Michal Konopa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Michal Konopa has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Jan Fesl
Department of Data Science and Computer Systems Faculty of Agriculture and Technology University of South Bohemia Czech Republic
2 shared publications - Ladislav Beránek
Department of Data Science and Computer Systems Faculty of Agriculture and Technology University of South Bohemia Czech Republic
2 shared publications - Jan Fesl
Department of Computer Systems, Faculty of Information Technology, Czech Technical University in Prague, Prague, Czech Republic
1 shared publication - Jiří Jelínek
University of South Bohemia
1 shared publication
Latest Publications
- Open Access
JASDA: Introducing Job-Aware Scheduling in Scheduler-Driven Job Atomization
The increasing complexity and temporal variability of workloads on MIG-enabled GPUs challenge the scalability of traditional centralized scheduling. Building upon the SJA concept, this paper introduces JASDA-a novel paradigm that extends SJA from a largely centralized scheduling model toward a fully decentralized negotiation process. In JASDA, jobs actively generate and score feasible subjobs in response to scheduler-announced execution windows, while the scheduler performs policy-driven clearing that balances utilization, fairness, and temporal responsiveness. This bidirectional, iterative interaction embeds feedback, calibration, and probabilistic safety directly into the scheduling loop, enabling adaptive and transparent decision-making. By coupling principles from auction theory and online optimization with the temporal granularity of GPU workloads, JASDA provides a scalable foundation for market-aware and fairness-driven resource management-bridging theoretical scheduling models with practical deployment in modern MIG-enabled environments relevant to Artificial Intelligence and Agriculture 4.0.
Open AccessJASDA: Introducing Job-Aware Scheduling in Scheduler-Driven Job Atomization
The increasing complexity and temporal variability of workloads on MIG-enabled GPUs challenge the scalability of traditional centralized scheduling. Building upon the SJA concept, this paper introduces JASDA-a novel paradigm that extends SJA from a largely centralized scheduling model toward a fully decentralized negotiation process. In JASDA, jobs actively generate and score feasible subjobs in response to scheduler-announced execution windows, while the scheduler performs policy-driven clearing that balances utilization, fairness, and temporal responsiveness. This bidirectional, iterative interaction embeds feedback, calibration, and probabilistic safety directly into the scheduling loop, enabling adaptive and transparent decision-making. By coupling principles from auction theory and online optimization with the temporal granularity of GPU workloads, JASDA provides a scalable foundation for market-aware and fairness-driven resource management-bridging theoretical scheduling models with practical deployment in modern MIG-enabled environments relevant to Artificial Intelligence and Agriculture 4.0.
- Open Access
Scheduler-Driven Job Atomization
Modern GPU clusters, particularly those built on NVIDIA's Multi-Instance GPU (MIG) architecture, often suffer from inefficiencies because jobs are treated as rigid, indivisible blocks that occupy a fixed slice until completion. The reliance on static peak memory estimates exacerbates fragmentation, underutilization, and job rejections. We propose Scheduler-Driven Job Atomization (SJA), a new paradigm that establishes a bidirectional interaction between scheduler and jobs. In SJA, the scheduler advertises available execution gaps, and jobs respond by signaling interest if they can potentially generate a subjob that fits the offered time-capacity window. The scheduler may collect multiple signals for the same slot and, based on its allocation policy (e.g., fairness, efficiency, or SLA priorities), selects which job is granted the slot. Only then does the chosen job materialize a safe, self-contained subjob tailored to that opportunity. Unlike migration or preemption, SJA proactively shapes workloads before execution, thereby avoiding costly state transfers and unpredictable interruptions. It aims to increase GPU utilization, reduce wait times, and minimize migration overhead by aligning jobs with opportunities in real time, ensuring that each admitted subjob is correct by construction. This paper is presented as a concept paper: it introduces the paradigm, defines its building blocks, and outlines future research directions, rather than offering a full experimental evaluation.
Open AccessScheduler-Driven Job Atomization
Modern GPU clusters, particularly those built on NVIDIA's Multi-Instance GPU (MIG) architecture, often suffer from inefficiencies because jobs are treated as rigid, indivisible blocks that occupy a fixed slice until completion. The reliance on static peak memory estimates exacerbates fragmentation, underutilization, and job rejections. We propose Scheduler-Driven Job Atomization (SJA), a new paradigm that establishes a bidirectional interaction between scheduler and jobs. In SJA, the scheduler advertises available execution gaps, and jobs respond by signaling interest if they can potentially generate a subjob that fits the offered time-capacity window. The scheduler may collect multiple signals for the same slot and, based on its allocation policy (e.g., fairness, efficiency, or SLA priorities), selects which job is granted the slot. Only then does the chosen job materialize a safe, self-contained subjob tailored to that opportunity. Unlike migration or preemption, SJA proactively shapes workloads before execution, thereby avoiding costly state transfers and unpredictable interruptions. It aims to increase GPU utilization, reduce wait times, and minimize migration overhead by aligning jobs with opportunities in real time, ensuring that each admitted subjob is correct by construction. This paper is presented as a concept paper: it introduces the paradigm, defines its building blocks, and outlines future research directions, rather than offering a full experimental evaluation.
- Open Access
- 1 December 2023
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 13 (6) , 6691-6700
A novel deep-learning based approach to DNS over HTTPS network traffic detection
Domain name system (DNS) over hypertext transfer protocol secure (HTTPS) (DoH) is currently a new standard for secure communication between DNS servers and end-users. Secure sockets layer (SSL)/transport layer security (TLS) encryption should guarantee the user a high level of privacy regarding the impossibility of data content decryption and protocol identification. Our team created a DoH data set from captured real network traffic and proposed novel deep-learning-based detection models allowing encrypted DoH traffic identification. Our detection models were trained on the network traffic from the Czech top-level domain maintainer, Czech network interchange center (CZ.NIC), and successfully applied to the identification of the DoH traffic from Cloudflare. The reached detection model accuracy was near 95%, and it is clear that the encryption does not prohibit the DoH protocol identification.
- 1 December 2023
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 13 (6) , 6691-6700
Open AccessA novel deep-learning based approach to DNS over HTTPS network traffic detection
Domain name system (DNS) over hypertext transfer protocol secure (HTTPS) (DoH) is currently a new standard for secure communication between DNS servers and end-users. Secure sockets layer (SSL)/transport layer security (TLS) encryption should guarantee the user a high level of privacy regarding the impossibility of data content decryption and protocol identification. Our team created a DoH data set from captured real network traffic and proposed novel deep-learning-based detection models allowing encrypted DoH traffic identification. Our detection models were trained on the network traffic from the Czech top-level domain maintainer, Czech network interchange center (CZ.NIC), and successfully applied to the identification of the DoH traffic from Cloudflare. The reached detection model accuracy was near 95%, and it is clear that the encryption does not prohibit the DoH protocol identification.