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.

Modern edge-cloud systems face challenges in ef-ficiently scaling resources to handle dynamic and unpredictable workloads. Traditional scaling approaches typically rely on static thresholds and predefined rules, which are often inadequate for optimizing resource utilization and maintaining performance in distributed and dynamic environments. This inefficiency hin-ders the adaptability and performance required in edge-cloud infrastructures, which can only be achieved through the newly proposed in-place scaling. To address this problem, we propose the Multi-Agent Reinforcement Learning-based In-place Scaling Engine (MARLISE) that enables seamless, dynamic, reactive control with in-place resource scaling. We develop our solution using two Deep Reinforcement Learning algorithms: Deep Q-Network (DQN), and Proximal Policy Optimization (PPO). We analyze each version of the proposed MARLISE solution using dynamic workloads, demonstrating their ability to ensure low response times of microservices and scalability. Our results show that MARLISE- based approaches outperform heuristic method in managing resource elasticity while maintaining microservice response times and achieving higher resource efficiency.

Reconfigurable intelligent surfaces (RISs) play an important role in extending the connectivity and improving the data rate of future wireless communication systems. However, the conventional (passive) RISs have their limitations and, thus, a hybrid-relay RIS (HR-RIS) architecture is proposed to reap the benefits of relaying systems with high power consumption but higher throughput, and passive RIS systems with cascaded fading effects but low complexity. In this paper, we investigate the performance of HR-RISs in a massive multiple-input multiple-output (M-MIMO) system with zero-forcing (ZF) processing, where channel state information (CSI) is unavailable. We first model the uplink/downlink channels and derive the linear minimum mean square error (LMMSE) estimate of the effective channels. We, then, derive a closed-form expression for the signal to interference and noise ratio (SINR) and spectral efficiency (SE). Finally, we provide some useful engineering insights with our asymptotic analysis and numerical results.

In this paper, a new transceiver design for multi-user multi-relay MIMO downlink channel is proposed. We derive the closed-form expressions for the gradients of the weighted sum-MSE with respect to the precoders and present a new transceiver design based on the gradient descent algorithm. The algorithm monotonically decreases the weighted sum-MSE and hence guarantees local convergence. Simulation results show that the proposed algorithm can generate good suboptimal solution with much faster convergence rate comparing to other algorithms.