The increasing use of renewable energies places new challenges on the balance of the electricity system between demand and supply, due to the intermittent nature of renewable energy resources. However, through frequency regulation (FR) services, owners of battery storage systems can become an essential part of the future smart grids. We propose a thorough first study on the use of batteries associated with base stations (BSs) of a cellular network, to participate in ancillary services with respect to FR services, via an auction system. Trade-offs must be made among the number of participating BSs, the degradation of their batteries and the revenues generated by FR participation. We propose a large-scale mathematical programming model to identify the best participation periods from the perspective of a cellular network operator. The objective is to maximize profit while considering the aging of the batteries following their usage to stabilize the electrical grid. Experiments are conducted with data sets from different real data sources. They not only demonstrate the effectiveness of the optimization model in terms of the selection of BSs participating in ancillary services and providing extra revenues to cellular network operators, but also show the feasibility of ancillary services being provided to cellular network operators.

In Frequency Division Duplex (FDD) systems, for efficient communication, the downlink Channel State Information (CSI) should be sent to the base station through feedback links. Since such transmissions come with the cost of signaling overhead, the state-of-the-art has approaches for data-driven compression of CSI using auto-encoders and other Machine Learning (ML) algorithms. However, models built on a particular training dataset need additional domain transfer overhead for different test settings and environments. We propose a causality-aware Channel State Information (CSI) encoding system that adapts to changes in input data distribution as follows: (a) Create a model of the underlying constraints that generate the observational data, e.g., using Structural Causal Models (SCMs), where the model (e.g., SCMs) captures the cause-and-effect relationships between the observational or endogenous variable (i.e., channel state information) and the unobserved or exogenous variables (e.g., User Equipment (UE) speed, frequency, etc.). The causal graph is represented by directed acyclic graphs (DAGs), where nodes (vertices) correspond to the endogenous variables, and the directed edges account for the causal parent-child relationship. In this scenario, the endogenous variable is the input vector of vectors, $H$ , whereas the exogenous variables include the vendor and non-vendor specific parameters, e.g., power thresholds, channel quality indicator, etc., as detailed in the document, and (b) Perform domain adaptation by applying the learned Structural Causal Model to the received data, e.g., by using a causal layer in the neural network. To the best of our knowledge, this work first demonstrates the efficacy of causality-aware CSI compression and its usefulness in domain adaptability, out-of-distribution generalization, and power savings.