Apr 2026· SEAMS@ICSE· pp. 253-258· 0 citations· 11 references
Computer Science
TL;DR
iFogSim-placement, a framework designed for experimenting with self-adaptive service placement, is introduced, demonstrating its ability to capture performance metrics, including application latency, resource usage, and energy consumption.
Abstract
Service placement in edge computing is a complex multi-objective optimisation problem defined by conflicting requirements and dynamic environments. While self-adaptive approaches are essential for handling this dynamism, the community needs specific frameworks to evaluate them. We introduce iFogSim-placement, a framework designed for experimenting with self-adaptive service placement. Unlike existing simulators, iFogSim-placement decouples decision-making from execution for modelling information staleness, mobility, and stochastic demand. The artefact enables implementing self-adaptive approaches as Java plug-ins and evaluating them under heterogeneous configurations. Researchers can define experiments to evaluate self-adaptive approaches under variable configurations, including network topology, application complexity, request patterns, and mobility scenarios. We present the architecture, usage instructions, and validation of the artefact, demonstrating its ability to capture performance metrics, including application latency, resource usage, and energy consumption. The artefact is open-source (https://github.com/DawnSpider96/iFogSim-Placement), aiming to lower the barrier to developing and fairly benchmarking self-adaptive edge systems.
ADASCALE is an adaptive framework that jointly scales and places microservice replicas under multi-dimensional dynamics that consistently meets SLO targets and improves both latency and throughput.
Ming Chen, Muhammed Tawfiqul Islam, M. R. Read et al.· 0 citations
Edge computing is a promising paradigm for deploying latency-sensitive applications (Apps) as it brings resources closer to end users. Edge Apps often adopt a microservice (MS) architecture, breaking monolithic Apps into lightweight, containerized MSs that can be dynamically and independently deployed. However, managing such Apps involves three key challenges: (i) optimizing the placement of MSs to reduce both response time and resource overhead, (ii) handling MS migration or relocation as users move while minimizing App service disruption (App downtime), and (iii) enabling MS sharing across Apps while ensuring performance guarantees. We formulate this as an optimization problem, named Multi-microservice Application Placement (MAP), prove its NP-hardness, and introduce STEP (State and Topology-aware Edge-MS Placement), a polynomial-time heuristic. STEP distinguishes itself from prior work by: (i) jointly considering stateful and stateless MS characteristics in deployment decisions, (ii) exploiting MS shareability to reduce resource usage, (iii) balancing response latency, App downtime, and resource utilization, and (iv) leveraging multiple versions of the same MS to adapt quality of service to available edge resources. Our results in a small-scale scenario show that STEP achieves near-optimal performance with only 7% higher CPU cost than the optimal solution. Large-scale real-time experiments on a Kubernetes cluster demonstrate that STEP consistently outperforms competing methods, achieving up to 50% lower deployment costs while delivering 50% gain in app quality and saving 15% in radio resources with over 90% request success rates.
Madhura Adeppady, Yenchia Yu, Ali Rahmanian et al.· IEEE Transactions on Network...· 0 citations
This paper presents the design and evaluation of a network slicing implementation in a simulated 5G Standalone (SA) mobile network deployed as a nomadic edge node, where “nomadic” refers to the physical portability and ease of redeployment of a self-contained, containerized 5G testbed suitable for university teaching and experimentation. The platform integrates Open5GS, UERANSIM, Kamailio, and Prometheus/Grafana to emulate a sliced 5G core and access network supporting differentiated service requirements typical of heterogeneous traffic classes and latency-sensitive applications. Slice provisioning is fully configurable, and Docker-based resource constraints are applied to enforce Quality of Service (QoS) differentiation. Performance was assessed through bandwidth and traffic-quality measurements, demonstrating measurable improvements in packet loss and jitter for high-priority slices, with corresponding degradation for lower-priority slices. Although the laboratory environment limits replication of distributed real-world deployments, the results confirm the effectiveness of network slicing for traffic isolation and service prioritization in 5G SA systems. These findings highlight the practical boundaries of container-based slicing enforcement in a single-host nomadic 5G SA node, and inform the design of future multi-host deployments.
Elena-Ramona Modroiu, Jianwei Cheng, Damian Atlaß et al.· International Conference on...· 0 citations
The lack of determinism restricts the integration of safety-critical applications into Edge–Fog–Cloud (EFC) architectures. Existing EFC schedulers are typically designed for dynamic, best-effort operation based on unmanaged resource allocation and elastic virtualization. This paradigm introduces unbounded queueing, resource contention, and timing jitter, making standard schedulers unsuitable for hard-deadline workloads. Moreover, most approaches focus on computational placement, while communication is abstracted or treated as a secondary cost term. As a result, bounded-latency routing and deterministic task execution are rarely co-optimized under a unified timing model. This paper addresses these gaps by utilizing a managed Time-Triggered Edge–Fog–Cloud (TTEFC) architecture that supports safety-critical workloads, orchestrates IEEE Time-Sensitive Networking (TSN) for local intra-domain communication, and uses IETF Deterministic Networking (DetNet) for routed inter-domain paths. On this infrastructure, a hierarchical genetic algorithm (HGA) is proposed to jointly schedule partition-to-execution-location allocation, partition execution order, inter-partition route selection, and negotiated per-partition time budgets that act as temporal boundaries for parallel partition-level optimizers. An adaptive slack reallocation operator redistributes unused temporal slack from over-satisfied partitions to budget-violating partitions, improving feasibility convergence. Experiments on synthetic DAG workloads with 100–500 tasks compare the proposed HGA against HEFT and round-robin baselines. These baselines are included as scoped external references to contextualize the end-to-end scheduling performance of the proposed method. Ablation results show that slack reallocation improves partition-budget feasibility, reaches feasible budget assignments earlier, and produces tighter budget–makespan alignment than feedback-free and static-budget variants. An automotive-characteristic DAG case study further evaluates the method on an application-oriented workload under the same timing and communication assumptions.
Omar Hekal, Josepaul Paulachan, Daniel Onwuchekwa et al.· Future Internet· 0 citations
Energy community simulations based on optimization models are increasingly used to evaluate energy sharing strategies among prosumers. However, integrating such computationally intensive models into user-facing applications presents significant challenges, including limited solver concurrency, long execution times, and the need for scalable and secure infrastructures. This paper presents a scalable architecture for delivering energy community simulations as a service. The proposed system integrates optimization models defined in Pyomo and solved using Gurobi within a distributed environment based on remote compute servers. To address bounded solver concurrency and avoid blocking in the API layer under concurrent requests, a job-based execution model is introduced, enabling asynchronous task handling and controlled concurrency. The architecture is implemented using a containerized approach, combining an API layer for request handling with a distributed execution layer for optimization tasks, and infrastructure as code to ensure reproducibility and security. Experimental evaluation demonstrates the system's ability to manage concurrent simulation workloads while maintaining responsiveness and respecting solver limitations. The results highlight how appropriate system design enables the practical deployment of optimization-based energy simulations, bridging the gap between research models and real-world applications.
D. Pereira, Pedro Rafael, Jo˜ao Soares et al.· Annual International Compute...· 0 citations
The deployment of microservices in edge environments is increasingly critical to support latency-sensitive and data-intensive applications such as IoT analytics, real-time monitoring, and smart city services. Edge infrastructures are highly heterogeneous in terms of compute capacity, communication latency, and energy efficiency. Furthermore, the geographical distance between edge nodes may introduce non-negligible energy consumption for data transfers, which is often overlooked in traditional placement strategies. While prior works focus on minimizing response time, there is a need to adapt and extend such strategies for energy efficiency in edge computing. This paper proposes an Energy-Latency Trade-off Optimization Strategy (ELTOS) for microservice placement in edge environments. ELTOS formulates and solves a cost-based optimization for microservice placement on heterogeneous edge servers. The main goal of this optimization algorithm is to minimize the transmitted data size between microservices on different edge servers, saving energy while ensuring a suitable level of end-to-end latency for each request. Experimental evaluations using real edge computing infrastructure demonstrate the efficiency of the proposed ELTOS compared with previous work. A comparison result of energy consumption shows that ELTOS outperforms the previous method in 70% of all pairwise comparisons; therefore, ELTOS consumes less energy while maintaining QoS performance level. ELTOS enhances the median, 95th, and 99th percentile response times on average by 6.03%, 7.47%, and 3.30%, respectively.
Ida Falco, A. K. Idrees, Carmine Colarusso et al.· International Conference on...· 0 citations