To Train or Not to Train: Balancing Efficiency and Training Cost in Deep Reinforcement Learning for Mobile Edge Computing

Artificial Intelligence (AI) is a key component of 6G networks, as it enables communication and computing services to adapt to end users' requirements and demand patterns. The management of Mobile Edge Computing (MEC) is a meaningful example of AI application: computational resources available at the network edge need to be carefully allocated to users, whose jobs may have different priorities and latency requirements. The research community has developed several AI algorithms to perform this resource allocation, but it has neglected a key aspect: learning is itself a computationally demanding task, and considering free training results in idealized conditions and performance in simulations. In this work, we consider a more realistic case in which the cost of learning is specifically accounted for, presenting a new algorithm to dynamically select when to train a Deep Reinforcement Learning (DRL) agent that allocates resources. Our method is highly general, as it can be directly applied to any scenario involving a training overhead, and it can approach the same performance as an ideal learning agent even under realistic training conditions.

Content-based Wake-up for Energy-efficient and Timely Top-k IoT Sensing Data Retrieval

Energy efficiency and information freshness are key requirements for sensor nodes serving Industrial Internet of Things (IIoT) applications, where a sink node collects informative and fresh data before a deadline, e.g., to control an external actuator. Content-based wake-up (CoWu) activates a subset of nodes that hold data relevant for the sink's goal, thereby offering an energy-efficient way to attain objectives related to information freshness. This paper focuses on a scenario where the sink collects fresh information on top-k values, defined as data from the nodes observing the k highest readings at the deadline. We introduce a new metric called top-k Query Age of Information (k-QAoI), which allows us to characterize the performance of CoWu by considering the characteristics of the physical process. Further, we show how to select the CoWu parameters, such as its timing and threshold, to attain both information freshness and energy efficiency. The numerical results reveal the effectiveness of the CoWu approach, which is able to collect top-k data with higher energy efficiency while reducing k-QAoI when compared to round-robin scheduling, especially when the number of nodes is large and the required size of k is small.

A Fairness-Oriented Reinforcement Learning Approach for the Operation and Control of Shared Micromobility Services

As Machine Learning systems become increasingly popular across diverse application domains, including those with direct human implications, the imperative of equity and algorithmic fairness has risen to prominence in the Artificial Intelligence community. On the other hand, in the context of Shared Micromobility Systems, the exploration of fairness-oriented approaches remains limited. Addressing this gap, we introduce a pioneering investigation into the balance between performance optimization and algorithmic fairness in the operation and control of Shared Micromobility Services. Our study leverages the Q-Learning algorithm in Reinforcement Learning, benefiting from its convergence guarantees to ensure the robustness of our proposed approach. Notably, our methodology stands out for its ability to achieve equitable outcomes, as measured by the Gini index, across different station categories--central, peripheral, and remote. Through strategic rebalancing of vehicle distribution, our approach aims to maximize operator performance while simultaneously upholding fairness principles for users. In addition to theoretical insights, we substantiate our findings with a case study or simulation based on synthetic data, validating the efficacy of our approach. This paper underscores the critical importance of fairness considerations in shaping control strategies for Shared Micromobility Services, offering a pragmatic framework for enhancing equity in urban transportation systems.

Effective Communication with Dynamic Feature Compression

The remote wireless control of industrial systems is one of the major use cases for 5G and beyond systems: in these cases, the massive amounts of sensory information that need to be shared over the wireless medium may overload even high-capacity connections. Consequently, solving the effective communication problem by optimizing the transmission strategy to discard irrelevant information can provide a significant advantage, but is often a very complex task. In this work, we consider a prototypal system in which an observer must communicate its sensory data to a robot controlling a task (e.g., a mobile robot in a factory). We then model it as a remote Partially Observable Markov Decision Process (POMDP), considering the effect of adopting semantic and effective communication-oriented solutions on the overall system performance. We split the communication problem by considering an ensemble Vector Quantized Variational Autoencoder (VQ-VAE) encoding, and train a Deep Reinforcement Learning (DRL) agent to dynamically adapt the quantization level, considering both the current state of the environment and the memory of past messages. We tested the proposed approach on the well-known CartPole reference control problem, obtaining a significant performance increase over traditional approaches.

Push- and Pull-based Effective Communication in Cyber-Physical Systems

In Cyber Physical Systems (CPSs), two groups of actors interact toward the maximization of system performance: the sensors, observing and disseminating the system state, and the actuators, performing physical decisions based on the received information. While it is generally assumed that sensors periodically transmit updates, returning the feedback signal only when necessary, and consequently adapting the physical decisions to the communication policy, can significantly improve the efficiency of the system. In particular, the choice between push-based communication, in which updates are initiated autonomously by the sensors, and pull-based communication, in which they are requested by the actuators, is a key design step. In this work, we propose an analytical model for optimizing push- and pull-based communication in CPSs, observing that the policy optimality coincides with Value of Information (VoI) maximization. Our results also highlight that, despite providing a better optimal solution, implementable push-based communication strategies may underperform even in relatively simple scenarios.

Timely and Massive Communication in 6G: Pragmatics, Learning, and Inference

5G has expanded the traditional focus of wireless systems to embrace two new connectivity types: ultra-reliable low latency and massive communication. The technology context at the dawn of 6G is different from the past one for 5G, primarily due to the growing intelligence at the communicating nodes. This has driven the set of relevant communication problems beyond reliable transmission towards semantic and pragmatic communication. This paper puts the evolution of low-latency and massive communication towards 6G in the perspective of these new developments. At first, semantic/pragmatic communication problems are presented by drawing parallels to linguistics. We elaborate upon the relation of semantic communication to the information-theoretic problems of source/channel coding, while generalized real-time communication is put in the context of cyber-physical systems and real-time inference. The evolution of massive access towards massive closed-loop communication is elaborated upon, enabling interactive communication, learning, and cooperation among wireless sensors and actuators.

Goal-Oriented Scheduling in Sensor Networks with Application Timing Awareness

Taking inspiration from linguistics, the communications theoretical community has recently shown a significant recent interest in pragmatic , or goal-oriented, communication. In this paper, we tackle the problem of pragmatic communication with multiple clients with different, and potentially conflicting, objectives. We capture the goal-oriented aspect through the metric of Value of Information (VoI), which considers the estimation of the remote process as well as the timing constraints. However, the most common definition of VoI is simply the Mean Square Error (MSE) of the whole system state, regardless of the relevance for a specific client. Our work aims to overcome this limitation by including different summary statistics, i.e., value functions of the state, for separate clients, and a diversified query process on the client side, expressed through the fact that different applications may request different functions of the process state at different times. A query-aware Deep Reinforcement Learning (DRL) solution based on statically defined VoI can outperform naive approaches by 15-20%.

Fast Context Adaptation in Cost-Aware Continual Learning

In the past few years, DRL has become a valuable solution to automatically learn efficient resource management strategies in complex networks with time-varying statistics. However, the increased complexity of 5G and Beyond networks requires correspondingly more complex learning agents and the learning process itself might end up competing with users for communication and computational resources. This creates friction: on the one hand, the learning process needs resources to quickly convergence to an effective strategy; on the other hand, the learning process needs to be efficient, i.e., take as few resources as possible from the user's data plane, so as not to throttle users' QoS. In this paper, we investigate this trade-off and propose a dynamic strategy to balance the resources assigned to the data plane and those reserved for learning. With the proposed approach, a learning agent can quickly converge to an efficient resource allocation strategy and adapt to changes in the environment as for the CL paradigm, while minimizing the impact on the users' QoS. Simulation results show that the proposed method outperforms static allocation methods with minimal learning overhead, almost reaching the performance of an ideal out-of-band CL solution.

Learning-Based Rich Feedback HARQ for Energy-Efficient Short Packet Transmission

The trade-off between reliability, latency, and energy-efficiency is a central problem in communication systems. Advanced hybrid automated repeat request (HARQ) techniques can reduce the number of retransmissions required for reliable communication, but they have a significant computational cost. On the other hand, strict energy constraints apply mainly to devices, while the access point receiving their packets is usually connected to the electrical grid. Therefore, moving the computational complexity required for HARQ schemes from the transmitter to the receiver may provide a way to overcome this trade-off. To achieve this, we propose the Reinforcement-based Adaptive Feedback (RAF) scheme, in which the receiver adaptively learns how much additional redundancy it requires to decode a packet and sends rich feedback (i.e., more than a single bit), requesting the coded retransmission of specific symbols. Simulation results show that the RAF scheme achieves a better trade-off between energy-efficiency, reliability, and latency, compared to existing HARQ solutions and a fixed threshold-based policy. Our RAF scheme can easily adapt to different modulation schemes, and since it relies on the posterior probabilities of the codeword symbols at the decoder, it can generalize to different channel statistics.

Multi-Agent Reinforcement Learning for Pragmatic Communication and Control

The automation of factories and manufacturing processes has been accelerating over the past few years, boosted by the Industry 4.0 paradigm, including diverse scenarios with mobile, flexible agents. Efficient coordination between mobile robots requires reliable wireless transmission in highly dynamic environments, often with strict timing requirements. Goal-oriented communication is a possible solution for this problem: communication decisions should be optimized for the target control task, providing the information that is most relevant to decide which action to take. From the control perspective, networked control design takes the communication impairments into account in its optmization of physical actions. In this work, we propose a joint design that combines goal-oriented communication and networked control into a single optimization model, an extension of a multiagent POMDP which we call Cyber-Physical POMDP (CP-POMDP). The model is flexible enough to represent several swarm and cooperative scenarios, and we illustrate its potential with two simple reference scenarios with a single agent and a set of supporting sensors. Joint training of the communication and control systems can significantly improve the overall performance, particularly if communication is severely constrained, and can even lead to implicit coordination of communication actions.