Environmental monitoring is essential for smart agriculture, renewable energy assessment, and climate-aware farm management. However, deploying autonomous sensing platforms in rural environments remains challenging due to energy constraints, communication reliability, and real-time processing requirements. This paper presents a modular, solar-powered environmental monitoring platform integrating LTE-M communication and TinyML-enabled edge sensing. The proposed system adopts a dual-microcontroller architecture, combining an Arduino Nano 33 BLE for real-time sensor acquisition and edge processing with an Arduino MKR NB 1500 dedicated to low-power wide-area communication. The platform integrates temperature, humidity, atmospheric pressure, rainfall, wind, and light sensors within a scalable framework. Two monitoring stations were deployed in rural regions of Romania to evaluate communication robustness, sensing stability, and energy autonomy. Field results demonstrate reliable LTE-M connectivity (4,306 RSSI samples; mean -75.51 dBm) and strong agreement with a regional weather station, with mean deviations of \( -0.71^{\circ} \)C (temperature), \( 4.98\% \)(humidity), and a stable pressure offset of -9.58 hPa attributable to altitude differences. Despite a total system cost of €315, the platform achieves measurement performance comparable to professional meteorological stations while maintaining long-term solar-powered operation. The proposed architecture provides a scalable and cost-effective solution for distributed smart agriculture and environmental monitoring applications.

Environmental monitoring is essential for smart agriculture, renewable energy assessment, and climate-aware farm management. However, deploying autonomous sensing platforms in rural environments remains challenging because of energy constraints, communication reliability, and real-time processing requirements. This paper presents a modular, solar-powered environmental monitoring platform integrating LTE-M communication and TinyML-enabled edge sensing. The proposed system adopts a dual-microcontroller architecture that combines an Arduino Nano 33 BLE for real-time sensor acquisition and edge processing with an Arduino MKR NB 1500 dedicated to low-power wide-area communication. The platform integrates temperature, humidity, atmospheric pressure, rainfall, wind, and light sensors within a scalable framework. Two monitoring stations were deployed in rural regions of Romania to evaluate communication robustness, sensing stability, and energy autonomy. Field results demonstrated reliable LTE-M connectivity (4306 received signal strength indicator [RSSI] samples; mean $-75.51$ dBm) and strong agreement with a regional weather station, with mean deviations of −0.71 °C (temperature), $4.98\%$ (humidity), and a stable pressure offset of $-9.58$ hPa attributable to altitude differences. Despite a total system cost of €315, the platform achieved measurement performance comparable to that of professional meteorological stations while maintaining long-term solar-powered operation. The proposed architecture provides a scalable and cost-effective solution for distributed smart agriculture and environmental monitoring applications.

The evolution from fifth generation (5G) to sixth generation (6G) networks demands a paradigm shift from AI-assisted functionalities to AI-native orchestration, where intelligence is intrinsic to the radio access network (RAN). This work introduces two AI-based enablers for PHY-layer awareness: (i) a waveform classifier that distinguishes orthogonal frequency-division multiplexing (OFDM) and orthogonal time frequency space (OTFS) signals directly from in-phase/quadrature (IQ) samples, and (ii) a numerology detector that estimates subcarrier spacing, fast Fourier transform (FFT) size, slot duration, and cyclic prefix type without relying on higher-layer signaling. Experimental evaluations demonstrate high accuracy, with waveform classification achieving 99.5% accuracy and numerology detection exceeding 99% for most parameters, enabling robust joint inference of waveform and numerology features. The obtained results confirm the feasibility of AI-native spectrum awareness, paving the way toward self-optimizing, context-aware, and adaptive 6G wireless systems.

Open-source and commercial fifth-generation (5G) deployments are difficult to compare because they are built for different goals and reported under different conditions, which slows down validation and technology transfer from research to practice. This study explores the deployment and evaluation of two 5G Standalone (SA) disaggregated Radio Access Network (RAN) systems, using open-source research RAN, commercial RAN, and Software-Defined Radio (SDR) hardware. The first testbed is a SDR-based prototype, containing a Universal Software Radio Peripheral (USRP) B210 device, using Software Radio System RAN (srsRAN) as the RAN. The commercial-based testbed contains a Benetel RAN550 Radio Unit (RU), connected via an optical fiber to a Commercial Off-the-Shelf (COTS) server acting as the Distributed Unit (DU) and Centralized Unit (CU) using the Accelleran virtualized Baseband Unit (vBBU) platform. The Core Network (CN) is implemented using the open-source Open5GS in both testbeds. To evaluate the network’s functionality, throughput and latency are tracked using a Motorola Edge 50 Pro mobile terminal. The experimental results are analyzed and compared with representative performance metrics reported in the literature to place the measurements in a broader research context. This study further assesses trade-offs related to cost, portability, and scalability by comparing SDR-based research prototypes with commercial deployments.

The growth of 5G applications makes it difficult to meet diverse performance requirements while using network resources efficiently. Fixed network slicing methods cannot adapt to changing traffic, leading to higher latency, lower throughput, and increased packet loss. This paper presents an experimental validation of adaptive slicing on a 3GPP Release 16-compliant 5G Standalone testbed combining Open5GS, srsRAN, software-defined radios, and commercial devices. The framework classifies traffic demand into low, medium, or high levels and adjusts slice resources in real time. Measurements show approximately 15% lower latency, higher throughput, and significantly reduced packet loss compared with static slicing. Unlike simulation-based studies or deep learning approaches requiring specialized hardware, the proposed setup achieves real-time adaptation on only CPU resources, demonstrating that practical adaptive slicing can be realized with open-source platforms and standard 5G equipment.

The transition from early non-standalone 5G deployments to 5G Standalone and, more recently, 5G-Advanced has turned mobile networks into flexible, programmable infrastructures capable of supporting private, industrial, and research-oriented deployments for the development of beyond-5G applications and architectures. Evaluating these networks’ capabilities, however, remains challenging because commercial platforms often provide limited access to internal interfaces, radio parameters, and network measurements. This paper presents an open-source private 5G SA testbed for beyond-5G application validations built using Open5GS, srsRAN, Ettus USRP N310 software-defined radio, programmable SIM cards, and commercial 5G customer-premise equipment. The platform is deployed in a semi-anechoic chamber. End-to-end operation is validated through subscriber registration, authentication, PDU session establishment, and external data connectivity. The performance of the implemented 5G network is evaluated using throughput, block error rate, modulation and coding scheme, and gNB trace logs. Unlike previous open-source 5G testbeds that primarily use RF waveguides, individual network components, or a limited set of radio configurations, the proposed platform combines COTS SIM-based UE operation with a controlled over-the-air evaluation of FDD/TDD and multiple antenna configurations and correlates application-level throughput with internal gNB radio metrics. For FDD downlink operation, the average throughput increased by approximately 74% from 1 × 1 to 2 × 2 and by a further 57% from 2 × 2 to 4 × 4, although the additional peak-throughput gain from 2 × 2 to 4 × 4 remained limited. The platform provides a reproducible environment for validating beyond-5G mechanisms, comparing network configurations, and studying the behavior of future open-source 5G SA systems under controlled conditions.