The growing complexity of Cyber-Physical Systems (CPS) in industrial and manufacturing environments calls for more sophisticated methods to represent heterogeneous assets and processes. In response, hierarchical Digital Twins (DTs)–virtual representations of physical, taxonomy-based processes–offer transparent, layered modeling of diverse data sources. This layered structure fuels renewed interest in intelligent engines capable of extracting meaningful insights and mapping them within the stratified DT ecosystem. While current Intelligent Digital Twin (I-DT) engines based on Deep Learning are computationally demanding, lightweight alternatives like Reservoir Computing (RC) offer efficient solutions with low training costs and fast inference for modeling causal dynamics. This inherent trade-off between performance and practicality underscores the limitations of evaluating I-DTs on accuracy alone. To address this gap, this work introduces a novel metric, Fidelity , designed to provide a comprehensive evaluation. Unlike traditional approaches, Fidelity also accounts for maintainability and deployability, especially in contexts involving time-varying and hierarchical data dynamics. Extensive experiments on two multimodal datasets demonstrate the competitiveness of our RC-based engine and highlight the value of introducing Fidelity for effectively profiling I-DTs. Specifically, our RC-based engine, identified as optimal through a higher Fidelity score, consumes an order of magnitude less energy and achieves up to 39 % higher accuracy (about 10 % increase on average) compared to both canonical and other RC-based alternatives.

The remarkable success of attention-based models in real-world applications has sparked a crucial question for Reservoir Computing (RC): Can its inherent computational efficiency compete with the high-performance, yet energy-intensive, novel deep learning architectures? Can Deep and modular RC neural networks address state-of-the-art challenges in Computer Vision and Natural Language Processing? In the attempt to consolidate RC capabilities towards more complex tasks, this paper delves into the exploration of a comprehensive RC’s offline-online cycle cost analysis. Our investigation highlights hyperparameters (HPs) optimization as a major bottleneck in RC deployment, particularly for those exploring RC capabilities and those who want to maintain user-level knowledge of the solution. To address this, we introduce an adaptive ϵ-Greedy based search exploration mechanism, significantly streamlining the off-line optimization process while maintaining high accuracy. Furthermore, we enhance existing RC frameworks to support online transfer learning and inference, enabling seamless, fast, and energy-efficient adaptation to real-world environments. By analyzing the impact of optimized HPs on performance, we aim to demonstrate the viability of RC as a powerful and efficient alternative for many practical applications, including those on devices with limited resources. Experimental results proved that our solution is able to reduce the time required for offline HPs optimization by 70%, enabling energy savings of up to 88%. Moreover, in the online scenario, it guarantees similar performance in terms of accuracy while reducing memory usage by 66%.

The increasing demand for efficient resource allocation in mobile networks has catalyzed the exploration of innovative solutions that could enhance the task of real-time cellular traffic prediction. Under these circumstances, federated learning (FL) stands out as a distributed and privacy-preserving solution to foster collaboration among different sites, thus enabling responsive near-the-edge solutions. In this paper, we comprehensively study the potential benefits of FL in telecommunications through a case study on federated traffic forecasting using real-world data from base stations (BSs) in Barcelona (Spain). Our study encompasses relevant aspects within the federated experience, including model aggregation techniques, outlier management, the impact of individual clients, personalized learning, and the integration of exogenous sources of data. The performed evaluation is based on both prediction accuracy and sustainability, thus showcasing the environmental impact of employed FL algorithms in various settings. The findings from our study highlight FL as a promising and robust solution for mobile traffic prediction, emphasizing its twin merits as a privacy-conscious and environmentally sustainable approach, while also demonstrating its capability to overcome data heterogeneity and ensure high-quality predictions, marking a significant stride towards its integration in mobile traffic management systems.

To meet the growing quest for enhanced network capacity, mobile network operators (MNOs) are deploying dense infrastructures of small cells. This, in turn, increases the power consumption of mobile networks, thus impacting the environment. As a result, we have seen a recent trend of powering mobile networks with harvested ambient energy to achieve both environmental and cost benefits. In this paper, we consider a network of virtualized small cells (vSCs) powered by energy harvesters and equipped with rechargeable batteries, which can opportunistically offload baseband (BB) functions to a grid-connected edge server depending on their energy availability. We formulate the corresponding grid energy and traffic drop rate minimization problem, and propose a distributed deep reinforcement learning (DDRL) solution. Coordination among vSCs is enabled via the exchange of battery state information. The evaluation of the network performance in terms of grid energy consumption and traffic drop rate confirms that enabling coordination among the vSCs via knowledge exchange achieves a performance close to the optimal. Numerical results also confirm that the proposed DDRL solution provides higher network performance, better adaptation to the changing environment, and higher cost savings with respect to a tabular multi-agent reinforcement learning (MRL) solution used as a benchmark.

In this paper, we focus on the design of energy self-sustainable mobile networks by enabling intelligent energy management that allows the base stations to mostly operate off-grid by using renewable energy. We propose a centralized control algorithm based on Deep Reinforcement Learning. The single agent is able to learn how to efficiently balance the energy inflow and spending among base stations observing the environment and interacting with it. In particular, we provide a study on the performance achieved by this approach when considering different representations of the environment. Numerical results demonstrate that using a good level of abstraction in the choice of the representation variables may enable a proper mapping of the environment into actions to take, so as to maximize the numerical reward.

In this paper, we discuss a handover management scheme for Next Generation Self-Organized Networks. We propose to extract experience from full protocol stack data, to make smart handover decisions in a multi-cell scenario, where users move and are challenged by deep zones of an outage. Traditional handover schemes have the drawback of taking into account only the signal strength from the serving, and the target cell, before the handover. However, we believe that the expected Quality of Experience (QoE) resulting from the decision of target cell to handover to, should be the driving principle of the handover decision. In particular, we propose two models based on multi-layer many-to-one LSTM architecture, and a multi-layer LSTM AutoEncoder (AE) in conjunction with a MultiLayer Perceptron (MLP) neural network. We show that using experience extracted from data, we can improve the number of users finalizing the download by 18 %, and we can reduce the time to download, with respect to a standard event-based handover benchmark scheme. Moreover, for the sake of generalization, we test the LSTM Autoencoder in a different scenario, where it maintains its performance improvements with a slight degradation, compared to the original scenario.

Flexible functional split in Cloud Radio Access Network (CRAN) is a promising approach to overcome the capacity and latency challenges in the fronthaul. In such architecture, the baseband processing takes place partially at local base stations and the remaining processes are executed at the central cloud. On the other hand, we have seen a recent trend of powering base stations with ambient energy sources to achieve both environmental sustainability and profit advantages. As the base stations become smaller and deployed in densified manner, it is evident that baseband processing power consumption has a huge share in the total base station power consumption breakdown. Given that such base stations are powered by energy harvesting sources, energy availability conditions the decision on where to place each baseband function in the system. This work focuses on applying reinforcement learning techniques, in particular Q-learning and SARSA, for optimal placement of baseband functional split options in virtualized small cells that are solely powered by energy harvesting sources. In addition, a comparison of such online optimization solution with respect to offline performance bounds is provided.

Dense deployment of small base stations (SBSs) will play a crucial role in 5G cellular networks for satisfying the expected huge traffic demand. Dynamic ON/OFF switching of SBSs and the use of renewable energies have recently attracted increasing attention to limit the energy consumption of such a network. In this paper, we present a Layered Learning solution for the radio resource management of dense cellular networks with SBSs powered solely by renewable energy. In the first layer, reinforcement learning agents locally select switch ON/OFF policies of the SBSs according to the energy income and the traffic demand. The second layer relies on an Artificial Neural Network that estimates the network load conditions to implement a centralized controller enforcing local agent decisions. Simulation results prove that the proposed layered framework outperforms both a greedy and a completely distributed solution both in terms of throughput and energy efficiency.

Flexible functional split in Cloud Radio Access Network (CRAN) greatly overcomes fronthaul capacity and latency challenges. In such architecture, part of the baseband processing is done locally and the remaining is done remotely in the central cloud. On the other hand, Energy Harvesting (EH) technologies are increasingly adopted due to sustainability and economic advantages. Power consumption due to baseband processing has a huge share in the total power consumption breakdown of smaller base stations. Given that such base stations are powered by EH, in addition to QoS constraints, energy availability also conditions the decision on where to place each baseband function in the system. This work focuses on determining the performance bounds of an optimal placement of baseband functional split option in virtualized small cells that are solely powered by EH. The work applies Dynamic Programming (DP), in particular, Shortest Path search is used to determine the optimal functional split option considering traffic requirements and available energy budget.

The virtualization of mobile network functions constitutes one of the main blocks for addressing the high flexibility requirements of fifth generation (5G) communication systems. Reconfigurable hotspots are expected to be massively deployed to enable on-demand services and dynamically adapt the network capacity according to traffic requirements. In this paper, we present the extensions and modifications of the long term evolution (LTE) module of the ns-3 simulator (LENA) to include a software defined radio (SDR) physical layer implementation. These extensions combine the native flexibility of the simulator with the SDR features of a real-time prototype. Moreover, the framework was designed to distribute the communication functions across different elements of the network with the possibility of adjusting several transmission parameters as in a network function virtualization (NFV) paradigm. Thanks to an emulated full network protocol stack, the prototype allows the experimentation of novel 5G solutions and the evaluation of relevant key performance indicators (KPIs) from the lower layer protocols up to application level. To this aim, we present the experimental evaluation of the KPIs of energy, latency, throughput and reconfiguration time in relevant scenarios.

In this paper, we propose an optimal direct load control of renewable powered small base stations based on Dynamic Programming. The optimization is represented using Graph Theory and the problem is stated as a Shortest Path problem. The proposed optimal algorithm is able to adapt to the varying conditions of renewable energy sources and traffic demands. We analyze the optimal ON/OFF policies considering different energy and traffic scenarios. Then, we evaluate network performance in terms of system drop rate and grid energy consumption. The obtained results are compared with a greedy approach. This study allows to elaborate on the behavior and performance bounds of the system and gives a guidance for approximated policy search methods.

Future dense mobile networks will imply much higher costs both in access and backhaul. This paper analyzes the effect on wireless mesh backhaul routing performance when energy saving policies are present at the radio access network (RAN). We consider an heterogeneous two-tier network where small cells (SC) with energy harvesting capabilities extend the capacity of the macro base stations (MBS), and can autonomously switch on-off in order to increase the energy efficiency of the network based on a Q-learning (QL) algorithm. Instead of calculating new routes for each SCs activation pattern, we propose to agnostically adapt to the RAN traffic demands using a non-route-based backpressure routing policy for the wireless mesh backhaul to even the network resource usage amongst SCs. We used the ns-3 simulator to integrate the different mobile network segments: RAN, wireless mesh backhaul, and evolved packet core (EPC). Simulation results show an achieved reduction of the %37% of the RAN energy consumption while satisfying traffic demands with an improvement of up to a factor of 10 of delay performance in the backhaul during peak hours.

Packet scheduler at the medium access control (MAC) layer is essential to improve radio resource utilization in the Long Term Evolution (LTE) network. The MAC scheduler allocates resource blocks to user terminals (UEs) according to the priority metric, which varies in different scheduling algorithms. Although there have been many studies on the performance of LTE schedulers at the MAC layer, it is interesting to evaluate the impact of different LTE MAC schedulers on the transport layer, particularly on the transmission control protocol (TCP). In this study, we implement three mainstream LTE MAC schedulers in Network Simulator-3 (NS-3), namely, maximum throughput (MT), blind equal throughput (BET) and proportional fair (PF). Extensive simulations are conducted to examine the different TCP throughput achieved with the frequency domain version and the time domain version of these schedulers in a vehicular environment. The performance difference is attributed to important factors such as the resource allocation granularity, channel-awareness in scheduling, and the number of UEs.

In this paper, we present an open source simulation model for the ns-3 simulator that allows the simulation of LTE handover scenarios, to support the design and evaluation of handover decision algorithms. In addition to the features supported by other publicly available open source LTE simulators, such as mobility, propagation, channel, PHY and MAC modeling, our model provides additional features such as the modeling of the RRC protocol, the MAC random access procedure, and the X2, S1 and S11 interfaces. On top of these features, the LTE handover procedure is modeled, following closely the 3GPP specifications. We present in detail the characteristics of each component of the simulation model, highlighting the modeling assumptions that were made in each case.

In this work we present a link abstraction model for the simulation of downlink data transmission in LTE networks. The purpose of this model is to provide an accurate link performance metric at a low computational cost by relying solely on the knowledge of the SINR and of the modulation and coding scheme. To this aim, the model combines Mutual Information-based multi-carrier compression metrics with Link-Level performance curves matching, to obtain lookup tables that express the dependency of the Block Error Rate on the SINR values and on the modulation and coding scheme being used. In addition, we propose a 3GPP-compliant Channel Quality Indicator evaluation procedure, based on the proposed Link Abstraction Model, to be used as part of the LTE Adaptive Modulation and Coding mechanisms. Finally, we discuss how these contributions have been tested, validated and integrated in the ns-3 simulator. The link abstraction model described in this paper has been included in the official ns-3 distribution since release 3.14.

The main goal of the SWAP project is that of designing, implementing and ultimately testing a new breed of wireless sensor nodes with energy scavenging capabilities. Our design will include novel energy scavenging hardware as well as network protocols and algorithms. In this paper, we summarize the outcomes of the first year of the project as well as the way forward to the further phases. In particular, we analyze the state of the art in the main research areas: energy efficient communication protocol design, ultra-low-power hardware design and most advanced harvesting techniques. For what concerns the future phases of the project we elaborate on the adoption of statistical predictive models for the energy description, we account for game theoretic approaches for distributed optimization and we apply our considerations on the most modern standards for wireless sensor networks communication. We review the state of the art on hardware components, to provide a shortlist of the most efficient building blocks of the SWAP platforms as well as a draft version of the schematics of the module. Finally, we provide a brief overview on the latest energy harvester for miniature scale devices and we argue on the feasibility of a hybrid solar-electromagnetic harvesting module.

In this paper we present a new simulation module for ns-3 aimed at the simulation of LTE networks. This module has been designed with a product-oriented perspective in order to allow LTE equipment manufacturers to test RRM/SON algorithms in a simulation environment before they are deployed in the field. First, we describe the design of our simulation module, highlighting its novel aspects. Subsequently, we discuss the testing methodology that we adopted to validate its output. Finally, we present some experimental result to assess its performance in terms of execution time and memory usage.

In this paper we study the performance of the ambient networks (AN) access selection architecture. We consider heterogeneous wireless networks, where mobile terminals (MTs) own multiple radio technologies and need to remain connected while on the move. We would like to provide the MTs with seamless IP services, such as video/audio streaming, so that changes in their point of attachment will not affect the experienced streaming quality. In the first part of this paper, we present the AN architecture for access selection, along with its functional entities (FEs), their interrelations and the algorithms that are to be run within each FE. Hence, we describe our ns2 simulation framework and detail two simulation scenarios. We finally discuss, through extensive simulation results, the effectiveness of the AN architecture in reaching the above goals.

In this letter we discuss the exploitation of aggregated mobility patterns in mobile networks including heterogeneous multiple access techniques. We advocate the use of knowledge about neighboring devices to create routing groups (RGs) of adjacent nodes in order to optimize radio resource management. Basically, RGs consist of aggregated logical structures which are built and maintained at the application layer. Their use allows decreased signaling overhead between groups of nodes and access points (AP) and, at the same time, improved connectivity, which is achieved through the exploitation of technology diversity and relaying schemes. We illustrate a simple yet effective analytical model, and validate it through accurate simulation results. Finally, we show the effectiveness of the RG approach in terms of resource efficiency, throughput and multiple access performance.

This paper investigates routing strategies for mobile and heterogeneous multi-hop wireless networks. We leverage the knowledge about users mobility to improve the efficiency of route discovery and of the following data forwarding phase. In particular, we exploit group mobility behaviors, which allow us to apply a distributed on-line algorithm for the recognition of aggregated mobility patterns. Hence, we adopt a novel routing strategy that uses the aggregate structure formed within this algorithm to simplify the exchange of signaling and data messages. Finally, we demonstrate and quantify the benefits obtained with the proposed technique by means of a simulator for heterogeneous wireless networks.

The focus of this paper is on routing over heterogeneous networks. We consider a scenario involving both infrastructure and infrastructureless wireless networks, where a set of mobile users are interested in communicating with several access points (APs). Multi-hop routing, possibly over heterogeneous technologies, is exploited to extend the coverage for those users that are not within the transmission range of any APs. We propose a proactive tree-based approach for the dissemination of routing information and the subsequent data forwarding towards the APs. Subsequently, we compare its performance against reactive routing algorithms for ad hoc networks. The network performance is obtained via simulation through careful modeling of the considered radio interfaces. The results indicate the superiority of proactive schemes under moderate/high traffic conditions and motivate further research