Toward Experimentation-as-a-Service in 5G/6G: The Plaza6G Prototype for AI-Assisted Trials

Toward Experimentation-as-a-Service in 5G/6G: The Plaza6G Prototype for AI-Assisted Trials Sergio Barrachina-Muñoz, Marc Carrascosa-Zamacois, Horacio Bleda, Umair Riaz, Yasir Maqsood, Xavier Calle, Selva Vía, Miquel Payaró, Josep Mangues-Bafalluy Centre Tecnològic de Telecomunicacions de Catalunya (CTTC/CERCA) , Barcelona, Spain sbarrachina, mcarrascosa, hbleda, uriaz, ymaqsood, xcalle, svia, mpayaro, jmangues@cttc.cat Abstract—This paper presents Plaza6G, the first operational Experiment-as-a-Service(ExaS) platform unifying cloud resources with next-generation wireless infrastructure. Developed at CTTC in Barcelona, Plaza6G integrates GPU-accelerated compute clus- ters, multiple 5G cores, both open-source (e.g., Free5GC) and commercial (e.g., Cumucore), programmable RANs, and physical or emulated user equipment under unified orchestration. In Plaza6G, the experiment design requires minimal expertise as it is expressed in natural language via a web portal or a REST API. The web portal and REST API are enhanced with a Large Language Model (LLM)-based assistant, which employs retrieval-augmented generation (RAG) for up-to-date experiment knowledge and Low-Rank Adaptation (LoRA) for continuous domain fine-tuning. Over-the-air (OTA) trials leverage a four- chamber anechoic facility and a dual-site outdoor 5G network operating in sub-6 GHz and mmWave bands. Demonstrations include automated CI/CD integration with sub-ten-minute setup and interactive OTA testing under programmable propagation conditions. Machine-readable experiment descriptors ensure re- producibility, while future work targets policy-aware orchestra- tion, safety validation, and federated testbed integration toward open, reproducible wireless experimentation. Index Terms—Experiment-as-a-service (ExaS), network au- tomation, wireless testbeds, 5G, 6G, LLM I. INTRODUCTION The increasing complexity of next-generation (xG) wire- less networks necessitates experimentation environments that transcend simulation and theoretical modeling. Cloud-native architectures, software-defined networking, and programmable radio interfaces are fundamentally reshaping wireless service design and validation. However, integrating realistic radio con- ditions with scalable computing resources remains challeng- ing. Our previous work [1] built upon theExperimentation-as- a-Service(ExaS) paradigm [2], [3] enabling on-demand, re- producible, and automated experimentation by embedding xG testbeds directly into Continuous Integration and Continuous Deployment (CI/CD) pipelines. While that work established the vision and architectural principles, this paper presents the first operational realization of ExaS via thePlaza6Gplatform. Developed at CTTC in Barcelona,Plaza6Gimplements ExaS by unifying cloud computing flexibility with real 5G and 6G experimental infrastructure (Fig. 1). The platform provisions bare-metal servers, virtual machines/instances, Ku- bernetes clusters, GPUs, and xG radio and core networks This work was partially funded by Spanish MINECO grants TSI-064100-2022-16/-2023-26 (Plaza6G/Plaza6G+) and Grant PID2021-126431OB-I00 (ANEMONE) funded by MCIN/AEI/ 10.13039/501100011033 and by ERDF A way of making Europe Web portal ExaS Scheduler Plaza6G brain LLM Assistant RAG + LoRA User Layer Orchestration Layer Experiment Modalities Simulation ns3, Komondor Compute 3000 CPUs, 30 vGPUs Network 200 Gbps links Infrastructure xG radio UEs, O-RAN, mmWave Experiment repository REST API user Emulation srsRAN, Simbox Storage 500 TB In-lab OTA anechoic chamber Outdoors private 5G network Fig. 1: Conceptual architecture of Plaza6G. through unified orchestration. Users interact via a web portal or API enhanced with a large-language-model (LLM)-based interface that interprets natural-language requests and automat- ically configures compute and wireless resources. This design enables users with minimal domain expertise to deploy com- plex experiments immediately, eliminating manual scripting and configuration barriers. Plaza6G represents, to our knowledge, the first platform merging cloud-scale resources with real wireless infrastructure under an AI-assisted ExaS model. Existing 5G/6G testbeds typically require manual intervention, present fragmented in- terfaces, and demand specialized expertise, constraining ac- cessibility and hindering reproducibility. Plaza6G addresses these limitations through integrated automation and intelligent orchestration. This paper demonstrates Plaza6G’s current capabilities through two representative use cases. First, the API is used to launch in parallel three emulated 5G networks, enabling automated CI/CD network acceptance testing as part of a software developers pipeline, where applications under devel- opment are validated concurrently across different 5G core im- plementations. Second, a real over-the-air (OTA) experiment is executed via the web portal, in which a user requests the deployment of a complete 5G network with a physical user equipment (UE) and a gNB. These concurrent experiments highlight Plaza6G’s scalability, reproducibility, and multi- tenant isolation capabilities. arXiv:2603.16356v1 [cs.NI] 17 Mar 2026 I. THEPLAZA6G PLATFORM ANDRESOURCES A. Architecture and Experiment Modalities Building upon theExperimentation-as-a-Service(ExaS) model introduced in [1],Plaza6Grepresents its first opera- tional instantiationa multi-domain environment enabling auto- mated wireless experimentation across four distinct modalities with varying fidelity levels. The platform adopts a three-layer architecture: theuser layerprovides web portal and REST API access augmented by an LLM-based interface interpreting intents into executable experiment graphs; theorchestration layercoordinates re- source allocation through policy-driven scheduling; and the infrastructure layerexposes heterogeneous compute, network, and radio assets as composable services. User interaction combines graphical workflow composition with natural-language processing via an LLM-based assistant. The LLM backend, deployed locally at CTTC, leverages retrieval-augmented generation (RAG) and Low-Rank Adap- tation (LoRA) [4] to improve technical dialogue accuracy and orchestration safety while maintaining low latency. Fig. 2 shows the portal where natural-language intents are trans- formed into executable workflows. Plaza6G supports four experimentation modalities under unified orchestration:(i) Simulationemploys discrete-event simulators (ns-3[5],Komondor[6]) for large-scale protocol evaluation;(i) Emulationinstantiates virtualized protocol stacks (UERANSIMor srsRAN UE/gNB) for rapid multi- configuration benchmarking;(i) In-labintegrates physical equipment (e.g.,Amarisoft Callbox, commercial UEs) within a four-chamber anechoic facility for repeatable OTA validation; and(iv) Outdoorsleverages a dual-site outdoor 5G network (sub-6 GHz, mmWave) for end-to-end trials under realistic conditions. These modalities enable progressive validation from simulation through field deployment within the same framework. B. Infrastructure and Resources Plaza6G infrastructure spans three integrated technological domains supporting all experiment modalities. Thecompute domainprovides GPU-accelerated clusters hosting virtual ma- chines and Kubernetes workloads with support for edge-cloud continuum deployment. Current capacity exceeds 3,000 CPU cores, 30 vGPUs (NVIDIA L40S), and approximately 500 TB of storage, enabling concurrent execution of simulation, em- ulation, and virtualized network function workloads. Thenet- work domainoffers multiple 5G core implementations such as Free5GC,Open5GS, orCumucore, supporting end-to-end net- work slicing and service isolation across all experiment types. Theradio domaincomprises programmable RAN platforms includingAmarisoft Callbox, O-RAN, and srsRAN, alongside both emulated user equipment (UERANSIM,Amarisoft Sim- box) and physical devices (commercial Android smartphones). Controlled OTA testing leverages the four-chamber anechoic facility ensuring repeatable radio propagation conditions for in-lab experiments, while outdoor infrastructure supports field trials as described below. Fig. 2: Plaza6G web portal with the LLM assistant. Fig. 3: Coverage of the Plaza6G outdoor private 5G network at the PMT campus, operating across sub-6 GHz and mmWave bands. The color scale indicates received signal power, from yellow (strong) to dark blue (weak). Plaza6G extends laboratory capabilities through a dual-site outdoor 5G network deployed across rooftop installations at theParc Mediterrani de la Tecnologiacampus. Operating in both sub-6 GHz and mmWave bands, this network sup- ports configuration with open-source or commercial 5G cores, enabling field experimentation under realistic propagation, interference, and mobility conditions. In particular, the two outdoor radio sites can also be re-configured so that they belong to two independent 5G networks to test, e.g., roaming scenarios. Fig. 3 presents measured coverage, demonstrating stable connectivity across the campus area served by the rooftop antenna deployment. C. Positioning Against Existing Testbeds Large-scale European initiatives including 5GENESIS [7], 5G-VINNI [8], VITAL-5G [9], and 5G-EVE [10] have estab- lished comprehensive validation infrastructures for 5G tech- nologies. Recent efforts such as 6G-SANDBOX [11] target early 6G experimentation, whileJoiner[12] federates 11 UK testbeds with automation capabilities, and the IEEE 5G/6G In- novation Testbed pursues end-to-end 3GPP-compliant CI/CD integration (currently under development). However, these platforms predominantly rely on predefined workflows requir- ing manual configuration, constraining both accessibility and automation potential. Plaza6Gdifferentiates itself through three key innova- tions: (i) unified orchestration spanning simulation, emulation, controlled in-lab, and field experiment modalities within a single platform, (i) AI-assisted zero-touch experimentation accessible to users without domain-specific scripting expertise, and (i) native support for theExperiment-as-Code(ExaC) paradigm [2], [3], [13], enabling fully reproducible, version- controlled experiment definitions deployable via natural lan- guage or programmatic APIs. This combination of elements positions Plaza6G as a next-generation platform bridging the gap between cloud elasticity and realistic wireless experimen- tation across the complete validation spectrum. I. DEMONSTRATIONUSECASES To validate Plaza6Gs operational capabilities, two represen- tative scenarios are presented: (i) automated API-driven vali- dation integrated with external CI/CD pipelines, and (i) con- trolled OTA experimentation with physical 5G equipment. These use cases highlight Plaza6Gs ability to embed network acceptance testing within software workflows while also sup- porting reproducible OTA and field experiments across sub- 6 GHz and mmWave environments. A. Emulated Use Case: CI/CD Network Acceptance via API This scenario demonstrates Plaza6G as an automated valida- tion stage within continuous integration workflows. A CI/CD pipeline triggers experimentation via a REST API call ex- pressed in natural language. For instance, to validate applica- tion performance across different 5G core implementations, a user can submit: "user_request":"Deploy<my_app>across three5Gcores(Open5GS,Free5GC,OAI-CN) andverify<my_kpi>exceedsthresholdfor testapproval." For the sake of simplicity, in this demonstration,my_app is instantiated asiperf3andmy_kpiis mean throughput with an acceptance test threshold of 50 Mbps. The LLM backend interprets the request, identifies the application under test, target cores, and success criteria, then generates an experiment plan. The system returns one of three responses (approved, clarification required, ordenied) based on resource availability and policy constraints. CI/CD pipelines may proceed automat- ically upon approval or incorporate human-in-the-loop review, depending on organizational trust policies. Each experiment instantiates a complete emulated 5G sys- tem comprisingUERANSIM-based UE and gNB connected to one of the three 5G core implementations. A dedicated Data Network Name (DNN) virtual machine hosts the ap- plication server (iperf3 -s), while the emulated UE exe- cutesiperf3 -cfor 2 minutes, generating TCP and UDP traffic for benchmarking. The ExaS scheduler manages the complete lifecycle (resource allocation, UE/gNB/5GC/DNN instantiation, measurement collection, and teardown) through an asynchronous scheduler. All three experiments execute concurrently on isolated compute pools, with comprehensive telemetry such as throughput, latency, and CPU utilization automatically archived. 5G core and traffic protocol F5GC-TCP O5GS-TCPOAI-TCPF5GC-UDP O5GS-UDPOAI-UDP Throughput (Mbps) 0 50 100 150 200 250 300 350 400 DL UL Fig. 4: Throughput performance comparison for both UDP and TCP traffic across three 5G core implementations executed concurrently via Plaza6G API. Tests duration of 120 seconds, with throughput logged every second. Figure 4 depicts representative throughput distributions across the three 5G cores. All measured mean values exceed the specified 50 Mbps threshold, demonstrating consistent per- formance for user’s app under test. From a DevOps perspec- tive, this enables “network acceptance testing" where CI/CD pipelines advance to staging or production only after minimum KPI thresholds are satisfied. Measured setup time remains below ten minutes per experiment, reducing configuration effort by over an order of magnitude compared to manual procedures. B. In-lab use case: Over-the-Air Controlled Experiment The second scenario illustrates Plaza6Gs capability to au- tomate the provisioning of complex physical experimenta- tion environments while deliberately supporting human-in- the-loop experimentation. Unlike the CI/CD use case we discussed before, which targets fully automated and script- driven validation, this scenario is designed for exploratory and interactive experimentation, where users manually access net- work elements and conduct measurements without predefined execution scripts. The experiment provisioning phase is fully automated. Using the Plaza6G web portal and its LLM assistant, the user selects an experiment template that deploys aFree5GC core, anAmarisoft CallboxgNB, and a commercial Android smartphone acting as UE. Templates expose a curated set of commonly used 5G parameters (e.g., 100 MHz bandwidth, MIMO) to simplify initial configuration, while allowing users to override or refine parameters either manually or through the LLM assistant. The gNB and UE are placed in separate chambers of the four-chamber anechoic facility, enabling programmable control of path loss, attenuation profiles, and interference conditions. Figure 5 shows the physical OTA experiment setup. The scheduler automatically provisions compute, core, and radio resources and establishes end-to-end connectivity, after which the environment is handed over to the user for interactive experimentation. Once the setup is complete, the user remotely accesses the UE viaVysorto manually execute application-level tests, Fig. 5: Anechoic chamber with an Android UE and an Amarisoft Callbox for controlled OTA experimentation. install software, or explore network behavior under controlled radio conditions. By progressively adjusting inter-chamber attenuation, users can interactively study the impact of channel degradation on throughput, latency, and perceived quality of experience. This mode of operation supports exploratory stud- ies such as adaptive streaming behavior, application robustness to radio impairments, and edgecloud service performance under varying link quality, without constraining the experiment to predefined workflows. Throughout the session, the LLM assistant can provide contextual information on current signal conditions, active configurations, and runtime statistics in natural language, assisting users in interpreting observations while retaining full control over experiment execution. IV. DISCUSSION ANDOUTLOOK A. Reproducibility and Workflow Traceability All Plaza6G experiments follow a unified orchestration workflow in which every action, from initial resource pro- visioning to final teardown, is logged as a machine-readable descriptor capturing software versions, network topology, hardware identifiers, and configuration parameters. These de- scriptors are archived in a searchable experiment repository that supports version control and longitudinal performance tracking across multiple runs. In addition to local traceability, Plaza6G maintains a con- sistent naming and indexing scheme that links experiment descriptors, orchestration logs, and collected metrics. This structured organization enhances repeatability while allowing users to audit the full lifecycle of an experiment, from creation to completion, through a unified web interface. To foster transparency and community reproducibility, the detailed pro- cedure for replicating the emulated use case presented in Section I-A has been published on theprotocols.ioplatform. This companion protocol demonstrates the same workflow executed via the Plaza6G web portal rather than the API, providing additional insight into the graphical interface and user interaction process. 1 B. Conclusions and future work The demonstrations in Section I validatePlaza6Gas a practical realization of the ExaS paradigm, unifying radio, core, and compute infrastructure under automated orchestra- tion. LLM-assisted interfaces and programmable APIs reduce the expertise required for wireless experimentation, enabling reproducible, concurrent trials with setup times below ten minutes. By coupling data-center automation with xG infras- tructure, Plaza6G turns network experimentation into an on- demand cloud service for developers, researchers, and vendors. Future work will extend Plaza6G along several directions. (1) Policy-aware orchestration will optimize scheduling for cost, energy, and radio resource usage. (2) Safety and vali- dation mechanisms will verify LLM-generated actions to en- sure correctness and reproducibility. (3) Planned LoRA-based fine-tuning will incrementally refine the LLM using selected orchestration logs and user dialogues, improving technical ac- curacy without full-model retraining. (4) Federated operation with external testbeds is envisioned to enable geographically distributed, multi-domain experiments; integration with ETSI OpenSlice [14] is under study to align Plaza6G with emerging open orchestration standards. REFERENCES [1]S. Barrachina-Muñoz, H. Bleda, M. Requena, S. Vía, M. Payaró, and J. Mangues-Bafalluy, “Experiment-as-a-Service in the Pipeline: Empowering CI/CD with xG Acceptance Testing,” inWireless On- Demand Netw. Syst. and Serv. Conf. (WONS). IEEE, 2025, p. 1–4. [2]T. W. Edgar and T. R. Rice, “Experiment as a service,” in2017 IEEE Int. Symp. on Tech. for Homeland Security (HST). IEEE, 2017. [3]M. Bonifaceet al., “BonFIRE: A Multi-Cloud Experimentation-as-a- Service Ecosystem,” inBuilding the Future Internet through FIRE. River Publishers, 2022, p. 243–266. [4]E. J. Hu, Y. Shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, W. Chenet al., “LoRA: Low-rank adaptation of large language models.” ICLR, vol. 1, no. 2, p. 3, 2022. [5]A. Larrañagaet al., “An open-source implementation and validation of 5G NR configured grant for URLLC in ns-3 5G LENA: A scheduling case study in industry 4.0 scenarios,”Journal of Network and Computer Applications, vol. 215, p. 103638, 2023. [6]S. Barrachina-Muñoz, F. Wilhelmi, I. Selinis, and B. Bellalta, “Komon- dor: A wireless network simulator for next-generation high-density WLANs,” in2019 Wireless Days (WD). IEEE, 2019, p. 1–8. [7]G. Xylouriset al., “Experimentation and 5G KPI measurements in the 5GENESIS platforms,” inProceedings of the 1st Workshop on 5G Measurements, Modeling, and Use Cases, 2021, p. 1–7. [8]A. J. Gonzalez, M. Xie, P. H. Lehne, and P. Grønsund, “Achieving high throughput and low latency with 5G: A real implementation experience,” IEEE Communications Magazine, vol. 59, no. 10, p. 84–90, 2021. [9]V. Charpentieret al., “Utilizing the VITAL-5G platform to advance 5G standalone integration with vertical industries,”EURASIP Journal on Wireless Comm. and Networking, vol. 2025, no. 1, p. 27, 2025. [10]M. Guptaet al., “The 5G EVE end-to-end 5G facility for extensive trials,” in2019 ICC workshops. IEEE, 2019, p. 1–5. [11]P. Merino-Gomez, B. Garcia, C. Andreo, D. Artuñedo, and J. Macias, “On-demand Trial Networks over 6G-SANDBOX infrastructure,” in 2024 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit). IEEE, 2024, p. 1021–1026. [12]S. Saunders, O. Dilley, and D. Simeonidou, “JOINER-NSF: UKs national facility for spectrum access innovation,” inIEEE Intl. Symp. on Dynamic Spectrum Access Netw. (DySPAN). IEEE, 2025, p. 77–78. 1 The complete experimental protocol, including setup, execution, and data collection steps, is available at https://w.protocols.io/view/ plaza6g-experiment-reproduction-protocol-use-case-a-dm6gpm6pjgzp/v1. [13]L. Aguilaret al., “Experiments as Code and its application to VR studies in human-building interaction,”Scientific Reports (Nature Portfolio), vol. 14, no. 1, p. 9883, 2024. [14]ETSI, “ETSI OpenSlice: Open Source Platform for Service Orchestra- tion and Management,” https://osl.etsi.org/, accessed: Oct. 24, 2025.