Artificial Intelligence (AI) is being incorporated in several optimization, scheduling, orchestration as well as in native communication network functions. This paradigm shift results in increased energy consumption, however, quantifying the end-to-end energy consumption of adding intelligence to communication systems remains an open challenge since conventional energy consumption metrics focus on either communication, computation infrastructure, or model development. To address this, we propose a new metric, the Energy Cost of AI Lifecycle (eCAL) of an AI model in a system. eCAL captures the energy consumption throughout the development, deployment and utilization of an AI-model providing intelligence in a communication network by (i) analyzing the complexity of data collection and manipulation in individual components and (ii) deriving overall and per-bit energy consumption. We show that as a trained AI model is used more frequently for inference, its energy cost per inference decreases, since the fixed training energy is amortized over a growing number of inferences. For a simple case study we show that eCAL for 100 inferences is 2.73 times higher than for 1000 inferences. Additionally, we have developed a modular and extendable opensource simulation tool to enable researchers, practitioners, and engineers to calculate the end-to-end energy cost with various configurations and across various systems, ensuring adaptability to diverse use cases.

Time‐series classification is a relevant step supporting decision‐making processes in various domains, and deep neural models have shown promising performance in this respect. Despite significant advancements in deep learning, the theoretical understanding of how and why complex architectures function remains limited, prompting the need for more interpretable models. Recently, the Kolmogorov–Arnold Networks (KANs) have been proposed as a more interpretable alternative to deep learning. While KAN‐related research is significantly rising, to date, the study of KAN architectures for time‐series classification has been limited. In this paper, we aim to conduct a comprehensive and robust exploration of the KAN architecture for time‐series classification utilizing 117 datasets from UCR benchmark archive, from multiple different domains. More specifically, we investigate (a) the transferability of reference architectures designed for regression to classification tasks, (b) the hyperparameter and implementation configurations for an architecture that best generalizes across 117 datasets, (c) the associated complexity trade‐offs, and (d) KANs interpretability. Our results demonstrate that (1) the Efficient KAN outperforms MLPs in both performance and training times, showcasing its suitability for classification tasks. (2) Efficient KAN exhibits greater stability than the original KAN across grid sizes, depths, and layer configurations, especially when lower learning rates are employed. (3) KAN achieves competitive accuracy compared to state‐of‐the‐art models such as HIVE‐COTE2 and InceptionTime, while maintaining smaller architectures and faster training times, highlighting its favorable balance of performance and transparency. (4) The interpretability of the KAN model, as confirmed by SHAP analysis, reinforces its capacity for transparent decision‐making.

Driven by various academic, standardization and regulatory initiatives, recent research on spectrum resource utilisation has focused also on technology and transmission classification using various deep learning (DL) architectures. However, especially in unlicensed bands it is often hard to obtain labelled data of sufficient quality for training DL for all transmissions that may occur. Therefore in this paper we investigate clustering techniques that require no labelled data or prior knowledge on continuous spectrum sensing sweeps over a 200 kHz wide band in the unlicensed European 868 MHz frequency band. Using several clusterability tests we show that the sweeps can be clustered, however the number of clusters is not clear. By analyzing the sweeps with three state-of-the-art techniques, K-Means, Agglomerative Hierarchical Clustering, and Hierarchical Density-Based Spatial Clustering (HDBSCAN) 9-10 clusters are discovered. The quantitative evaluation shows that HDBSCAN outperforms the other two and the qualitative analysis shows that HDBSCAN seems to be able to better discriminate between the same technology transmitting at/from different power levels/distance, however it has a relatively poorer class balance compared to K-Means and tends to group more transmissions than needed in the majority no transmission cluster.

Time series classification is an important task in many fields. In intrusive and non-intrusive load monitoring (N)ILM, time series data are obtained from power measurements of electrical appliances that are not known in advance, therefore extracting the type of appliance from the data is a relevant problem in smart grids. We propose a transformation that encodes a time series into an image that can be effectively recognised by well known image classification algorithms. The transformation is based on plotting the time series into a matrix and filling the area under it, producing a more pronounced representation of its shape. We perform an extensive evaluation on 1 synthetic and 4 measured datasets. Our experiments on synthetic and mixed measured data yielded F1 scores of 99.2% and 85.9%, respectively, and outperformed the state-of-the-art on three out of four tested datasets. Additionally, we conclude that our method tends to work better on longer time series segments, as the resulting images contain more distinguishing features.

In recent years, much work has been done on processing of wireless spectrum data involving machine learning techniques in domain-related problems for cognitive radio networks, such as anomaly detection, modulation classification, technology classification and device fingerprinting. Most of the solutions are based on labeled data, created in a controlled manner and processed with supervised learning approaches. However, spectrum data measured in real-world environment is highly nondeterministic, making its labeling a laborious and expensive process, requiring domain expertise, thus being one of the main drawbacks of using supervised learning approaches in this domain. In this paper, we investigate the utilization of self-supervised learning (SSL) for exploring spectrum activities in a real-world unlabeled data. In particular, we assess the performance of SSL models, based on the reference DeepCluster architecture. We carefully consider the current state-of-the-art feature extractors, taking into account the performance and complexity trade-offs. Our findings demonstrate that SSL models achieve superior performance regarding the feature quality and clustering performance compared to baseline feature learning approaches. With SSL models we achieve significant reduction of the feature vectors size by two orders of magnitude, while improving the performance by a factor ranging from 2 to 2.5 across the evaluation metrics, supported by visual assessment. Furthermore, we showcase how adapting the reference SSL architecture to domain-specific data is followed by a substantial reduction in model complexity up to one order of magnitude, without compromising, and in some cases, even improving the clustering performance.

Today, there are billions of connected IoT devices and their number continues to grow as they contribute to the digitalization of infrastructures. However, the deployment process of these smart wireless devices when delivered to customer premises is slow and error prone as each of them needs to be provisioned with authentication credentials to access the corporate network. In this paper, we propose HANNA, a human-friendly provisioning and configuration framework for smart devices, that extends the zero-touch paradigm to large IoT deployments by introducing voice assisted configuration in combination with large scale ad-hoc communications to overcome the initial installation effort of IoT deployments. The most prominent role in HANNA is played by the assisting device, which includes a voice assistant capable of correctly understanding a minimum number of keywords required for initial provisioning and configuration of the devices. The device’s role is to interact with the user and ensure that all provisioning details are received. These are then converted into appropriate machine instructions for further use by the mass provisioning mechanism. We provide an example prototype implementation of HANNA and evaluate the performance of the assisting device in the human-to-machine communication phase and the performance of the selected communication technique in the machine-to-machine communication phase. Our results show the potential of existing speech-to-text engines for this application area and also reveal shortcomings with respect to the robustness of the engines in office-like working environments as well as with respect to user’s gender and language proficiency level. Additionally we show that the proposed machine-to-machine provisioning approach is always faster compared to manual provisioning for cases with more than ten devices.

Location based services, already popular with end users, are now inevitably becoming part of new wireless infrastructures and emerging business processes. The increasingly popular Deep Learning (DL) artificial intelligence methods perform very well in wireless fingerprinting localization based on extensive indoor radio measurement data. However, with the increasing complexity these methods become computationally very intensive and energy hungry, both for their training and subsequent operation. Considering only mobile users, estimated to exceed 7.4 billion by the end of 2025, and assuming that the networks serving these users will need to perform only one localization per user per hour on average, the machine learning models used for the calculation would need to perform 65×1012predictions per year. Add to this equation tens of billions of other connected devices and applications that rely heavily on more frequent location updates, and it becomes apparent that localization will contribute significantly to carbon emissions unless more energy-efficient models are developed and used. This motivated our work on a new DL-based architecture for indoor localization that is more energy efficient compared to related state-of-the-art approaches while showing only marginal performance degradation. A detailed performance evaluation shows that the proposed model produces only 58% of the carbon footprint while maintaining 98.7% of the overall performance compared to state of the art model external to our group. Additionally, we elaborate on a methodology to calculate the complexity of the DL model and thus the CO2footprint during its training and operation.

The Internet of Things (IoT) is being widely adopted in today's society, interconnecting smart embedded devices that are being deployed for indoor and outdoor environments, such as homes, factories and hospitals. Along with the growth in the development and implementation of these IoT devices, their simple and rapid deployment, initial configuration and out-of-the-box operational provisioning are becoming prominent challenges to be circumvented. Considering a large number of heterogeneous devices to be deployed within next generation IoT networks, the amount of time needed for manual provisioning of these IoT devices can significantly delay the deployment and manual provisioning may introduce human-induced failures and errors. By incorporating zero-touch provisioning (ZTP), multiple heterogeneous devices can be provisioned with less effort and without human intervention. In this paper, we propose software-enabled access point (Soft-AP)- and Bluetooth-based ZTP solutions relying only on a single mediator device and evaluate their performances using LOG-A-TEC testbed against manual provisioning in terms of the time required for provisioning (time-to-provision, TTP). We demonstrate that on average, Soft-AP- and Bluetooth-based ZTP solutions outperform manual provisioning with about 154% and 313% when compared to the expert provisioning, and with about 434% and 880% when compared to the non-expert provisioning in terms of TTP performances, respectively.

Ensuring a reliable communication in wireless networks strictly depends on the effective estimation of the link quality, which is particularly challenging when propagation environment for radio signals significantly varies. In such environments, intelligent algorithms that can provide robust, resilient and adaptive links are being investigated to complement traditional algorithms in maintaining a reliable communication. In this respect, the data-driven link quality estimation (LQE) using machine learning (ML) algorithms is one of the most promising approaches. In this paper, we provide a quantitative evaluation of design decisions taken at each step involved in developing a ML-based wireless LQE on a selected, publicly available dataset. Our study shows that, re-sampling to achieve training class balance and feature engineering have a larger impact on the final performance of the LQE than the selection of the ML method on the selected data.

In this paper we propose an architecture for fully-reconfigurable, plug-and-play wireless sensor network testbed. The proposed architecture is able to reconfigure and support easy experimentation and testing of standard protocol stacks (i.e. uIPv4 and uIPv6) as well as non-standardized clean-slate protocol stacks (e.g. configured using RIME). The parameters of the protocol stacks can be remotely reconfigured through an easy to use RESTful API. Additionally, we are able to fully reconfigure clean-slate protocol stacks at run-time. The architecture enables easy set-up of the network - plug - by using a protocol that automatically sets up a multi-hop network (i.e. RPL protocol) and it enables reconfiguration and experimentation - play - by using a simple, RESTful interaction with each node individually. The reference implementation of the architecture uses a dual-stack Contiki OS with the ProtoStack tool for dynamic composition of services.

TV White Spaces (TVWS) technology allows wireless devices to opportunistically use locally-available TV channels enabled by a geolocation database. The UK regulator Ofcom has initiated a pilot of TVWS technology in the UK. This paper concerns a large- scale series of trials under that pilot. The purposes are to test aspects of white space technology, including the white space device and geolocation database interactions, the validity of the channel availability/powers calculations by the database and associated interference effects on primary services, and the performances of the white space devices, among others. An additional key purpose is to perform research investigations such as on aggregation of TVWS resources with conventional resources and also aggregation solely within TVWS, secondary coexistence issues and means to mitigate such issues, and primary coexistence issues under challenging deployment geometries, among others. This paper provides an update on the trials, giving an overview of their objectives and characteristics, some aspects that have been covered, and some early results and observations.

We propose a framework for dynamic composition of communication services that is well suited for facilitating research and prototyping on real experimental infrastructures of remotely configurable embedded devices. By using the concept of composability, our framework supports modular component development for various networking functions, thereby promoting code reuse. The framework consists of four components: the physical testbed, the module library, the declarative language, and the workbench. Its reference implementation, ProtoStack, developed using semantic web technologies, supports remote experimentation on sensor platform-based infrastructure and is thus well suited also for experimenters who do not possess their own physical experimentation infrastructure. We illustrate how ProtoStack supports research in service-oriented networks and cognitive networking. The cost of increased flexibility and prototyping speed of the protocol stack is paid in terms of increased memory footprint, processing speed, and energy consumption. Compared to the most related noncomposable approach, the CRime library used by ProtoStack has a 16--17% larger footprint, takes 2.4 times longer to execute an open-send-recv-close sequence, and consumes 1.6% more power in doing so. Even though with ProtoStack more resources are consumed by the node, the tradeoff in terms of prototyping speed pays off.

In this paper we propose a methodology for the experimental evaluation of a simple yet efficient power allocation game on a real-world outdoor experimental testbed. We adapt the existing theoretical framework and the ProActive Power Update (PAPU) algorithm to suit the constraints imposed by the LOG-a-TEC low-cost reconfigurable testbed. The resulting framework is implemented and evaluated in the ISM 2.4 GHz band. We study the effects of the empirical parameter estimation on the best response and players' strategies which represent the Nash equilibra. Our results show that for a certain cost range, the system can reach Nash equilibria. The equilibria and the convergence time are strongly influenced by each player's cost but also by the channel gains.

Since 1990s, the investigations of aerospace communication segment have not only been concerned with satellites, but increasingly with lower altitude repeaters flying in the stratosphere. They are the so-called high-altitude platforms (HAPs) with important advantages with respect to satellites in terms of reduced cost of implementation, deployment, and launch. However, HAPs are characterized by a reduced coverage, as compared with satellites. Nevertheless, in recent literature, HAPs are not regarded as competitors of the satellite technology. On the contrary, the emphasis is on the effective and seamless integration among heterogeneous aerospace segments (GEO, LEO, and HAP) and aerospace segments with terrestrial wireless networks in order to globally extend the broadband wireless connectivity. This paper is focused on the role of HAPs in providing global connectivity in future communication systems and services. Potentialities, enabling technologies, and challenges are presented from the perspective of the integrated terrestrial/HAPs/satellite communications infrastructure.

The efficiency of wireless communication systems largely depends on proper understanding of propagation impairments and the design of suitable countermeasures, taking into account physical causes and time-scales of propagation phenomena. The primary focus of this paper is the link between High Altitude Platform (HAP) and a collective mobile terminal onboard high speed train. The paper characterizes the temporal behavior of the propagation channel on this link by means of first- and second-order statistics, presents a QoS framework based on IP architecture, and discusses potential propagation impairment countermeasures from the perspective of their usage in the provision of different services.

Multiple-input multiple-output (MIMO) technology, which makes use of the spatial dimension by utilising multiple antennas at the transmitter and receiver, has proved an efficient solution for providing higher data throughput and/or link reliability in wireless systems. In this study, the authors investigate a virtual MIMO (V-MIMO) technique, based on a constellation of multiple high-altitude platforms (HAPs), providing broadband wireless access to high-speed trains under predominantly line-of-sight (LOS) propagation conditions. They analyse the performance of transmit diversity based on space–time block coding (STBC), in particular Alamouti and extended Alamouti schemes, using fixed wide-lobe receive antennas, and compare it to the reference receive diversity scheme based on best HAP selection that requires highly directional and steerable antennas. Simulation results for different diversity schemes are based on the calculation of carrier to interference-plus-noise ratio (CINR) along representative railway lines in a realistic terrain configuration. The CINR levels obtained are mapped onto transmission modes specified by standards developed for two wireless systems operating at distinct frequency bands, the DVB-S2 assumed for operation in mm-wave bands and the IEEE 802.16e (mobile WiMAX) for operation at 3.5 GHz. Simulation results show that the use of transmit diversity schemes in a multiple HAP constellation decreases the link outage and also increases the average spectral efficiency, but requires a marked increase in transmit power, especially for the system operating in mm-wave bands.

Combining some of the best terrestrial and satellite systems' characteristics, high altitude platforms (HAPs) have recently emerged as an alternative solution for the provision of broadband services. Characterised by challenging propagation conditions in the allocated frequency bands, they require efficient utilisation of radio interface in order to make best use of the available spectrum. This paper analyses possible utilisation of DVB-S2 standard on HAPs, focusing on the performance of its adaptive coding and modulation (ACM) procedures as a mean of maximizing the link reliability and throughput. Two distinct operating scenarios are addressed, one assuming static channel conditions with the applied rain fading and the other representing mobile channel conditions along a representative railway track We show that by considering only a subset of transmission modes (MODCODs) defined by the DVB-S2 standard, the system could be optimized in terms of achievable spectral efficiency as well as in terms of implementation complexity. A procedure for optimal MODCOD subset selection is proposed, taking into account the predefined switching thresholds and round-trip time delay.

Provision of mobile broadband wireless access, for instance via high altitude platforms (HAPs) to the passengers on a high-speed train, requires the development of efficient and reliable radio interface, which has to adapt to the variation of propagation channel conditions in order to optimise the utilisation of radio resources. In this paper we focus on the implementation aspects and performance analysis of adaptive coding and modulation scheme based on the IEEE 802.16 standard. In order to maximize the link reliability in a fading environment we propose switching between the transmission schemes assisted by the information on the corrected bytes of the previous frames obtained from the Reed-Solomon decoder, thus increasing the throughput while retaining the targeted bit-error-rate (BER). To adequately take into account the real implementation aspects, the selected procedures were implemented on a digital signal processing (DSP) board and tested on a HAP propagation channel model. The performance evaluation results, given in terms of spectral efficiency and the Reed-Solomon decoder state, confirm the adaptability of the implemented switching scenarios to the variation of the HAP propagation channel attenuation.

Next-generation satellite networks are expected to provide a variety of applications with diverse performance requirements, which will call for the development of adaptive routing procedures supporting different levels of services. In this paper, we propose traffic class dependent (TCD) routing, which has the potential to differentiate between traffic classes using different optimization criteria in route calculation. The performance of TCD routing is evaluated for different traffic scenarios using an empirical traffic source model derived from the real backbone Internet traffic trace and compared with results obtained with equivalent Poisson traffic as a reference point. In addition, TCD routing is compared with a simple single service routing procedure, which does not make any distinction between traffic classes. Performance analysis, in terms of average packet delay, normalized data throughput, and normalized link load, reveals improved routing resulting from traffic class differentiation, regardless of the traffic scenario considered. The performance measures based of aggregate traffic flow show no significant difference between routing of empirical and equivalent Poisson traffic.

Delivery of IP services is becoming increasingly important for wireless access networks, HeliNet being their representative based on high altitude platforms. Accordingly, new problems arise regarding quality of service (QoS) or class of service (CoS) provision and resource allocation. Traffic QoS/CoS should be managed on multiple communication layers such as application, network and radio interface layer. In the network layer, IP QoS models can offer various levels of QoS to the application layer, while the radio interface should provide mechanisms which can guarantee the required QoS level to IP. Mapping of QoS/CoS parameters between the network layer and radio interface can be performed in a suitable convergence sublayer. The paper addresses IP transmission over the HeliNet radio interface. Using a simulation model, it is shown that the introduction of scheduling algorithms, as part of the uplink medium access control (MAC) protocol, improves the ability of the radio interface to offer the required QoS/CoS to IP.

This paper addresses traffic class dependent routing in the intersatellite link network of a non-geostationary packet-switched satellite system. Three different traffic classes are considered, each with its particular optimisation criteria. Performance analysis, in terms of average packet delay of particular traffic class and average packet throughput, has been evaluated using specifically developed simulation software to model the ISL network. Four different simulation scenarios were used to investigate the impact of different scheduling and routing policies on the network performances for different network traffic loads.

Regular mesh topologies typical for satellite communication networks comprised of intersatellite links provide high network flexibility and reliability, but due to dynamic changing of traffic load and interorbit link distance variation, adaptive routing is an absolute requirement for optimizing the network utilization. In this article, we address adaptive routing in the intersatellite link (ISL) segment of nongeostationary packet-switched satellite communication systems, focusing on the relative impacts of traffic load and propagation delay on the link cost. We consider four reference traffic flow scenarios with different levels of traffic concentration. he network performance is evaluated in terms of routing performance measures important from both the end user and the network operator perspectives. Using an ISL network simulator, we reveal some intrinsic effects of the selected constellation and effects introduced with different assumptions regarding the traffic model.