arXiv subjects

Francesco Smarra

Publications and source records attributed to Francesco Smarra.

4 recordsLinked to original sources

arXiv2025

Inverse Optimality for Fair Digital Twins: A Preference-based approach

Digital Twins (DTs) are increasingly used as autonomous decision-makers in complex socio-technical systems. However, their mathematically optimal decisions often diverge from human expectations, revealing a persistent mismatch between algorithmic and bounded human rationality. This work addresses this challenge by proposing a framework that introduces fairness as a learnable objective within optimization-based Digital Twins. In this respect, a preference-driven learning workflow that infers latent fairness objectives directly from human pairwise preferences over feasible decisions is introduced. A dedicated Siamese neural network is developed to generate convex quadratic cost functions conditioned on contextual information. The resulting surrogate objectives drive the optimization procedure toward solutions that better reflect human-perceived fairness while maintaining computational efficiency. The effectiveness of the approach is demonstrated on a COVID-19 hospital resource allocation scenario. Overall, this work offers a practical solution to integrate human-centered fairness into the design of autonomous decision-making systems.

cs.LG↗

arXiv2025

Optimal control over Markovian wireless communication channels under generalized packet dropout compensation

Control loops closed over wireless links greatly benefit from accurate estimates of the communication channel condition. To this end, the finite-state Markov channel model allows for reliable channel state estimation. This paper develops a Markov jump linear system representation for wireless networked control with persistent channel state observation, stochastic message losses, and generalized packet dropout compensation. With this model, we solve the finite- and infinite-horizon linear quadratic regulation problems and introduce an easy-to-test stability condition for any given infinite-horizon control law. We also thoroughly analyze the impact of a scalar general dropout compensation factor on the stability and closed-loop performance of a rotary inverted pendulum controlled remotely through a wireless link. Finally, we validate the results numerically via extensive Monte Carlo simulations, showing the benefits of the proposed control strategy.

eess.SY↗

arXiv2021

Learning Markov models of fading channels in wireless control networks: a regression trees based approach

Finite-state Markov models are widely used for modeling wireless channels affected by a variety of non-idealities, ranging from shadowing to interference. In an industrial environment, the derivation of a Markov model based on the wireless communication physics can be prohibitive as it requires a complete knowledge of both the communication dynamics parameters and of the disturbances/interferers. In this work, a novel methodology is proposed to learn a Markov model of a fading channel via historical data of the signal-to-interference-plus-noise-ratio (SINR). Such methodology can be used to derive a Markov jump model of a wireless control network, and thus to design a stochastic optimal controller that takes into account the interdependence between the plant and the wireless channel dynamics. The proposed method is validated by comparing its prediction accuracy and control performance with those of a stationary finite-state Markov chain derived assuming perfect knowledge of the physical channel model and parameters of a WirelessHART point-to-point communication based on the IEEE-802.15.4 standard.

eess.SY↗

arXiv2020

NeurOpt: Neural network based optimization for building energy management and climate control

Model predictive control (MPC) can provide significant energy cost savings in building operations in the form of energy-efficient control with better occupant comfort, lower peak demand charges, and risk-free participation in demand response. However, the engineering effort required to obtain physics-based models of buildings is considered to be the biggest bottleneck in making MPC scalable to real buildings. In this paper, we propose a data-driven control algorithm based on neural networks to reduce this cost of model identification. Our approach does not require building domain expertise or retrofitting of existing heating and cooling systems. We validate our learning and control algorithms on a two-story building with ten independently controlled zones, located in Italy. We learn dynamical models of energy consumption and zone temperatures with high accuracy and demonstrate energy savings and better occupant comfort compared to the default system controller.

eess.SY↗