scheduling for the Cloud

Workload scheduling in cloud environments often relies on simplistic assumptions about application resource needs and hardware utilization. Overlooking application-level performance objectives and hardware resource contention that leads to inefficient resource usage and degraded performance. This paper addresses two key limitations of current approaches. First, unnecessarily strict enforcement of service level objectives (SLOs) often leads to resource underutilization and poor energy efficiency. Second, lack of congestion awareness in shared resources such as last-level cache (LLC) and memory bandwidth. In this paper, we propose two complementary strategies to address these limitations: (i) integrating soft SLO limits that allow controlled overcommitment and tolerate minor, transient violations to improve cluster efficiency, and (ii) introducing resource-aware scheduling and rescheduling based on real-time congestion insights for shared resources such as last-level cache (LLC) and memory bandwidth. Our results show that soft SLO limits reduce corrective rescheduling actions by 49% compared to hard-limit approaches while maintaining acceptable performance guarantees. Additionally, resource-aware scheduling decreases node-level congestion by 8% and further mitigates SLO violations, demonstrating the effectiveness of incorporating application-level flexibility and hardware-level insights into scheduling and rescheduling decisions.

Task-aware dynamic optimization for edge cloud systems

Internet of Things-Centric Optimized Service Provisioning in Multi-Cloud Environment

Due to the rapid growth of IoT and smart city applications the need for low-latency efficient service provisioning in distributed systems has grown substantially. Conventional cloud-centric architectures which rely on centralized processing tend to introduce significant latency that makes them ill-suited for real-time IoT workloads. This work addresses the challenge of service placement and resource allocation for IoT applications operating across multi cloud and fog computing infrastructures. Achieving satisfactory Quality of Service (QoS) requires simultaneous consideration of latency, bandwidth and resource utilization. Current single cloud and statically configured deployment strategies struggle with scalability and responsiveness in dynamic IoT scenarios. There is a clear need for adaptive intelligent frameworks capable of handling fluctuating workloads and heterogeneous resource availability. To address task placement, this work introduces a lightweight, QoS-aware service placement algorithm that evaluates latency, bandwidth, and node load in real time. Fog-layer task scheduling is handled through an enhanced weighted fair queuing (EWFQ) mechanism that incorporates user-defined priorities and live feedback signals. A weighted Q-learning algorithm (WQLA) is further introduced to refine placement decisions by learning from interactions with the deployment environment across multi-cloud and fog nodes. Simulation results confirm that the proposed approach yields reduced latency and more consistent wait times relative to heuristic and genetic baselines. Energy efficiency and service availability are also sustained under varying load conditions. The combined, adaptive framework delivers a practical and scalable method for IoT service provisioning in multi-cloud environment, advancing the groundwork for future work in context-sensitive, secure, and scalable resource management.

Multi-Queue Priority-Based Scheduling for Real-Time Edge Computing Applications

The rapid proliferation of Internet of Things (IoT) devices has intensified demands for low-latency, resource-efficient task scheduling at the network edge. Conventional policies such as Round-Robin and First-Come-First-Serve (FCFS) fail to satisfy the Quality-of-Service (QoS) requirements of Industrial-IoT and autonomous-vehicle workloads. This paper presents Multi-Queue Priority-Based Scheduling (MQPBS), a lightweight algorithm that classifies tasks into three dynamic priority queues (High, Medium, Low) using deadline-aware heuristics, applies Shortest-Job-First (SJF) intra-queue ordering, and employs an aging mechanism to prevent starvation. Extensive simulation over task sets of 200–1000 tasks demonstrates that MQPBS reduces average waiting time by up to 17.6%, improves throughput by up to 10.8%, lowers energy consumption by 20%, and cuts the Deadline Miss Ratio (DMR) compared with the Priority-Aware Task-Scheduling (PaTS) baseline. Ablation experiments confirm the independent contribution of each algorithmic component. Scalability and sensitivity analyses further validate the robustness of MQPBS under heterogeneous arrival patterns and varying load intensities. The results establish MQPBS as a scalable, reliable scheduler for next-generation edge infrastructures.

Multi-Agent Scheduling with LLM-Assisted Contract Net Negotiation for Stream Processing in Mobile Edge Computing

Stream-processing systems increasingly operate across heterogeneous mobile edge--cloud infrastructures, where workload volatility, resource contention, and stringent quality-of-service (QoS) requirements complicate decentralized scheduling. This paper proposes \emph{MAS-DecStream}, whose main contribution is \emph{LLM-MR-CNP}: an extension of the classical Contract Net Protocol with semantic CFP formulation, progressive context disclosure, multi-round proposal revision, negotiation memory, and deterministic validation. Edge-cluster agents refine natural-language offloading proposals from local observations, predicted resource states, and qualitative runtime context, while hard resource and QoS constraints remain deterministic. Experiments derived from the Alibaba ASI Trace evaluate the extension at three levels: single- versus multi-round CNP, rule-based versus LLM-assisted refinement, and fixed-model single- versus multi-round negotiation. Under the evaluated configurations, MAS-DecStream reduces latency violations to 3\%, eliminates resource overcommitment, reaches a conflict-resolution rate of 0.91 with 20 agents, and improves utility by up to 22\% over the multi-round rule-based baseline. A separate 25-case evaluation shows model- and prompt-dependent accuracy--cost trade-offs. The results provide initial evidence that multi-round CNP refinement is the principal protocol-level gain, with LLM assistance adding value for qualitative and uncertain runtime context.