Abstract Most of the energy produced in world is consumed by commercial and residential buildings. With growth global economy demographics, this demand has become increasingly important. This led to higher unit electricity prices, frequent stresses on main grid carbon emissions due inefficient management. paper presents an energy-consumption management system based time-shifting loads according dynamic day-ahead pricing. simultaneously reduces bill peaks, while maintaining user comfort terms...

Abstract This article proposes a method for accurately predicting solar irradiance over 24-hour horizon to forecast photovoltaic energy generation in positive-energy building. In order make this prediction, the input data are divided into seasons and preprocessed using variational mode decomposition (seasonal-VMD) method. The VMD is used extracting high-bandwidth features from data, decomposing them finite number of smooth modes focusing on specific frequency ranges. Hence, accuracy signal...

To improve braking safety, modern electric vehicles are equipped with both friction and regenerative systems. The combined use of these two modes is mainly carried out in ABS operation. This paper deals the problem torque control mode. EV considered a traction motor interior permanent magnet synchronous machine type (IPMSM). Using field-oriented (FOC) strategy, regulators, namely adaptive fuzzy PID (AFPID) neuro-fuzzy inference system (ANFIS) developed their performances analyzed compared....

This paper proposes a Multi-stage Home Energy Management System (MS-HEMS) for power demand distribution among the Photovoltaic system (PV), Storage (ESS), and Electrical Power Grid (EPG). MS-HEMS consists of two layers: Anticipative layer (AL) reactive (RL). The AL employs Particle Swarm Optimization (PSO) day-ahead energy management based on weather consumption forecasts; RL includes an Extremum-Seeking Controller (ESC) that determines ideal setpoint each source in real-time, compensating...

To ensure braking stability and maximize energy recovery, electric vehicles combine two modes, friction regenerative braking. This paper proposes a novel torque distribution (BTD) algorithm between frictional/regenerative brake systems. Security regeneration are the main issues in allocation design. Based on extremum search (ES) technique, objectives constraints of hybrid ABS well handled. The offered BTD can improve battery's state charge (SOC) by optimizing system efficiency, while...

This paper develops a predictive current controller for an induction motor (IM), based on neural networks. More precisely, the proposed regulator treats this control problem as optimization exploiting predictor IM currents. The considered objective function is constituted of two components, namely: tracking errors and electromagnetic torque ripples. Moreover, computed over given time horizon, currents prediction results. Particle Swarm Optimization (PSO) algorithm used to solve problem....

This paper presents a hybrid method for accurately predicting Global Horizontal Irradiance (GHI) over the following 24 hours to forecast energy production from photo-voltaic system in positive building. The input data is preprocessed using Variational Mode Decomposition (VMD) extract wide-bandwidth features and decompose them into smooth modes focused on specific frequency ranges. Salp Swarm Algorithm (SSA) utilized identify optimal VMD parameters accurate extraction. analysis employed most...

Abstract This paper develops an adaptive neural network (NN) observer for proton-exchange membrane fuel cells (PEMFCs). Indeed, information on the oxygen excess ratio (OER) value is crucial to ensure optimal management of durability and reliability PEMFC. The OER indicator computed from mass nitrogen inside PEMFC cathode. Unfortunately, measurement process both these masses difficult costly. To solve this problem, design a state attractive. However, behaviour cell system highly non-linear...

Designing high-gain observers (HGOs) for the state estimation of an electric vehicle's electrohydraulic brake (EHB) system is challenging. This type observer applicable to model nonlinearities and constant feature gains. However, they are very sensitive measurement noise, which unavoidable in EHB. The first novelty this study that it compensates noise using a filtered (FHGO) ensure EHB estimation. proposed FHGO provides estimate master cylinder pressure, motor current, rotor speed from...

Summary We are considering the problem of designing observers for heat partial differential equations (PDEs) that subject to sensor delay and parameter uncertainty. In order get finite‐dimensional observers, described by ordinary (ODE), we develop a design method based on modal decomposition approach. The approach is extended so both uncertainty effects compensated for. To cope more effectively with delay, an output predictor designed online provided predictions substituted future values in...

This paper focuses on the problem of controlling DC-to-DC switched power converters Buck type. The system nonlinear feature is coped with by resorting to backstepping control approach. Both adaptive and nonadaptive versions are designed shown yield quite interesting tracking robustness performances. A comparison study shows that controllers perform as well passivity-based controllers. For both, choice design parameters proves be crucial for achieving respect load resistance variations. From...

In this paper, the problem of controlling anti-lock braking system (ABS) was considered. Based on LuGre friction model, an output-feedback adaptive controller that enjoys good performances whatever road conditions, developed. Specifically, tracks optimal slip coefficient and, unlike previous work, reference ratio is online estimated according to conditions as well longitudinal vehicle speed. The feature proves be crucial for compensating uncertainty changing characteristics. consists of: (i)...

This paper presents a comprehensive solution for Multi-Individual load disaggregation and Multi-individual Forecasting in residential energy systems. The approach combines Variable Mode Decomposition (VMD) deep learning algorithms, incorporating feature selection using Random Forest Regressor parameter optimization through the Salp Swarm Algorithm (SSA). Correlation analysis is used to identify most relevant Intrinsic Functions (IMFs) each appliance, while self-correlation determine past...