The stakes are enormous. Fifth-generation technology, commercialized in 2019, can connect roughly one million devices in an area of 0.38 square miles, deliver peak data throughput of 20 gigabits per second, and achieve minimum latency of one millisecond. Yet the survey’s authors argue that 5G shows restricted flexibility in dynamic contexts. Vehicular services demand ultra-low latency and high reliability simultaneously, and the varied, rigorous requirements of Vehicle-to-Everything communication, known as V2X, often exceed what 5G can guarantee. Beyond 5G and especially sixth-generation networks are anticipated to close that gap by tapping higher frequency spectrum, enabling more network capacity with substantially reduced latency.

The core innovation the survey examines is network slicing, a technique that divides a single physical network into multiple logically separate networks, each tailored to the needs of a different service. In a vehicular context, one slice might serve safety-critical messages between cars, another might carry infotainment streams for passengers, and a third might handle bulk sensor uploads for autonomous driving algorithms. Because each slice can be designed with its own quality of service guarantees, network slicing has significantly enhanced the growth of vehicular networks. The approach relies on softwarization technologies such as software-defined networking and network functions virtualization, which let operators carve, configure, and reconfigure slices on demand rather than through fixed hardware.

But slicing alone is not enough, and this is where the survey’s central argument emerges. Vehicles are, by definition, mobile, and high mobility is one of the defining characteristics of vehicular network members. When a car crosses from one cell to another, or from one network domain to a completely different one, its slice relationships must travel with it. Mobility management is the set of techniques that dynamically preserves these slice relationships and quality of service guarantees while users or devices move. In advanced vehicular networks, the authors emphasize, network slicing and mobility management are two key components that must collaborate to ensure quality of service. A slice that cannot follow the vehicle is a broken promise.

The difficulty is that vehicular surroundings are dynamic and varied in ways that defeat traditional, rule-based mobility management. Handover decisions, the moments when a connection transfers between base stations or between slices, depend on signal quality, traffic load, vehicle speed, and prediction of future position, all changing from second to second. Conventional schemes with fixed parameters, such as static handover thresholds and time-to-trigger values, struggle to adapt. The survey reviews a range of critical techniques for mobility management in 6G vehicular networks, including handover optimization, dual connectivity, positioning and localization methods, and predictive approaches that anticipate where a vehicle will be before the connection needs to move.

Enter deep reinforcement learning, a machine learning technique that combines deep neural networks with the trial-and-error logic of reinforcement learning. In this framework, an agent observes the state of its environment, takes an action, and receives a reward or penalty, gradually learning a policy that maximizes long-term benefit. Deep neural networks allow the agent to handle enormous, high-dimensional state spaces, such as the full radio and traffic conditions of a highway segment, that would overwhelm tabular methods. Algorithms surveyed in the paper include deep Q-networks and their variants, actor-critic families such as proximal policy optimization and soft actor-critic, and multi-agent extensions in which several learning agents cooperate to manage shared resources.

The applications documented in the survey span the entire vehicular networking stack. Deep reinforcement learning has been applied to radio access network slicing for cellular V2X, to resource allocation among competing slices, to task offloading in vehicular edge computing, and to handover decisions in heterogeneous networks. Multi-agent deep reinforcement learning approaches have been used for network slicing in vehicular communications, where distributed agents coordinate slice resources without a central controller. The technique has also been applied to beam management in millimeter-wave systems, trajectory planning for unmanned aerial vehicles that assist ground networks, and joint optimization of caching, computing, and radio resources. In each case, the promise is the same: adaptive, experience-driven decisions that outperform static rules in environments no engineer could fully anticipate.

Why does this matter beyond the laboratory? The advancement of transportation, the authors note, affects multiple facets of people’s lives, encompassing the economy, tourism, and healthcare. Reliable V2X communication underpins emergency vehicle prioritization, platooning, cooperative perception for autonomous driving, and remote monitoring applications. A network that drops a safety message during a handover is not merely inconvenient; it can be dangerous. By combining network slicing, which guarantees per-service resources, with intelligent mobility management, which guarantees continuity of those guarantees under motion, 6G vehicular networks aim to make connected driving dependable enough for safety-critical deployment. The survey also situates this within a broader 6G toolkit that includes intelligent reflecting surfaces, integrated sensing and communication, digital twin networks, and non-terrestrial components such as low Earth orbit satellites.

The authors are careful about limitations. They state that the use of deep reinforcement learning is a beneficial method to improve mobility management in sliced vehicular networks, but that further studies are required. Open challenges include the exploration problem in reinforcement learning, the training cost and sample efficiency of deep agents, the interpretability of learned policies, and the security of learning-based slicing systems, an area where federated learning approaches are being explored to detect attacks across sliced networks. Standardization efforts, including the ITU’s IMT-2030 framework for 6G and the Open Radio Access Network architecture, will shape how intelligent mobility management is actually deployed.

To encourage further work, the survey outlines potential future research objectives, ranging from end-to-end slice mobility across heterogeneous domains to explainable AI for resource management in vehicular network slicing. The authors hope the survey will help researchers understand in depth the concept of network slicing in vehicular networks and the impact of mobility management in sliced environments. For the rest of us, the message is simpler: the self-driving future depends not just on smarter cars, but on networks smart enough to learn, adapt, and never let go of a moving vehicle’s connection, no matter how fast the road unfurls beneath it.

Subject of Research: Deep reinforcement learning for mobility management in sliced 6G vehicular networks

Article Title: Applying deep reinforcement learning to manage mobility in a sliced 6G vehicular network: a survey

Article References: Amaira, A., & Zarai, F. (2026). Applying deep reinforcement learning to manage mobility in a sliced 6G vehicular network: a survey. Cluster Computing, 29(14), Article 820. https://doi.org/10.1007/s10586-026-06606-8

Image Credits: AI Generated

DOI: 10.1007/s10586-026-06606-8

Keywords: 6G, vehicular networks, network slicing, mobility management, deep reinforcement learning, V2X, 5G, handover, machine learning, quality of service, edge computing, beyond 5G

Named Data Networking is one of the most prominent clean-slate redesigns of the internet’s core. Instead of delivering packets to numeric host addresses, NDN routes traffic by name: a consumer expresses interest in a piece of named data, and the network fetches it from wherever it lives. Routers keep track of pending requests in a Pending Interest Table, the PIT, which records where each Interest came from so the matching Data packet can be sent back along the reverse path. This design makes content caching natural and decouples data from location, which sounds ideal for mobile users. Yet mobility still creates friction, because the forwarding paths that carry data toward a consumer were set up when the consumer was attached to a different access point.

The friction becomes acute in push mode. In classical pull-based NDN, each Interest retrieves exactly one Data packet, so a moving consumer simply re-issues Interests from its new location and the network rebuilds paths packet by packet. Push-based communication changes that bargain. Using a construct known as a Persistent Interest, a consumer issues a single request and the producer then pushes a continuous stream of Data packets back without waiting for further Interests. This is far more efficient for real-time streaming, because it removes the round-trip delay of asking for every packet individually. The catch is that the forwarding state installed for that Persistent Interest is long-lived, and when the consumer hands over to a new access point, the old path lingers in the network as a ghost.

Those ghost paths, the researchers explain, are not merely cosmetic clutter. Until the PIT entries on the stale route expire, the network keeps wasting bandwidth by trying to deliver packets toward a location the consumer has already left, and the stream itself is disrupted because the new path has not yet been established. The persistence duration of a stale path, measured from the moment of handover to the moment the network has fully cleaned it up, is therefore a critical performance metric, and the team provides what they describe as a reproducible benchmark of this path-cleanup efficiency for each scheme they tested.

Graft and Prune is best understood as an engineering refinement of an earlier idea. A prior mechanism called Prune-and-Graft, or P&G, first removes the stale path and then establishes a new one toward the producer. That ordering works, but it opens a data-loss window in one-to-one communication: between the prune and the graft, packets have nowhere to go. The new scheme simply reverses the sequence. It grafts a fresh forwarding path toward the producer first, and only then prunes the stale one. By keeping the old path alive until the new one is ready, G&P preserves data continuity throughout the handover, eliminating the loss window that P&G incurs.

Three properties distinguish the design. It is lightweight, adding minimal signaling overhead to an already busy handover moment. It is anchor-less, meaning it does not depend on any fixed rendezvous point, home agent, or mobility anchor in the network, which keeps the architecture true to NDN’s location-independent philosophy. And it is fully NDN-compliant, requiring no changes to the packet formats or forwarding semantics that the architecture already defines. In a field where many mobility proposals quietly break the protocol’s rules, that compliance matters, because it means the mechanism could in principle be deployed on standard NDN routers without architectural surgery.

To find out whether the idea survives contact with reality, the team evaluated G&P against three anchor-less baselines: Prune-and-Graft, Path Stretch, and Bit Embedding. The experiments used ndnSIM, an open-source simulator for NDN built on the ns-3 network simulator, and ran two separate simulation campaigns, one with a stationary producer and one with a mobile producer, covering both one-to-one consumer scenarios and one-to-many scenarios in which several consumers follow the same stream. Consumer mobility speeds were varied across the trials to see how each scheme behaves for a pedestrian, a cyclist, or a fast-moving vehicle.

The results, reported in the journal Multimedia Tools and Applications, show that G&P maintains competitive performance on all state-of-the-art metrics compared with the baseline schemes across every tested condition, and that it scales gracefully as the number of consumers increases. That last point is significant for the one-to-many case, which mirrors how live streaming actually works in the wild: many viewers attached to the same producer, each potentially moving at a different moment. A mechanism that degrades as the audience grows would be a poor fit for that workload, whereas one that holds its performance under load is a genuine candidate for deployment.

The work arrives at a moment when the traffic patterns of the mobile internet are tilting heavily toward exactly the kind of continuous, delay-sensitive streams that push mode is designed to serve. Industry forecasts cited in the paper project that 5G will carry more than 80 percent of total mobile traffic by 2030, rising to 83 percent by 2031, with global mobile data traffic growing steadily through the decade. Video streaming, video calling, and interactive applications dominate that growth, and all of them punish the packet loss and service disruption that stale forwarding paths cause during handover. A protocol that shortens the window of disruption, or removes it entirely, translates directly into fewer frozen frames and fewer dropped calls.

The researchers, Achraf Gazdar, Aljawharah Almuaythir, and Muna Al-Razgan of the Department of Software Engineering at King Saud University, position G&P as a robust and practical protocol for real-time push-based streaming in mobile NDN environments rather than a theoretical curiosity. Its contribution is deliberately modest in scope and large in consequence: a reordering of two well-understood operations, graft before prune, that closes a data-loss window, plus a systematic characterization of how long stale paths haunt the network under each competing scheme. As Named Data Networking research matures from architecture papers toward deployable protocols, refinements of this kind, which respect the architecture’s constraints while fixing its mobility blind spots, are the pieces that will determine whether content-centric networking can deliver on its promise for the mobile, streaming-dominated internet now taking shape.

Subject of Research: Consumer mobility management in Named Data Networking under push communication mode for real-time streaming

Article Title: Graft and Prune: enhanced consumer mobility in NDN under push communication mode in real-time streaming applications

Article References: Gazdar, A., Almuaythir, A., & Al-Razgan, M. (2026). Graft and Prune: enhanced consumer mobility in NDN under push communication mode in real-time streaming applications. Multimedia Tools and Applications, 85(10), Article 763. https://doi.org/10.1007/s11042-026-21917-z

Image Credits: AI Generated

DOI: 10.1007/s11042-026-21917-z

Keywords: Named Data Networking, consumer mobility, push communication, real-time streaming, Persistent Interest, stale paths, ndnSIM, handover, content-centric networking, forwarding paths, protocol design, network simulation