arXiv subjects

Henni Ouerdane

Publications and source records attributed to Henni Ouerdane.

At least 19 recordsLinked to original sources

arXiv2026

QuatIca: Advanced Numerical Linear Algebra and Optimization for Quaternionic Matrices in Python

Quaternion-valued representations provide a convenient way to model coupled multi-channel signals (e.g., RGB imagery, polarization data, vector fields, and multi-detector time series). Yet practical and numerically reliable software support remains far less mature than those based on the real/complex setting. Here, we present QuatIca, an open-source Python library for quaternion numerical linear algebra and optimization, designed for both research prototyping and reproducible experimentation. QuatIca provides core quaternion matrix operations and norms; dense decompositions and reductions (QR, LU, Q-SVD, eigendecomposition, Hessenberg/tridiagonal reduction, Cholesky decomposition, and Schur helpers); iterative solvers including quaternion GMRES (with preconditioning) and Newton-Schulz pseudoinverse schemes; and domain-focused routines for signal and image processing such as quaternion Tikhonov restoration. The library also includes OptiQ, which solves quaternion Hermitian semidefinite programs using log-det barrier Newton methods with $μ$-continuation. We highlight design choices that preserve quaternion structure, and we provide end-to-end demonstrations including quaternion image deblurring, Lorenz-attractor filtering, and quaternion image completion. QuatIca is distributed via PyPI and accompanied by open-source development on GitHub and continuously deployed documentation with runnable tutorials.

math.NA↗

arXiv2026

Benchmarking Reinforcement Learning via Stochastic Converse Optimality: Generating Systems with Known Optimal Policies

The objective comparison of Reinforcement Learning (RL) algorithms is notoriously complex as outcomes and benchmarking of performances of different RL approaches are critically sensitive to environmental design, reward structures, and stochasticity inherent in both algorithmic learning and environmental dynamics. To manage this complexity, we introduce a rigorous benchmarking framework by extending converse optimality to discrete-time, control-affine, nonlinear systems with noise. Our framework provides necessary and sufficient conditions, under which a prescribed value function and policy are optimal for constructed systems, enabling the systematic generation of benchmark families via homotopy variations and randomized parameters. We validate it by automatically constructing diverse environments, demonstrating our framework's capacity for a controlled and comprehensive evaluation across algorithms. By assessing standard methods against a ground-truth optimum, our work delivers a reproducible foundation for precise and rigorous RL benchmarking.

cs.LG↗

arXiv2025

Fusion-ResNet: A Lightweight multi-label NILM Model Using PCA-ICA Feature Fusion

Non-intrusive load monitoring (NILM) is an advanced load monitoring technique that uses data-driven algorithms to disaggregate the total power consumption of a household into the consumption of individual appliances. However, real-world NILM deployment still faces major challenges, including overfitting, low model generalization, and disaggregating a large number of appliances operating at the same time. To address these challenges, this work proposes an end-to-end framework for the NILM classification task, which consists of high-frequency labeled data, a feature extraction method, and a lightweight neural network. Within this framework, we introduce a novel feature extraction method that fuses Independent Component Analysis (ICA) and Principal Component Analysis (PCA) features. Moreover, we propose a lightweight architecture for multi-label NILM classification (Fusion-ResNet). The proposed feature-based model achieves a higher $F1$ score on average and across different appliances compared to state-of-the-art NILM classifiers while minimizing the training and inference time. Finally, we assessed the performance of our model against baselines with a varying number of simultaneously active devices. Results demonstrate that Fusion-ResNet is relatively robust to stress conditions with up to 15 concurrently active appliances.

cs.LG↗

arXiv2025

Quantum determinism and completeness restored by indistinguishability and long-time particle detection

We argue that measurement data in quantum physics can be rigorously interpreted only as a result of a statistical, macroscopic process, taking into account the indistinguishable character of identical particles. Quantum determinism is in principle possible on the condition that a fully-fledged quantum-field-theoretic model is used to describe the measurement device in interaction with the studied object as one system. In contrast, any approach that relies on Born's rule discriminates the dynamics of a quantum system from that of the detector with which it interacts during measurement. In this work, we critically analyze the validity of this measurement postulate applied to single-event signals. In fact, the concept of ``individual'' particle becomes inadequate once both indistinguishability and a scattering approach allowing an unlimited interaction time for an effective detection, are considered as they should be, hence preventing the separability of two successive measurement events. In this context, measurement data should therefore be understood only as a result of statistics over many events. Accounting for the intrinsic noise of the sources and the detectors, we also show with the illustrative cases of the Schrödinger cat and the Bell experiment that once the Born rule is abandoned on the level of a single particle, realism, locality and causality are restored. We conclude that indiscernibility and long-time detection process make quantum physics not fundamentally probabilistic.

physics.gen-ph↗

arXiv2025

HiFAKES: Synthetic High-Frequency NILM Data for NILM Models Diagnostics and Generalization Testing

Monitoring electricity consumption at the appliance level is crucial for increasing energy efficiency in residential and commercial buildings. Using a single meter, the non-intrusive load monitoring (NILM) breaks down household consumption down to appliance-level, providing comprehensive insights into end-user electricity behavior. NILM models are trained on a household's total power consumption paired with submetered appliance labels. When sampled at high frequencies ($\geq$ 1 kHz), these datasets capture the full waveform characteristics, significantly improving disaggregation accuracy and model generalization. Nevertheless, such datasets are scarce, collected from a limited number of households, and rarely include labels for power estimation, which complicates their use for model training, evaluation, or debugging. We propose HiFAKES, a pre-trained synthetic data generator that can instantly generate unlimited amounts of fully labeled high-frequency NILM data, including aggregated and submetered current signatures. The data is ready-to-use and annotated for load identification (classification) and power estimation (regression). It allows simulating seen and completely unseen scenarios of appliances' behavior with full control over the number of appliance classes, operational modes, class similarity, brand diversity, and the number of concurrently running devices. We propose a structured methodology to test the generalization of NILM models on simulated unseen households. The reliability of the HiFAKES synthetic data is assessed using a domain-agnostic 3-dimensional metric. The generated signatures achieve high realism (93\% authenticity), closely resemble real-world data (84\% fidelity), and include a reasonable portion of unseen signatures (5\%).

eess.SP↗

arXiv2025

Indoor thermal comfort management: A Bayesian machine-learning approach to data denoising and dynamics prediction of HVAC systems

The optimal management of a building's microclimate to satisfy the occupants' needs and objectives in terms of comfort, energy efficiency, and costs is particularly challenging. This complexity arises from the non-linear, time-dependent interactions among all the variables of the control problem and the changing internal and external constraints. Focusing on the accurate modeling of the indoor temperature, we propose a data-driven approach to address this challenge. We account for thermal inertia, non-linear effects, small perturbations of the indoor climate dynamics caused by ventilation and weather variations, as well as for the stochastic nature of the control system due to the observed noise in the input signal. Since the prohibitive cost of quality data acquisition and processing limits the implementation of data-driven approaches for real-life problems, we applied a method that merges several Bayesian machine learning and deep learning architectures that are suitable for predicting complex system dynamics, while relaxing the dataset quality requirements. Our framework includes a built-in deep Kalman filter, which makes it deployable even with low-accuracy temperature sensors. It achieves state-of-the-art performance, best performing with a 150-minute prediction horizon with an RMSE of 0.2455, an MAE of 0.162, and an $R^2$ of 0.926. The model's performance remains consistent even when exposed to highly noisy data. Finally, we show how our approach can be extended to other applications including demand response event duration prediction and equipment failure detection.

eess.SY↗

arXiv2025

Toward Explainable NILM: Real-Time Event-Based NILM Framework for High-Frequency Data

Non-Intrusive Load Monitoring (NILM) is an advanced, and cost-effective technique for monitoring appliance-level energy consumption. However, its adaptability is hindered by the lack of transparency and explainability. To address this challenge, this paper presents an explainable, real-time, event-based NILM framework specifically designed for high-frequency datasets. The proposed framework ensures transparency at every stage by integrating a z-score-based event detector, appliance signature estimation, Fourier-based feature extraction, an XG-Boost classifier, and post hoc SHAP analysis. The SHAP analysis further quantifies the contribution of individual features, such as cosine of specific harmonic phases, to appliance classification. The framework is trained and evaluated on the PLAID dataset, and achieved a classification accuracy of 90% while maintaining low computational requirements and a latency of less than one second.

eess.SY↗

arXiv2025

Enhancing Non-Intrusive Load Monitoring with Features Extracted by Independent Component Analysis

In this paper, a novel neural network architecture is proposed to address the challenges in energy disaggregation algorithms. These challenges include the limited availability of data and the complexity of disaggregating a large number of appliances operating simultaneously. The proposed model utilizes independent component analysis as the backbone of the neural network and is evaluated using the F1-score for varying numbers of appliances working concurrently. Our results demonstrate that the model is less prone to overfitting, exhibits low complexity, and effectively decomposes signals with many individual components. Furthermore, we show that the proposed model outperforms existing algorithms when applied to real-world data.

eess.SY↗

arXiv2025

COLD: Concurrent Loads Disaggregator for Non-Intrusive Load Monitoring

The global effort toward renewable energy and the electrification of energy-intensive sectors have significantly increased the demand for electricity, making energy efficiency a critical focus. Non-intrusive load monitoring (NILM) enables detailed analyses of household electricity usage by disaggregating the total power consumption into individual appliance-level data. In this paper, we propose COLD (Concurrent Loads Disaggregator), a transformer-based model specifically designed to address the challenges of disaggregating high-frequency data with multiple simultaneously working devices. COLD supports up to 42 devices and accurately handles scenarios with up to 11 concurrent loads, achieving 95% load identification accuracy and 82% disaggregation performance on the test data. In addition, we introduce a new fully labeled high-frequency NILM dataset for load disaggregation derived from the UK-DALE 16 kHz dataset. Finally, we analyze the decline in NILM model performance as the number of concurrent loads increases.

eess.SP↗

arXiv2025

Cyclic solid-state quantum battery: Thermodynamic characterization and quantum hardware simulation

We introduce a cyclic quantum battery model, based on an interacting bipartite system, weakly coupled to a thermal bath. The working cycle of the battery consists of four strokes: system thermalization, disconnection of subsystems, ergotropy extraction, and reconnection. The thermal bath acts as a charger in the thermalization stroke, while ergotropy extraction is possible because the ensuing thermal state is no longer passive after the disconnection stroke. Focusing on the case of two interacting qubits, we show that phase coherence, in the presence of non-trivial correlations between the qubits, can be exploited to reach working regimes with efficiency higher than 50% while providing finite ergotropy. Our protocol is illustrated through a simple and feasible circuit model of a cyclic superconducting quantum battery. Furthermore, we simulate the considered cycle on superconducting IBM quantum machines. The good agreement between the theoretical and simulated results strongly suggests that our scheme for cyclic quantum batteries can be successfully realized in superconducting quantum hardware.

quant-ph↗

arXiv2024

The indoor agriculture industry: a promising player in demand response services

Demand response (DR) programs currently cover about 2\% of the average annual global demand, which is far from contributing to the International Energy Agency's ``Net Zero by 2050'' roadmap's 20\% target. While aggregation of many small flexible loads such as individual households can help reaching this target, increasing the participation of industries that are major electricity consumers is certainly a way forward. The indoor agriculture sector currently experiences a significant growth to partake in the sustainable production of high-quality food world-wide. As energy-related costs, up to 40\% of the total expenses, may preclude full maturity of this industry, DR participation can result in a win-win situation. Indeed, the agriculture system must transform and become a sustainable source of food for an increasing number of people worldwide under the constraints of preservation of soils and water, carbon footprint, and energy efficiency. We considered the case of the Russian Federation where indoor farming is burgeoning and already represents a load of several thousand megawatts. To show the viability of the indoor farming industry participation in implicit and explicit DR programs, we built a physical model of a vertical farm inside a phytotron with complete control of environmental parameters including ambient temperature, relative humidity, CO$_2$ concentration, and photosynthetic photon flux density. This phytotron was used as a model greenhouse. We grew different varieties of leafy plants under simulated DR conditions and control conditions on the same setup. Our results show that the indoor farming dedicated to greens can participate in DR without adversely affecting plant production and that this presents an economic advantage.

physics.soc-ph↗

arXiv2024

Physics-informed appliance signatures generator for energy disaggregation

Energy disaggregation is a promising solution to access detailed information on energy consumption in a household, by itemizing its total energy consumption. However, in real-world applications, overfitting remains a challenging problem for data-driven disaggregation methods. First, the available real-world datasets are biased towards the most frequently used appliances. Second, both real and synthetic publicly-available datasets are limited in number of appliances, which may not be sufficient for a disaggregation algorithm to learn complex relations among different types of appliances and their states. To address the lack of appliance data, we propose two physics-informed data generators: one for high sampling rate signals (kHz) and another for low sampling rate signals (Hz). These generators rely on prior knowledge of the physics of appliance energy consumption, and are capable of simulating a virtually unlimited number of different appliances and their corresponding signatures for any time period. Both methods involve defining a mathematical model, selecting centroids corresponding to individual appliances, sampling model parameters around each centroid, and finally substituting the obtained parameters into the mathematical model. Additionally, by using Principal Component Analysis and Kullback-Leibler divergence, we demonstrate that our methods significantly outperform the previous approaches.

eess.SY↗

arXiv2023

Assessing the value of energy storage systems for distribution grid applications

We analyze the potential benefits that energy storage systems (ESS) can bring to distribution networks in terms of cost, stability and flexibility. We propose an optimization model for the optimal sizing, siting, and operation of storage systems in distribution grids. A DistFlow formulation is used for modeling the AC power flow. The ESS model is based on a generic formulation that captures the charging and discharging modes' complementarity. The resulting optimization model is stated as a mixed-integer quadratically constrained program (MIQCP) problem. The optimization model is assessed on the modified 33-bus IEEE network, which includes renewable energy resources and ESS. The obtained results show that ESS can offer various important benefits such as overall cost reduction, energy arbitrage, voltage regulation, and congestion management in distribution grids. These findings highlight the significance of utilizing ESS technologies to provide aggregated value through various grid services, extending beyond energy arbitrage alone.

eess.SY↗

arXiv2023

Combining model-predictive control and predictive reinforcement learning for stable quadrupedal robot locomotion

Stable gait generation is a crucial problem for legged robot locomotion as this impacts other critical performance factors such as, e.g. mobility over an uneven terrain and power consumption. Gait generation stability results from the efficient control of the interaction between the legged robot's body and the environment where it moves. Here, we study how this can be achieved by a combination of model-predictive and predictive reinforcement learning controllers. Model-predictive control (MPC) is a well-established method that does not utilize any online learning (except for some adaptive variations) as it provides a convenient interface for state constraints management. Reinforcement learning (RL), in contrast, relies on adaptation based on pure experience. In its bare-bone variants, RL is not always suitable for robots due to their high complexity and expensive simulation/experimentation. In this work, we combine both control methods to address the quadrupedal robot stable gate generation problem. The hybrid approach that we develop and apply uses a cost roll-out algorithm with a tail cost in the form of a Q-function modeled by a neural network; this allows to alleviate the computational complexity, which grows exponentially with the prediction horizon in a purely MPC approach. We demonstrate that our RL gait controller achieves stable locomotion at short horizons, where a nominal MP controller fails. Further, our controller is capable of live operation, meaning that it does not require previous training. Our results suggest that the hybridization of MPC with RL, as presented here, is beneficial to achieve a good balance between online control capabilities and computational complexity.

cs.RO↗

arXiv2022

Voltage-amplified heat rectification in SIS junctions

The control of thermal fluxes -- magnitude and direction, in mesoscale and nanoscale electronic circuits can be achieved by means of heat rectification using thermal diodes in two-terminal systems. The rectification coefficient $\mathcal{R}$, given by the ratio of forward and backward heat fluxes, varies with the design of the diode and the working conditions under which the system operates. A value of $\mathcal{R}\ll 1$ or $\mathcal{R}\gg 1$ is a signature of high heat rectification performance but current solutions allowing such ranges, necessitate rather complex designs. Here, we propose a simple solution: the use of a superconductor-insulator-superconductor (SIS) junction under an applied fast oscillating (THz range) voltage as the control of the heat flow direction and magnitude can be done by tuning the initial value of the superconducting phase. Our theoretical model based on the Green functions formalism and coherent transport theory, shows a possible sharp rise of the heat rectification coefficient with values up to $\mathcal{R} \approx 500$ beyond the adiabatic regime. The influence of quantum coherent effects on heat rectification in the SIS junction is highlighted.

cond-mat.mes-hall↗

arXiv2022

SQUID-based interferometric accelerometer

Optics and more recently coherent matter waves enabled inertial sensors such as accelerometers and gyroscopes to reach high levels of resolution and sensitivity. As these technologies rest on physical phenomena that require particular setups and working conditions such as, e.g., kilometers of optical fibers or ultralow temperatures, their application range is limited because of lack of portability. Here, we propose a path forward considering a superconducting quantum interference device (SQUID) to detect and measure acceleration, using electronic interferometry. The operation of such an accelerometer rests on the ability of the Cooper pairs to record their wave function phase change as the device is subjected either to a transverse acceleration or vibrations. We provide numerical evidence for the feasibility of SQUID-based accelerometers that can be used for transverse acceleration and oscillatory motion measurement.

quant-ph↗

arXiv2021

Super-relaxation of space-time-quantized ensemble of energy loads to curtail their synchronization after demand response perturbation

Ensembles of thermostatically controlled loads (TCL) provide a significant demand response reserve for the system operator to balance power grids. However, this also results in the parasitic synchronization of individual devices within the ensemble leading to long post-demand-response oscillations in the integrated energy consumption of the ensemble. The synchronization is eventually destructed by fluctuations, thus leading to the (pre-demand response) steady state; however, this natural desynchronization, or relaxation to a statistically steady state, is too long. A resolution of this problem consists in measuring the ensemble's instantaneous consumption and using it as a feedback to stochastic switching of the ensemble's devices between on- and off- states. A simplified continuous-time model showed that carefully tuned nonlinear feedback results in a fast (super-) relaxation of the ensemble energy consumption. Since both state information and control signals are discrete, the actual TCL devices operation is space-time quantized, and this must be considered for realistic TCL ensemble modelling. Here, assuming that states are characterized by indoor temperature (quantifying comfort) and air conditioner regime (on, off), we construct a discrete model based on the probabilistic description of state transitions. We demonstrate that super-relaxation holds in such a more realistic setting, and that while it is stable against randomness in the stochastic matrix of the quantized model, it remains sensitive to the time discretization scheme. Aiming to achieve a balance between super-relaxation and customer's comfort, we analyze the dependence of super-relaxation on details of the space-time quantization, and provide a simple analytical criterion to avoid undesirable oscillations in consumption.

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↗