arXiv subjects

Ashkan Haji Hosseinloo

Publications and source records attributed to Ashkan Haji Hosseinloo.

5 recordsLinked to original sources

arXiv2022

Data-driven control of COVID-19 in buildings: a reinforcement-learning approach

In addition to its public health crisis, COVID-19 pandemic has led to the shutdown and closure of workplaces with an estimated total cost of more than $16 trillion. Given the long hours an average person spends in buildings and indoor environments, this research article proposes data-driven control strategies to design optimal indoor airflow to minimize the exposure of occupants to viral pathogens in built environments. A general control framework is put forward for designing an optimal velocity field and proximal policy optimization, a reinforcement learning algorithm is employed to solve the control problem in a data-driven fashion. The same framework is used for optimal placement of disinfectants to neutralize the viral pathogens as an alternative to the airflow design when the latter is practically infeasible or hard to implement. We show, via simulation experiments, that the control agent learns the optimal policy in both scenarios within a reasonable time. The proposed data-driven control framework in this study will have significant societal and economic benefits by setting the foundation for an improved methodology in designing case-specific infection control guidelines that can be realized by affordable ventilation devices and disinfectants.

eess.SY↗

arXiv2020

Data-driven control of micro-climate in buildings: an event-triggered reinforcement learning approach

Smart buildings have great potential for shaping an energy-efficient, sustainable, and more economic future for our planet as buildings account for approximately 40% of the global energy consumption. Future of the smart buildings lies in using sensory data for adaptive decision making and control that is currently gloomed by the key challenge of learning a good control policy in a short period of time in an online and continuing fashion. To tackle this challenge, an event-triggered -- as opposed to classic time-triggered -- paradigm, is proposed in which learning and control decisions are made when events occur and enough information is collected. Events are characterized by certain design conditions and they occur when the conditions are met, for instance, when a certain state threshold is reached. By systematically adjusting the time of learning and control decisions, the proposed framework can potentially reduce the variance in learning, and consequently, improve the control process. We formulate the micro-climate control problem based on semi-Markov decision processes that allow for variable-time state transitions and decision making. Using extended policy gradient theorems and temporal difference methods in a reinforcement learning set-up, we propose two learning algorithms for event-triggered control of micro-climate in buildings. We show the efficacy of our proposed approach via designing a smart learning thermostat that simultaneously optimizes energy consumption and occupants' comfort in a test building.

eess.SY↗

arXiv2015

Optimal control strategies for efficient energy harvesting from ambient vibrations

Ease of miniaturization and minimal maintenance are among the advantages for replacing conventional batteries with vibratory energy harvesters in a wide of range of disciplines and applications, from wireless communication sensors to medical implants. However, the current harvesters do not extract energy from the ambient vibrations in a very efficient and robust fashion, and hence, there need to be more optimal harvesting approaches. In this paper, we introduce a generic architecture for vibration energy harvesting and delineate the key challenges in the field. Then, we formulate an optimal control problem to maximize the harvested energy. Though possessing similar structure to that of the standard LQG problem, this optimal control problem is inherently different from the LQG problem and poses theoretical challenges to control community. As the first step, we simplify it to a tractable problem of optimizing control gains for a linear system subjected to Gaussian white noise excitation, and show that this optimal problem has non-trivial optimal solutions in both time and frequency domains.

eess.SY↗

arXiv2015

Energy harvesting via an adaptive bistable potential

Narrow bandwidth and easy detuning, inefficiency in broadband and non-stationary excitations, and difficulties in matching linear harvester's resonance frequency to low-frequency excitations at small scales, have convinced the researchers to investigate the nonlinear, in particular the bistable energy harvesters in the recent years. However, the bistable harvesters suffer from co-existing low and high energy orbits, and sensitivity to initial conditions, and have been recently proven inefficient when subjected to many real-world random and non-stationary excitations. Here, we propose a novel buy-low-sell-high strategy that can significantly improve the harvester's efficiency at low-frequencies in a much more robust fashion. This strategy could be realized by a passive adaptive bistable system. Simulation results confirm high efficiency of the adaptive bistable system following a buy-low-sell-high logic when subjected to harmonic and random non-stationary walking excitations compared to its conventional bistable and linear counterparts.

cond-mat.other↗

arXiv2014

Fundamental limits to nonlinear energy harvesting

Ease of miniaturization, and less or no maintenance, among other advantages, have pushed towards replacement of conventional batteries with energy harvesters in particular, vibratory energy harvesters. In the recent years, nonlinearity has been intentionally introduced into the otherwise linear energy harvesters in the hope of increasing the frequency bandwidth and power density. However, fundamental limits on the harvestable energy of a harvester subjected to an arbitrary excitation force is yet unknown. Understanding of these limits is not only essential for assessment of the technology potential, but also provides a broader prospective on the current harvesting mechanisms and guidance in their improvement. Here we derive the fundamental limits on output power of an ideal energy harvester, and develop an analysis framework for simple computation of this limit for more sophisticated set-ups. We show that the optimal harvester maximizes the harvested energy through a mechanical analogue of 'buy low-sell high' strategy. Inspired by this strategy we propose a novel concept of latch-assisted harvesting that is shown to harvest energy more efficiently than its linear and bistable counterparts over a wider range of excitation frequencies and amplitudes.

cond-mat.other↗