Telematics-based Internet of Things networks operate under severe energy constraints while facing continuous mobility, bursty traffic, and delay-sensitive data delivery. Routing inefficiencies in such environments directly shorten network lifetime and degrade service reliability. Most existing energy-aware routing approaches depend on reinforcement learning or centralized optimization, which introduce computational overhead, slow adaptation, and limited practicality in highly dynamic telematics scenarios. This study proposes a lightweight, mobility-aware energy-efficient routing framework that relies on localized decision metrics instead of learning-driven control. The routing strategy jointly considers residual energy, link stability, traffic load, and buffer occupancy to adapt paths in real time without global network state. Simulation results obtained over 30 independent runs show that the proposed framework improves packet delivery ratio by approximately 6-9% and extends network lifetime by about 12% compared to RLEAFS, LEA-RPL, and genetic algorithm–based routing schemes. End-to-end delay and routing control overhead are reduced by up to 15% under high- mobility and traffic- load conditions. The available solution provides a scalable and implementable routing system to the energy limited telematics IoT networks that strike a balance between efficiency, stability and operational simplicity.

Digital communication and automated control of smart grid networks are increasingly dependent on digital networks, which are susceptible to cyber-attacks that can be extended to physical disturbances of the power system. The current intrusion detection techniques are mostly based on the patterns of cyber traffic and can hardly differentiate between malicious and legitimate changes of operating variations in the dynamic grid settings. This paper presents a machine learning model grounded on energy to combine cyber-layer measurements with energy-space dynamics in a single learning representation. The method suggested uses physical consistency constraints in the classification process, which is not the case of the conventional cyber-only detectors. A simulation based smart grid dataset of 10,000 samples, and four operating classes. The proposed framework has a final detection accuracy equal to 95.8% and an F1-score of 0.95, which is 2-5% points higher than the typical baseline methods. The ablation analysis also proves the fact that the energy-domain features and constraints imposed by physical plausibility can add up to a significant increase of performance. The research results suggest that informed learning that considers physical considerations is an effective and viable way of achieving credible cyber security enhancement in smart grid networks.

The rapid expansion of renewable energy systems has contributed to the extensive use of cloud-based monitoring applications that receive and process massive amounts of operational telemetry information. Nevertheless, the dynamic and complex nature of renewable energy systems makes it difficult to detect abnormal behaviors that can adversely impact the reliability and efficiency of energy generation. This paper proposes an artificial intelligence-based anomaly detection system designed for cloud-controlled renewable energy systems. The proposed solution integrates deep representation learning models with a contextual drift-based anomaly scoring mechanism to identify anomalous operation patterns in multivariate renewable energy telemetry data. Normal system behavior is learned using an autoencoder-based architecture, and the proposed Context-Aware Residual Drift Scoring (CARDS) algorithm enhances anomaly detection by identifying contextual anomalies in system performance. Experimental evaluation was conducted on multivariate renewable energy telemetry data under cross-validation setups consistent with those used for comparison models. The proposed framework achieved a detection accuracy of 97.4% and an ROC–AUC score of 0.98, outperforming baseline algorithms such as Isolation Forest, LSTM-based detection, and Transformer-based models. These findings demonstrate that the suggested AI-based system offers a viable and scalable approach to enhancing reliability and operational intelligence in cloud-based renewable energy monitoring systems.

The growing adoption of communication and automation technology in smart energy grids has greatly amplified their vulnerability to cyber-attacks, and therefore, intrusion detection in a timely and reliable manner has become a pressing necessity. In this context, this paper will seek to fill this gap by introducing a hybrid fuzzy-deep learning framework, which combines uncertainty-sensitive feature modeling with spatiotemporal deep representation learning. A convolutional recurrent neural network is used to encode coordinated spatial and temporal patterns of attacks in the form of graded representations of raw grid and network measurements using the help of fuzzy logic. With this integration it is possible to have end to end learning in nonstationary and ambiguous operating conditions. The proposed framework achieves a detection accuracy of 97.6%, an F1-score of 0.96, and a false positive rate of 3.1%, outperforming representative machine learning and deep learning baselines. In addition, the average detection latency of 29.6 ms confirms its suitability for real-time monitoring applications. The primary value of the work is its ability to show that the systematic combination of the uncertainty modeling based on fuzzy with deep spatiotemporal learning can considerably increase the reliability of detection and the feasibility of operation, which can provide a viable way to achieve the goal of resilience in cybersecurity of smart energy grids.

The intelligent autonomous systems need to be reliable in the situations when there is uncertainty as well as nonlinear dynamics and time-varying disturbances. Traditional model-driven controllers are not flexible and purely learning-based models can be unstable and not easily interpretable. The current hybrid techniques strive to unite these paradigms, but they are generally based on offline optimization or loosely coupled structures of learning and control. This paper offers a hybrid soft computing and adaptive learning model based on combining fuzzy inference with an online learning process to make decisions in real-time. The fuzzy aspect provides the ability to deal with uncertainty and nonlinear mappings whereas the adaptive learning aspect optimizes control parameters through performance feedback with limited updates. Experimental analysis shows the presented framework can reach control accuracy of 95.2 which is 3-5 points better than the representative hybrid and learning-based baselines, with adaptation time lowered to 2.6 s. Stability analysis indicates a much lower level of control signal variance than with the unconstrained learning strategies. The primary value of the research is the single hybrid architecture that maintains the interpretability and allows further adaptation, which is a feasible and reliable solution to intelligent autonomous control in continuously evolving environments.

Cyber-attacks become manifested as a series of behavioral patterns, but not as an event, and many current security regimes stay based upon a static detection and fixed trust implementation. Such incongruence restricts their capability to act in a dependable manner in fluctuating and unpredictable threat situations. The existing artificial intelligence-based cybersecurity products mainly focus on the detection performance. Due to this, such systems will still be vulnerable to false positives, erratic reactions, and degradation of performance over time. This paper proposes a behavior-sensitive cybersecurity model that brings together sequential behavioral modelling, risk-adaptive cryptography implementation, and integrity-guaranteed learning in an architecture with closed loops. The temporally structured patterns of activity are considered as behavioral risk, which allows making proportional, not binary, trust decisions. Cryptographic policies are adaptively changed based on the inferenced risk, whereas learning updates are explicitly secured to maintain the model reliability as time goes by. The experimental findings indicate that the proposed framework can obtain a detection accuracy of 96.7% and F 1-score of 96.0, as well as a false positive rate decreased to 3.1%. Moreover, the adaptive response latency is also decreased by a factor of about 20-30% relative to the representative baselines and also enhanced stability in response to adversarial noise. These results indicate behavior-based intelligence.

The recent explosion of cyber threats in big data ecosystems has exposed the vulnerability of black-box machine learning models that prioritize accuracy over explainability. Traditional cybersecurity mechanisms do not create a sense as to why a prediction is provided and the analysts are left with doubts and the response mechanisms are slow. This is not very transparent and therefore compromises the operational trust and the traceability of high-risk decisions in real-time defense infrastructures. Current explainable AI (XAI) methods, despite their usefulness, are mostly stagnant, not connected to the changing situation of network behavior and human monitoring. They seldom inculcate the feedback mechanisms that can adjust the model explanations with new threat patterns. The research paper introduces an Explainable Artificial Intelligence and Data-Driven Security Analytics Framework that is hybrid and serves to combine global interpretability with SHAP, local reasoning with LIME, and adaptive refinement with an analyst-in-loop feedback layer. The architecture converts the threat detection to a self-fixing transparent process in which the analytical reasoning is dynamically developed with the data flow. In experimental tests of less than 10k concurrent traffic conditions, experimental results indicate that the system had a detection accuracy of 98.4 and Spearman correlation (0.91) between predicted risk scores and real levels of severity with a quantifiable 3.9% stability improvement over the similar XAI-based systems of intrusion detection. The combination of explainability with real-time analytics will further enhance the accuracy of detecting cyber threats and its interpretability reliability as well. The findings indicate the essential change to credible, self-explanatory, and adaptive security intelligence of the next-generation data networks.

Autonomous ground robots are increasingly relied upon in dynamic environments where reliable navigation and context-aware interaction are essential. However, existing robotic control systems often rely on cloud-based reinforcement learning (RL) frameworks or static algorithms that fail to adapt in real-time to noisy, unpredictable scenarios. These models typically overlook the constraints of edge deployment and lack robust integration with human interaction modalities such as voice and semantic object awareness. To address these limitations, this work proposes a fully embedded, IoT-enabled ground robot powered by a reinforcement learning-based adaptive control framework. The system leverages Raspberry Pi 4B+ as its core computational unit, integrating MQTT-driven communication, multimodal interaction through speech and vision, and lightweight policy convergence for obstacle-aware navigation. A novel RL-based state-action pipeline is trained and deployed entirely on-device, ensuring real-time responsiveness without external computation. Experimental evaluations show that the proposed framework reduces navigation errors by 22% and improves interaction latency by 37% over traditional PID and A*-based systems. The RL model converges in under 2200 episodes, with stable reward curves and high reliability across variable acoustic and physical terrains. This study showcases how low-cost, edge-based robots can achieve high autonomy and situational awareness contributing to future advancements in resilient, self-adaptive robotic systems within smart and resource-constrained environments.