Přístupnostní navigace
E-application
Search Search Close
Bachelor's Thesis
Author of thesis: Viktorie Lengálová
Acad. year: 2025/2026
Supervisor: prof. Ing. Radim Burget, Ph.D.
Reviewer: Ing. Martin Rosa
Network management represents a significant operational burden for organisations, placing high demands on specialist expertise, time and financial resources. Fast and accurate diagnosis of network faults directly affects service availability and user productivity. This bachelor's thesis presents the design, implementation and experimental evaluation of multi-agent systems using locally deployable generative language models for automatic fault diagnosis in data networks. Three multi-agent system architectures were designed, differing in the number of specialised agents and the approach to dividing the diagnostic task. Each architecture was tested with five language models — GPT-OSS 20B, GPT-OSS 120B, Qwen 2.5, Qwen 3.5 and gemma4. The best result was achieved by the combination of GPT-OSS 120B in the MAS-γ architecture, which reached a weighted accuracy of 69.0 % and a strict accuracy of 64.3 %. The experiments demonstrated that diagnostic quality depends primarily on the appropriate selection and scope of input data, as an excessive volume of information leads to reduced accuracy. The thesis confirms that modern locally deployable language models represent a viable option for supporting network diagnostics as a first-level analysis layer, without the need to transmit sensitive data outside the organisation's infrastructure.
Autogen, network security, generative language models, fault detection, network device configuration, multi-agent systems, OLLAMA, artificial intelligence
Date of defence
16.06.2026
Result of the defence
Defended (thesis was successfully defended)
Grading
A
Process of defence
Studentka prezentovala výsledky své práce a komise byla seznámena s posudky. Studentka obhájila bakalářskou práci a odpověděla na otázky členů komise a oponenta. Otázky: 1. V podkapitole „Vyhodnocení a kritéria testů" uvádzate tri možné prípady vyhodnotenia testu. Ani jeden z nich však nepracuje so zmiešanými scenármi – napríklad keď systém chybu správne opraví, no zároveň identifikuje aj falošne pozitívnu chybu. Nastal takýto prípad počas testovania? Ak áno, ako bol vyhodnotený? 2. Byl ještě jiný důvod použití lokálních jazykových modelů? 3. Na jakém hardwaru byly modely zprovozňovány?
Language of thesis
Czech
Faculty
Fakulta elektrotechniky a komunikačních technologií
Department
Department of Telecommunications
Study programme
Information Security (BPC-IBE)
Composition of Committee
prof. Ing. Radim Burget, Ph.D. (předseda) doc. Ing. Lukáš Malina, Ph.D. (místopředseda) Mgr. Jakub Vostoupal, Ph.D. (člen) Ing. Martin Zukal, Ph.D. (člen) Ing. Martin Jonák, Ph.D. (člen) Ing. Michal Švento (člen) Ing. Willi Lazarov (člen)
Supervisor’s reportprof. Ing. Radim Burget, Ph.D.
Grade proposed by supervisor: A
Reviewer’s reportIng. Martin Rosa
Grade proposed by reviewer: A
Responsibility: Mgr. et Mgr. Hana Odstrčilová