Low-latency content delivery is essential in the Internet of Vehicles (IoV) to support autonomous driving, cooperative perception, and infotainment services. However, rapidly changing vehicular mobility and demand patterns limit the effectiveness of existing content prediction and caching strategies, which often capture either short-term temporal trends or long-range dependencies, but not both. This paper proposes a hybrid deep learning architecture that integrates Long Short-Term Memory (LSTM) networks with Transformer encoders to jointly model fine-grained temporal dynamics and global correlations in content requests. The resulting popularity predictions are incorporated into a reinforcement learning (RL)-based caching policy, enabling proactive and adaptive cache placement at roadside units (RSUs) within an end-to-end optimization framework. Simulation results across representative IoV scenarios show that the proposed approach consistently improves cache hit ratio, retrieval latency, and prediction accuracy compared with LSTM-only, Transformer-only, Least Frequently Used (LFU), and Least Recently Used (LRU) baselines. Ablation studies further demonstrate the complementary strengths of the hybrid components, highlighting improved convergence behavior and robustness under varying demand distributions.

Low-latency content delivery is essential in the Internet of Vehicles (IoV) to support autonomous driving, cooperative perception, and infotainment services. However, rapidly changing vehicular mobility and demand patterns limit the effectiveness of existing content prediction and caching strategies, which often capture either short-term temporal trends or long-range dependencies, but not both. This paper proposes a hybrid deep learning architecture that integrates Long Short-Term Memory (LSTM) networks with Transformer encoders to jointly model fine-grained temporal dynamics and global correlations in content requests. The resulting popularity predictions are incorporated into a reinforcement learning (RL)-based caching policy, enabling proactive and adaptive cache placement at roadside units (RSUs) within an end-to-end optimization framework. Simulation results across representative IoV scenarios show that the proposed approach consistently improves cache hit ratio, retrieval latency, and prediction accuracy compared with LSTM-only, Transformer-only, Least Frequently Used (LFU), and Least Recently Used (LRU) baselines. Ablation studies further demonstrate the complementary strengths of the hybrid components, highlighting improved convergence behavior and robustness under varying demand distributions.

Low-latency content delivery is essential in the Internet of Vehicles (IoV) to support autonomous driving, cooperative perception, and infotainment services. However, rapidly changing vehicular mobility and demand patterns limit the effectiveness of existing content prediction and caching strategies, which often capture either short-term temporal trends or long-range dependencies, but not both. This paper proposes a hybrid deep learning architecture that integrates Long Short-Term Memory (LSTM) networks with Transformer encoders to jointly model fine-grained temporal dynamics and global correlations in content requests. The resulting popularity predictions are incorporated into a reinforcement learning (RL)-based caching policy, enabling proactive and adaptive cache placement at roadside units (RSUs) within an end-to-end optimization framework. Simulation results across representative IoV scenarios show that the proposed approach consistently improves cache hit ratio, retrieval latency, and prediction accuracy compared with LSTM-only, Transformer-only, Least Frequently Used (LFU), and Least Recently Used (LRU) baselines. Ablation studies further demonstrate the complementary strengths of the hybrid components, highlighting improved convergence behavior and robustness under varying demand distributions.

Low-latency content delivery is essential in the Internet of Vehicles (IoV) to support autonomous driving, cooperative perception, and infotainment services. However, rapidly changing vehicular mobility and demand patterns limit the effectiveness of existing content prediction and caching strategies, which often capture either short-term temporal trends or long-range dependencies, but not both. This paper proposes a hybrid deep learning architecture that integrates Long Short-Term Memory (LSTM) networks with Transformer encoders to jointly model fine-grained temporal dynamics and global correlations in content requests. The resulting popularity predictions are incorporated into a reinforcement learning (RL)-based caching policy, enabling proactive and adaptive cache placement at roadside units (RSUs) within an end-to-end optimization framework. Simulation results across representative IoV scenarios show that the proposed approach consistently improves cache hit ratio, retrieval latency, and prediction accuracy compared with LSTM-only, Transformer-only, Least Frequently Used (LFU), and Least Recently Used (LRU) baselines. Ablation studies further demonstrate the complementary strengths of the hybrid components, highlighting improved convergence behavior and robustness under varying demand distributions.

Low-latency content delivery is essential in the Internet of Vehicles (IoV) to support autonomous driving, cooperative perception, and infotainment services. However, rapidly changing vehicular mobility and demand patterns limit the effectiveness of existing content prediction and caching strategies, which often capture either short-term temporal trends or long-range dependencies, but not both. This paper proposes a hybrid deep learning architecture that integrates Long Short-Term Memory (LSTM) networks with Transformer encoders to jointly model fine-grained temporal dynamics and global correlations in content requests. The resulting popularity predictions are incorporated into a reinforcement learning (RL)-based caching policy, enabling proactive and adaptive cache placement at roadside units (RSUs) within an end-to-end optimization framework. Simulation results across representative IoV scenarios show that the proposed approach consistently improves cache hit ratio, retrieval latency, and prediction accuracy compared with LSTM-only, Transformer-only, Least Frequently Used (LFU), and Least Recently Used (LRU) baselines. Ablation studies further demonstrate the complementary strengths of the hybrid components, highlighting improved convergence behavior and robustness under varying demand distributions.

Low-latency content delivery is essential in the Internet of Vehicles (IoV) to support autonomous driving, cooperative perception, and infotainment services. However, rapidly changing vehicular mobility and demand patterns limit the effectiveness of existing content prediction and caching strategies, which often capture either short-term temporal trends or long-range dependencies, but not both. This paper proposes a hybrid deep learning architecture that integrates Long Short-Term Memory (LSTM) networks with Transformer encoders to jointly model fine-grained temporal dynamics and global correlations in content requests. The resulting popularity predictions are incorporated into a reinforcement learning (RL)-based caching policy, enabling proactive and adaptive cache placement at roadside units (RSUs) within an end-to-end optimization framework. Simulation results across representative IoV scenarios show that the proposed approach consistently improves cache hit ratio, retrieval latency, and prediction accuracy compared with LSTM-only, Transformer-only, Least Frequently Used (LFU), and Least Recently Used (LRU) baselines. Ablation studies further demonstrate the complementary strengths of the hybrid components, highlighting improved convergence behavior and robustness under varying demand distributions.

Low-latency content delivery is essential in the Internet of Vehicles (IoV) to support autonomous driving, cooperative perception, and infotainment services. However, rapidly changing vehicular mobility and demand patterns limit the effectiveness of existing content prediction and caching strategies, which often capture either short-term temporal trends or long-range dependencies, but not both. This paper proposes a hybrid deep learning architecture that integrates Long Short-Term Memory (LSTM) networks with Transformer encoders to jointly model fine-grained temporal dynamics and global correlations in content requests. The resulting popularity predictions are incorporated into a reinforcement learning (RL)-based caching policy, enabling proactive and adaptive cache placement at roadside units (RSUs) within an end-to-end optimization framework. Simulation results across representative IoV scenarios show that the proposed approach consistently improves cache hit ratio, retrieval latency, and prediction accuracy compared with LSTM-only, Transformer-only, Least Frequently Used (LFU), and Least Recently Used (LRU) baselines. Ablation studies further demonstrate the complementary strengths of the hybrid components, highlighting improved convergence behavior and robustness under varying demand distributions.

Low-latency content delivery is essential in the Internet of Vehicles (IoV) to support autonomous driving, cooperative perception, and infotainment services. However, rapidly changing vehicular mobility and demand patterns limit the effectiveness of existing content prediction and caching strategies, which often capture either short-term temporal trends or long-range dependencies, but not both. This paper proposes a hybrid deep learning architecture that integrates Long Short-Term Memory (LSTM) networks with Transformer encoders to jointly model fine-grained temporal dynamics and global correlations in content requests. The resulting popularity predictions are incorporated into a reinforcement learning (RL)-based caching policy, enabling proactive and adaptive cache placement at roadside units (RSUs) within an end-to-end optimization framework. Simulation results across representative IoV scenarios show that the proposed approach consistently improves cache hit ratio, retrieval latency, and prediction accuracy compared with LSTM-only, Transformer-only, Least Frequently Used (LFU), and Least Recently Used (LRU) baselines. Ablation studies further demonstrate the complementary strengths of the hybrid components, highlighting improved convergence behavior and robustness under varying demand distributions.

Low-latency content delivery is essential in the Internet of Vehicles (IoV) to support autonomous driving, cooperative perception, and infotainment services. However, rapidly changing vehicular mobility and demand patterns limit the effectiveness of existing content prediction and caching strategies, which often capture either short-term temporal trends or long-range dependencies, but not both. This paper proposes a hybrid deep learning architecture that integrates Long Short-Term Memory (LSTM) networks with Transformer encoders to jointly model fine-grained temporal dynamics and global correlations in content requests. The resulting popularity predictions are incorporated into a reinforcement learning (RL)-based caching policy, enabling proactive and adaptive cache placement at roadside units (RSUs) within an end-to-end optimization framework. Simulation results across representative IoV scenarios show that the proposed approach consistently improves cache hit ratio, retrieval latency, and prediction accuracy compared with LSTM-only, Transformer-only, Least Frequently Used (LFU), and Least Recently Used (LRU) baselines. Ablation studies further demonstrate the complementary strengths of the hybrid components, highlighting improved convergence behavior and robustness under varying demand distributions.

first_page

settings

Order Article Reprints

first_page

settings

Order Article Reprints

first_page

settings

Order Article Reprints

first_page

settings

Order Article Reprints

first_page

settings

Order Article Reprints

first_page

settings

Order Article Reprints

Sétif City, located in the Eastern High-lands of Algeria, faces a resurgence of urban flooding, a phenomenon exacerbated by the soil sealing resulting from rapid urbanization (+351.67% between 1986 and 2021) and the under-sizing of drainage infrastructure. In the context of a lack of integrated spatial assessment tools, this study aims to evaluate and map the flood vulnerability of the urban area by coupling Geographic Information Systems (GIS) and the Analytical Hierarchy Process (AHP). The methodology integrated seven vulnerability criteria (five physicals and two socio-economic), whose AHP-based weighting was judged reliable (Consistency Ratio: 6.4%). The results reveal that 45.65% of Sétif’s urban area (339.22 hectares) exhibits high to very high vulnerability. The AHP analysis identified slope (33.7% of the weight) and land use (29.1% of the weight) as the major determinants of this vulnerability. Critical areas, notably Ararsa, Yahyaoui, and Aïn Sebaâ districts, are characterized by the combination of gentle slopes and a high density of infrastructure. This work confirms the relevance of the AHP-GIS coupling in providing local authorities with an essential decision support tool for the revision of the Master Plan for Development and Urban Planning (PDAU) and for more resilient urban planning.

Sétif City, located in the Eastern High-lands of Algeria, faces a resurgence of urban flooding, a phenomenon exacerbated by the soil sealing resulting from rapid urbanization (+351.67% between 1986 and 2021) and the under-sizing of drainage infrastructure. In the context of a lack of integrated spatial assessment tools, this study aims to evaluate and map the flood vulnerability of the urban area by coupling Geographic Information Systems (GIS) and the Analytical Hierarchy Process (AHP). The methodology integrated seven vulnerability criteria (five physicals and two socio-economic), whose AHP-based weighting was judged reliable (Consistency Ratio: 6.4%). The results reveal that 45.65% of Sétif’s urban area (339.22 hectares) exhibits high to very high vulnerability. The AHP analysis identified slope (33.7% of the weight) and land use (29.1% of the weight) as the major determinants of this vulnerability. Critical areas, notably Ararsa, Yahyaoui, and Aïn Sebaâ districts, are characterized by the combination of gentle slopes and a high density of infrastructure. This work confirms the relevance of the AHP-GIS coupling in providing local authorities with an essential decision support tool for the revision of the Master Plan for Development and Urban Planning (PDAU) and for more resilient urban planning.

Sétif City, located in the Eastern High-lands of Algeria, faces a resurgence of urban flooding, a phenomenon exacerbated by the soil sealing resulting from rapid urbanization (+351.67% between 1986 and 2021) and the under-sizing of drainage infrastructure. In the context of a lack of integrated spatial assessment tools, this study aims to evaluate and map the flood vulnerability of the urban area by coupling Geographic Information Systems (GIS) and the Analytical Hierarchy Process (AHP). The methodology integrated seven vulnerability criteria (five physicals and two socio-economic), whose AHP-based weighting was judged reliable (Consistency Ratio: 6.4%). The results reveal that 45.65% of Sétif’s urban area (339.22 hectares) exhibits high to very high vulnerability. The AHP analysis identified slope (33.7% of the weight) and land use (29.1% of the weight) as the major determinants of this vulnerability. Critical areas, notably Ararsa, Yahyaoui, and Aïn Sebaâ districts, are characterized by the combination of gentle slopes and a high density of infrastructure. This work confirms the relevance of the AHP-GIS coupling in providing local authorities with an essential decision support tool for the revision of the Master Plan for Development and Urban Planning (PDAU) and for more resilient urban planning.