The 27th Workshop on Advances in Parallel and Distributed Computational Models (APDCM), which was held in conjunction with the International Parallel and Distributed Processing Symposium (IPDPS) on June 3 -7, 2025, aims to provide a timely forum for the exchange and dissemination of new ideas, techniques and research in the field of the parallel and distributed computational models. The APDCM workshop has a history of attracting participation from reputed researchers worldwide. The program committee has encouraged the authors of accepted papers to submit full-versions of their manuscripts to the International Journal of Networking and Computing (IJNC) after the workshop. After a thorough reviewing process, with extensive discussions, three articles on various topics have been selected for publication on the IJNC special issue on APDCM. On behalf of the APDCM workshop, we would like to express our appreciation for the large efforts of reviewers who reviewed papers submitted to the special issue. Likewise, we thank all the authors for submitting their excellent manuscripts to this special issue. We also express our sincere thanks to the editorial board of the International Journal of Networking and Computing, in particular, to the Editor-in-chief Professor Koji Nakano. This special issue would not have been possible without his support.

抄録全体を表示

Quadratic Unconstrained Binary Optimization (QUBO) has emerged as a unifying framework for diverse NP-hard combinatorial optimization problems. However, a major challenge in existing QUBO solvers is the need for extensive manual tuning of algorithmic hyperparameters, such as temperature schedules in simulated annealing, which can vary greatly in effectiveness depending on the problem instance. In this paper, we propose RL-driven annealing (RLA), a novel approach that integrates reinforcement learning (RL) with annealing-based local searches. Rather than relying on hand-crafted heuristics, RLA trains an agent to adaptively determine a bit-flip policy by observing the statistical properties of the energy differences in the objective function. Crucially, RLA encodes QUBO states as fixed-dimensional statistics, making the method scalable to various problem sizes. To further support large-scale problems, we employ distributed training on multi-GPU platforms using JAX's pmap, parallelizing both environment simulation and policy updates. Experimental evaluations on benchmark datasets, including TSP, QAP, Max-Cut, and randomly generated QUBO instances, demonstrate that RLA achieves solution qualities on par with or better than conventional annealing-based methods, while maintaining robust performance across diverse problem instances without extensive hyperparameter tuning. These results highlight RLA as a promising step toward a flexible and practical solver for QUBO-based applications.

抄録全体を表示

Non-uniform heterogeneous computing architectures are increasingly common in modern computing platforms targeting mission-critical edge-cloud and embedded applications. The multiplicity and diversity of processor and memory characteristics they provide offers unprecedented opportunities for improving performance of those applications through customized mapping of platform resources to the applications’ execution requirements. However, experience with these new platforms is limited compared to previous homogeneous multiprocessor platforms, and new analyses and empirical evaluations are needed to realize their potential more fully. In this paper we present principled analysis techniques and evaluate their effectiveness empirically using structural equation modeling methods in the context of the Orange Pi 5 platform, working towards new abstractions and coordination models to navigate the feature-rich landscape reshaping edge-computing and embedded systems architectures.

抄録全体を表示

This paper investigates the integration of Horizontal Pod Autoscaling (HPA) into containerized microservices architectures, focusing on optimizing performance, resource utilization, and operational costs. Building upon prior research on microservices grouping strategies, experiments were conducted using the Sock-Shop benchmark tool across low, medium, and high workload scenarios. Results reveal that HPA significantly enhances scalability, throughput, and latency—achieving up to 66% improved throughput and 32% reduced response times under certain grouping strategies. However, these advantages come with trade-offs, such as increased disk usage and operational complexity. This study provides a detailed analysis of HPA’s impact on dynamic environments and offers practical recommendations for balancing performance and cost in deployment strategies. Future research directions include exploring alternative scaling models, diverse workload impacts, serverless integration, and operational simplifications.

抄録全体を表示