Rachid Alaoui

Efficient allocation of electric vehicles (EVs) to charging stations in dense urban environments requires decision-making under partial observability and timevarying traffic demand. We present a controlled empirical comparison of two multiagent reinforcement learning paradigms for cooperative EV charging assignment in a SUMO-based urban network: Independent Q-Learning (IQL; DTDE) and QMIX (CTDE). Across 7 random seeds and 200 training episodes per seed (2,800 episodes in total), QMIX attains a mean training acceptance rate of 81.5±17.1%, versus 66.0 ± 16.8% for IQL. Under pure-greedy exploitation (ε=0, frozen weights, 32 episodes per seed), QMIX reaches 83.8±20.5% acceptance with 95.4% successper- accept, versus 64.4 ± 15.5% and 93.6% for IQL (Wilcoxon: T = 0, p ≤ 0.016; paired Cohen’s dz = 8.6). Non-RL baselines (NEAREST, WEIGHTED) accept all requests (100%) but incur higher timeout rates (9.3% and 4.1%), highlighting the value of learned selective acceptance. An ablation analysis suggests that, within this tabular-IQL vs. deep-QMIX comparison, CTDE/deep mixing— rather than reward shaping alone—better explains the gap.

Reproducible offline benchmarks for electric vehicle charging require explicit transition definitions and auditable data processing. We introduce IoEV-MARL, comprising 157,071 decision-level transitions from SUMO simulations of the road network of Tangier, Morocco, organized in a 62-column table. The corpus covers 700 collection episodes, seven seeds, four traffic regimes, and five behavioral arms: NEAREST, WEIGHTED, tabular Independent Q-Learning, and two QMIX checkpoint/exploration configurations. Learned collection policies originate from 120-episode training campaigns. A three-layer contract distinguishes decision-time observations, inter-decision elapsed time, and outcome/evaluation fields. Elapsed time is missing when no subsequent decision is recorded. The ETL protocol documents horizon censoring, missing successors, dimensional grain, and file-level provenance. Seven-fold leave-one-seed-out evaluations benchmark Behavior Cloning and offline Implicit Q-Learning on accept/reject decisions conditional on the selected station. Mean Behavior Cloning balanced accuracy ranges from 0.758 to 0.928 across tiers and feature sets, measuring imitation rather than operational performance. In matched greedy evaluation, QMIX has lower station-load dispersion in 7/7 seeds under Normal traffic, versus 2/7, 4/7, and 4/7 under Light, Peak, and Surge. Discrete-state audits characterize coverage gaps and structural reachability constraints. IoEV-MARL supports offline decision-learning research without establishing closed-loop performance gains.

Deep reinforcement learning (DRL) is widely assumed to outperform simpler rule-based and tabular baselines for sequential decision problems. We test this assumption for electric vehicle (EV) charging assignment using Simulation of Urban MObility (SUMO) simulations of real Rabat and Tangier road networks, with a protocol-amended, trained-vs-untrained diagnostic of Deep Q-Network (DQN) and Double DQN (DDQN) agents against untrained controls and an adaptive heuristic under a corrected pipeline and a not-yet-field-validated station-power regime. The primary endpoint, mean queue waiting time, is an assignment-to-arrival access delay. Trained policies are classified against a pre-specified 60 s rule using multiplicity-adjusted bootstrap intervals: of 12 pre-defined contrasts, none reaches the rule, two show a small detectable advantage, one is detrimental (softening to inconclusive with ten seeds), and nine are inconclusive. A legacy 210-run campaign predating the pipeline corrections is exploratory and shows no Holm-corrected difference. A reward/Markov decision process (MDP) audit identifies four structural defects and one replay sampling limitation; of the five audit-derived interventions, three were already active, one was structurally inert although enabled, and one showed no improvement. Exact per-contrast tests of the isolated ablations cannot reject at seven seeds; restoring R2 yields a small DDQN effect in one scenario that does not reproduce in a second. Two post hoc exploratory comparators, a deterministic minimum expected completion time dispatcher (MECT) and a discrete action proximal policy optimization (PPO) agent, are reported descriptively. The diagnostic does not separate under-training from a non-discriminative environment. The broader contribution is a reusable audit workflow for applied reinforcement learning benchmarks: endpoint semantic validation, trained-vs-untrained controls, multiplicity-adjusted inference and reward specification inspection.

Skin cancer is one of the most common diseases worldwide and, if left untreated, it can be life threatening. In this work, we propose a dual-branch deep learning framework that integrates a CNN–BiLSTM module for local spatial–sequential feature modeling with multiple transformer models (ViT, DeiT, SwinV2, and BEiT) for global representation learning. Each input image is processed in parallel by two branches. The first branch consists of a lightweight convolutional network, followed by row-wise and column-wise Bidirectional LSTM layers to capture spatial and sequential dependencies. The second branch employs a high-resolution transformer to extract features from the image. The features extracted from both branches of the hybrid CNN–BiLSTM–Transformer model are fused to construct a unified classifier for accurate skin lesion recognition. To further improve robustness, four CNN–BiLSTM–Transformer hybrid models are combined using a stacking strategy based on logistic regression that aggregates their prediction probabilities. Experimental results on the binary Kaggle and multi-class HAM10000 datasets demonstrate that stacking achieves better performance than the individual hybrid CNN–BiLSTM–Transformer models, reaching accuracies of 91.21% on the binary Kaggle dataset and 86.08 ± 0.47% on the HAM10000 dataset, respectively. These findings confirm the efficiency of using complementary local and global features for skin lesion classification.

This study presents a comprehensive comparative analysis of maximum power point tracking (MPPT) strategies for photovoltaic systems, focusing on the classical perturb and observe (P&O) method, an artificial intelligence based fuzzy logic controller (FLC), and a robust sliding mode control (SMC) technique. These methods aim to maximize power output by dynamically adapting to rapid and unpredictable environmental variations, such as changes in solar irradiance. Simulations performed the MATLAB/Simulink environment under diverse real-world scenarios demonstrate that SMC and FLC outperform the conventional P&O approach, particularly under conditions of sudden and severe environmental in fluctuations. The findings highlight the advanced controllers’ ability to sustain optimal power extraction, minimize energy losses, and maintain system stability across varying operating conditions. These results underscore the potential of SMC-based MPPT systems to enhance the efficiency and resilience of renewable energy applications, making them highly viable for deployment in real-world scenarios characterized by volatile environmental conditions.

This paper proposes a hybrid method for skin lesion classification combining deep learning features with conventional descriptors such as HOG, Gabor, SIFT, and LBP. Feature extraction was performed by extracting features of interest within the tumor area using suggested fusion methods. We tested and compared features obtained from different deep learning models coupled to HOG-based features. Dimensionality reduction and performance improvement were achieved by Principal Component Analysis, after which SVM was used for classification. The compared methods were tested on the reference database skin cancer-malignant-vs-benign. The results show a significant improvement in terms of accuracy due to complementarity between the conventional and deep learning-based methods. Specifically, the addition of HOG descriptors led to an accuracy increase of 5% for EfficientNetB0, 7% for ResNet50, 5% for ResNet101, 1% for NASNetMobile, 1% for DenseNet201, and 1% for MobileNetV2. These findings confirm that feature fusion significantly enhances performance compared to the individual application of each method.

The increasing demand for sustainable and efficient energy solutions has prompted extensive research into optimizing renewable energy sources in microgrid systems. This paper focuses on optimizing renewable energy sources within a standalone microgrid using particle swarm optimization (PSO) as the sole algorithm. The microgrid model proposed integrates photovoltaic (PV), wind, battery storage, and serves a load represented by an agricultural firm. Real-world data from Agdz in Ouarzazate, Morocco, is utilized for analysis. The primary objective is to minimize excess production from PV and wind sources when the battery reaches full charge. This research addresses the increasing demand for sustainable energy solutions by emphasizing a single optimization technique, PSO, for achieving a balanced and efficient energy generation system. The study aims to closely align energy production with load demand to reduce wastage and ensure a reliable energy supply within the microgrid. The evaluation is conducted based on the ability of the PSO algorithm to diminish the gap between total energy production and load demand. The use of the PSO algorithm resulted in a 30% reduction in excess energy, effectively mitigating unnecessary energy wastage when the battery is fully charged. This outcome highlights the algorithm's capacity to adapt and optimize energy production from primary sources to precisely align with the specific requirements of the load

The electric vehicle (EV) is considered an attractive alternative to a conventional vehicle, due to its potential beneficiation in decreasing carbon emission. But the battery range anxiety is a key challenge to its wide adoption and also the EV drivers spend so much time in public charging stations (CS) to charge especially during peak times. In this paper, we propose a charging station selected system (C3S) to control and manage EVs charging plans. Moreover, the C3S system proposed consists of a set of algorithms that are proposed to recommend a suitable CS for EV charging requests. The CS selection is based on minimizing travel time and takes into account in real-time the queuing time at CS, EVs' charging reservations, and the predicted time of EVs' future charging requests. Besides, we proposed three different strategies for predicting the EVs incoming and controlling the uncertainty matter of the dynamic arrival of EV charging requests. As part of the Helsinki City scenario, the evaluation results demonstrate the performance, especially at peak times, of our proposed C3S with regard to the CS recommendation which has the minimum total trip duration.