Coordinated service offloading is essential to meet Quality-of-Service (QoS) targets under non-stationary edge traffic. Yet conventional schedulers lack dynamic prioritization, causing deadline violations for delay-sensitive, lower-priority flows. We present PRONTO, a multi-agent framework with centralized training and decentralized execution (CTDE) that jointly optimizes SLA-aware offloading and adaptive service orchestration. PRONTO builds on Twin Delayed Deep Deterministic Policy Gradient (TD3) and incorporates spatiotemporal, topology-aware graph attention with top-K masking and temperature scaling to encode neighborhood influence at linear coordination cost. Gated Recurrent Units (GRUs) filter temporal features, while a hybrid reward couples task urgency, SLA satisfaction, and utilization costs. A priority-aware slicing policy divides bandwidth and compute between latency-critical and throughput-oriented flows. To improve robustness, we employ stability regularizers (temporal smoothing and confidence-weighted neighbor alignment), mitigating action jitter under bursts. Extensive evaluations show superior QoS and channel utilization, with up to 27.4% lower service delay and over 18% higher SLA Satisfaction Rate (SSR) compared with strong baselines.

The dense deployment of small cell networks is a key feature of next-generation mobile networks aimed at providing the necessary capacity increase. It is noteworthy that small cell networks employ high-capacity backhaul links on millimeter-wave bands to develop multi-hop topologies in order to mitigate data transmission costs. The current static backhaul infrastructures cannot control severe fluctuating network traffic. To resolve this problem, this paper proposed a novel adaptive backhaul topology with the ability to adapt to different traffic patterns. Based on the graph theory, the adaptive system dynamically allows changes to the hybrid millimeter-wave backhaul architecture, and it also provides the possibility of effective channel allocation to each backhaul link to meet capacity and QoS demands. Also, regarding the importance of green networking in integrated-access-and-backhaul networks we proposed a dynamic optimization model which minimizes the overall energy consumption of UL/DL Decoupled NOMA heterogeneous networks in addition to providing the essential coverage and capacity. The proposed model optimizes user association/power utilization and presents an effective modular and scalable framework for analytical technology-oriented modeling of integrated multi-hop backhauls. The numerical results proved that the joint power optimization and hybrid backhaul architecture can increase the total network throughput by 18 percent compared to the current optimized static architectures. It can also reduce the energy consumption level by 30 percent, and enhance users’ quality satisfaction by 24.5 percent with respect to user distribution patterns.

Mobile Edge Computing (MEC) is a viable solution in response to the growing demand for broadband services in the new-generation heterogeneous systems. The dense deployment of small cell networks is a key feature of next-generation radio access networks aimed at providing the necessary capacity increase. Nonetheless, the problem of green networking and service computing will be of great importance in the downlink, because the uncontrolled installation of too many small cells may increase operational costs and emit more carbon dioxide. In addition, given the resource and computational limitation of the user layer, energy efficiency (EE) and fairness assurance are critical issues in MEC-based cellular systems. Considering the user fairness criteria, this paper proposes a dynamic optimization model which maximizes the total UL/DL EE along with satisfying the necessary QoS constraints. Based on the non-convex characteristics of the EE maximization problem, the mathematical model can be divided into two separate subproblems, i.e., computational carrier scheduling and resource allocation. So that, a subgradient method is applied for the computational resource allocation and also successive convex approximation (SCA) and dual decomposition methods are adopted to solve the max-min fairness problem. The simulation results exhibit considerable EE improvement for various traffic models in addition to guaranteeing the fairness requirements. It also proved that the proposed computational partitioning scheme managed to significantly improve the total throughput for mobile computing services.

Abstract The dense deployment of small cells is a key feature of the next‐generation cellular networks aimed at providing the necessary capacity increase. But in such networks the problem of green networking will be of great importance, because the uncontrolled installation of too many cells may increase operational costs and emit more carbon dioxide. Nowadays, unmanned aerial vehicles (UAVs) offer an efficient approach to improve the quality, data rate, and meet the demanding performance requirements of applications in ultra‐dense cellular networks. This article proposes a dynamic optimization model which minimizes the overall energy consumption of UAV cellular networks in addition to guarantying the essential coverage and capacity. The proposed model optimizes user association and power utility to meet users' QoS requirements with the highest level of energy efficiency (EE). For this purpose, the surplus energy pattern of UAVs is first mathematically formulated and then applied to calculate its ruin probability. In fact, the ruin probability denotes the vulnerability of a UAV when it runs out of energy. The ruin probability is used in the next step to efficiently connect every user to the UAVs. Also, power allocation is implemented for the applications to achieve the optimal value of the accessible network's data rate through the water‐filling method. This model also performs coded routing in the multi‐hop backhauls to efficiently use the existing infrastructure of the cooperative networks for coding dual‐hop transmissions. The simulation results exhibit considerable network throughput and EE increase by 42% and 30%, respectively, for the proposed ruin‐based energy‐efficient approach in comparison with the conventional signal‐to‐interference/noise ratio‐based schemes.

This research focuses on resource assignment in cooperative energy heterogeneous systems with non-orthogonal multiple access in which cells are powered via a common grid network and alternative energy resources and all base stations have the ability to cover a group of subscribers simultaneously at a specific frequency band. In order to consider the local limitations of alternative energy resources, it was assumed that the alternative energy would be shared among the base stations by the dynamic grid network. In this architecture, resource allocation and user association frameworks should be reconfigured because conventional schemes use orthogonal multiple access. Hence, this paper suggests a novel approach joint optimal power allocation and user association techniques to achieve the maximum degree of energy efficiency for the whole system in which the quality of experience parameters are assumed to be bounded during multi-cell multicast sessions. The solution to the introduced problem in a scenario with fixed transmission power is an improved decentralized algorithm that supplies effective user association framework. The model has been modified to develop joint multi-layered resource control and user association that can distinguish the service pattern in cooperative energy heterogeneous systems with non-orthogonal multiple access to obtain more resource optimality than current approaches. The effectiveness of the suggested approach has been confirmed by the numerical results. Also, the results reveal that non-orthogonal multiple access can provide greater energy efficiency than orthogonal multiple access in heterogeneous wireless networks.