Kishu Gupta

This article is framed as a systematic review with original illustrative benchmarking of reinforcement learning (RL) for smart microgrid (SMG) control, communication, and simulation-to-real deployment. Although prior surveys have reviewed RL for microgrid energy management, they have not jointly analyzed control-communication co-design, adversarial robustness, federated and multi-agent coordination, and Sim2Real validation under one reproducible review protocol. To address this gap, we synthesize more than 160 peer-reviewed studies published between 2015 and 2025 and organize the literature through an explicit taxonomy covering RL family, control objective, communication dependency, validation level, cyber-resilience mechanism, and deployment maturity. The review compares algorithms, protocols, simulation platforms, and validation practices across scalability, latency sensitivity, robustness, privacy preservation, convergence behavior, and real-world readiness. In addition to the systematic synthesis, we report an illustrative benchmark using SUMO-RL-derived demand traces coupled to pymgrid to compare representative RL controllers under normalized control and communication metrics. The analysis shows that policy-gradient and multi-agent variants often provide stronger adaptability under dynamic operating conditions, but no single algorithm dominates across cost, latency, resilience, and deployment complexity. The paper concludes by identifying reproducibility, communication-aware validation, safety-constrained RL, privacy-preserving aggregation, and high-fidelity cyber–physical digital twins as the main barriers to trustworthy RL deployment in SMGs.

The significant upsurge in vehicle traffic presents a considerable challenge in the pursuit of smart mobilization and transportation (SMT) worldwide.Current approaches primarily focus on vehicular traffic management through congestion prediction but fall short in addressing essential objectives such as traffic reduction and appropriate vehicle selection to alleviate congestion in smart cities ($SmCt$). To address these concerns, this work introduces a novel Neighbor-Embedded Graph Neural Network-based Crowd Delivery Traffic Management (NeCDM) Model, comprising two key components: the Traffic Congestion Prediction Unit (TCPu) and the Traffic Observation and Management Unit (TOMu). The TCPu utilizes Graph Neural Network (GNN) optimization to accurately predict traffic flow levels at various delivery stations within $SmCt$ ecosystems. Additionally, the TOMu facilitates the intelligent selection of the most suitable delivery vehicles for fulfilling crowd delivery requests ($CDR$). This work emphasizes the potential of crowd delivery as a feasible solution for achieving SMT goals while adhering to smart city parameters ($\mathcal {SCP}$s), such as reduced carbon emissions, shorter travel times, and minimized travel distances. The proposed model achieves notable improvements in computational efficiency, including reductions of up to 4.03% in L1 loss ($\pounds$), 16.66% in L2 loss ($\pounds_{rmse}$), and 7.64% in computation time.

NeuroEvolution refers to the use of evolutionary algorithms to optimize neural network parameters and, in some cases, network architectures. The provided document outlines the fundamental components of evolutionary computation when applied to neural networks, including chromosome representation, population initialization, fitness evaluation, selection, crossover, mutation, replacement, and termination criteria. These processes collectively enable a population of neural-network-based solutions to evolve over time toward better performance on a given task. Additionally, the document highlights the role of population diversity and discusses how mechanisms such as elitism and diversity monitoring help avoid premature convergence. This work summarizes these concepts and bases a methodological framework on the principles presented.

In today’s digital landscape, high-efficiency video coding (H.265/HEVC) has emerged as the most widely used video coding standard, employing selective encryption schemes to protect the privacy of video content while maintaining efficient compression performance. However, existing coefficient scrambling methods impose a significant computational load, leading to increased bit rate overhead due to encryption, longer execution times, and insufficient safety measures. To address these issues, a new coefficient scrambling scheme based on chaotic maps is proposed. This approach leverages the pseudorandomness, ergodicity, and sensitivity to initial conditions inherent in chaotic maps to generate highly unpredictable coefficient distributions, thereby strengthening security while preserving low complexity. Unlike conventional scrambling, chaotic maps ensure minimal correlation between encrypted coefficients, enhancing resistance against statistical and differential attacks. Additionally, the scrambling conditions are specifically designed to minimize the impact on the bit rate overhead. Furthermore, when combined with syntax element encryption (SEC), which includes motion vector difference (MVD), quantized transform coefficients (QTC), and luma intraprediction mode (Luma IPM), this method effectively distorts video content. The proposed scheme operates synchronously with slices, ensuring that the decryption of video content remains intact even if some slices are lost. Additionally, a random sequence generated by AES-CTR is incorporated with the H.265 encoded stream to protect against chosen-plaintext attacks. The experimental results indicate that this scheme features high security, compliance with format standards, fast execution times, synchronous updates with slices, and resilience against common attacks, all while achieving a reduced bit rate overhead of 45.13% with a lowered average execution time overhead of 1.91%.

The increasing adoption of Large Language Models (LLMs) has intensified concerns regarding the sustainability of their supply chains, particularly concerning energy consumption, resource utilization, and carbon emissions. To address these concerns, this study proposes a two-step approach. First, a Delphi method is employed to systematically identify the critical factors affecting the sustainability of LLM supply chains. Expert consensus through four rounds of feedback highlights key factors such as Environmental Impact, Computational Efficiency & Resource Optimization, Data Quality & Ethical Considerations, and Social Responsibility & Governance. In the second step, the identified factor’s relative importance was calculated using Conjoint Analysis, a statistical technique used to determine how respondents value different factors of a supply chain of LLMs. This prioritization helps formulate strategies to make LLM’s supply chain sustainable. The low score for environmental impact suggests a lack of awareness about the sustainability of LLMs’ supply chain. The study finds Data Quality and Ethical considerations to be the most important considerations for the respondents. Thus, it provides a framework for implementing sustainable practices in LLMs’ supply chains in resource-constrained settings. The results demonstrate the effectiveness of this combined Delphi-Conjoint Analysis approach, providing actionable insights for AI organizations aiming to enhance the sustainability of their LLM operations.

Accurate workload prediction and advanced resource reservation are indispensably crucial for managing dynamic cloud services. Traditional neural networks and deep learning models frequently encounter challenges with diverse, high-dimensional workloads, especially during sudden resource demand changes, leading to inefficiencies. This issue arises from their limited optimization during training, relying only on parametric (interconnection weights) adjustments using conventional algorithms. To address this issue, this work proposes a novel comprehensively adaptive architectural optimization-based variable quantum neural network (CA-QNN), which combines the efficiency of quantum computing with complete structural and qubit vector parametric learning. The model converts workload data into qubits, processed through qubit neurons with controlled not-gated activation functions for intuitive pattern recognition. In addition, a comprehensive architecture optimization algorithm for networks is introduced to facilitate the learning and propagation of the structure and parametric values in variable-sized quantum neural networks (VQNNs). This algorithm incorporates quantum adaptive modulation (QAM) and size-adaptive recombination during the training process. The performance of the CA-QNN model is thoroughly investigated against seven state-of-the-art methods across four benchmark datasets of heterogeneous cloud workloads. The proposed model demonstrates superior prediction accuracy, reducing prediction errors by up to 93.40% and 91.27% compared to existing deep learning and QNN-based approaches.

In the era of crowd delivery vehicle routing and traffic management in smart cities, a complex challenge appears indistinctly, affecting both developed and developing nations worldwide. This challenging problem involves optimizing multi-depot routes while addressing various hurdles: minimizing travel time, distance, fuel consumption, and carbon emissions, all while navigating dynamic traffic congestion across diverse pathways. Existing approaches often focus on isolated aspects like shortest paths, carbon emissions, or traffic prediction, leaving the comprehensive multi-depot traffic management problem unaddressed. In response, this research work proposes an Intelligent Multi-Depot Vehicle Routing and Management (IM-VRM) model which provides a comprehensive and holistic solution. It employs a Graph Neural Network (GNN) learning-based routing with a greedy optimization to establish initial optimal pathways for multi-depot journeys. Subsequently, the IM-VRM model integrates traffic congestion prediction with green parameter computation, engaging the Dijkstra algorithm to select the most admissible routes. This consecutive steps-based travel route guidance process optimizes routing for heterogeneous vehicles, including both heavy-duty and light-duty types. It accounts for load-dependent fuel consumption, velocity, and carbon emissions. By doing so, it simplifies the complexities of multi-depot traffic routing and management. The proposed model has been rigorously evaluated using a real-world multi-depot traffic dataset, demonstrating its practical viability. Notably, IM-VRM model achieves a remarkable improvement in fuel savings, reduced carbon emissions, and shorter travel time outperforming previous state-of-the-art methods in both efficiency and precision.

Secure resource management (SRM) within a cloud computing environment is a critical yet infrequently studied research topic. This article provides a comprehensive survey and comparative performance evaluation of potential cyber threat countermeasure strategies that address security challenges during cloud workload execution and resource management. Cybersecurity is explored specifically in the context of cloud resource management, with an emphasis on identifying the associated challenges. The cyber threat countermeasure methods are categorized into three classes: defensive strategies, mitigating strategies, and hybrid strategies. The existing countermeasure strategies belonging to each class are thoroughly discussed and compared. In addition to conceptual and theoretical analysis, the leading countermeasure strategies within these categories are implemented on a common platform and examined using two real-world virtual machine (VM) data traces. Based on this comprehensive study and performance evaluation, this article discusses the tradeoffs among these countermeasure strategies and their utility, providing imperative concluding remarks on the holistic study of cloud cyber threat countermeasures and SRM. Furthermore, the study suggests future methodologies that could effectively address the emerging challenges of secure cloud resource management.

Data is a vital asset for any organization and are needed to be safeguarded against the deliberate damage or unintentional loss. In industry enormous volumes of data are exchanged constantly, which increases the risk of vulnerabilities, breaches, and alterations. Ensuring both data security and accessibility is essential. Data leakage/ breach means the unintentional distribution of sensitive information to unauthorized parties. This paper examines the concept of data leakage, Data Leakage Detection (DLD), and identification techniques, along with a literature review of existing methods. This paper highlight various data security strategies aim to improve the detection of responsible parties, known as culprit, who may be individuals or groups causing breaches.