Pest control in economic forests is a crucial aspect of sustainable forest resource management, yet it faces bottlenecks such as low efficiency and high miss rates for small objects. Based on the RT-DETR model, this paper proposes LightFAD-DETR, a lightweight architecture integrated with feature aggregation diffusion, designed for complex economic forest scenarios. Firstly, by employing the YOLOv9 lightweight backbone network to compress the computational base load, we introduce the RepNCSPELAN4-CAA module, which integrates re-parameterization techniques and one-dimensional strip convolution. This enhances the model’s ability for cross-regional modeling of slender insect morphologies. Secondly, a feature aggregation diffusion network is designed, incorporating a dimension-aware selective integration mechanism. This dynamically fuses shallow detail features with deep semantic features, effectively mitigating information loss for small objects occluded by foliage. Finally, a re-parameterized batch normalization technique is introduced to reconstruct the AIFI module. Combined with a progressive training strategy, this eliminates redundant parameters, thereby enhancing inference efficiency on edge devices. Experimental validation demonstrates that compared to the baseline RT-DETR model, LightFAD-DETR achieves a 1.4% improvement in ${mAP}_{0.5:0.95}$, while reducing parameters by 41.7% and computational load by 35.0%. With an inference speed reaching 106.3 FPS, the method achieves balanced improvements in both accuracy and lightweight design.

In the edge computing environment, due to factors, such as expensive devices, complex scenarios, and fine control requirements, it is necessary to use simulators to construct heterogeneous devices, simulate task offloading scenarios, and evaluate and optimize decision-making algorithms. However, existing edge computing simulators overly simplify the simulation process, neglecting device interactions and task complexities, making it difficult to finely control the task offloading process and customize complex scenarios. We propose EdgeSim++, a realistic, versatile, and easily customizable edge computing simulator. EdgeSim++ has the capability to generate a batch of heterogeneous devices with various features, supporting the simulation of multilayer cloud-edge-end scenarios and various multiaccess edge computing architectures. It dynamically sets task and device resource attributes, enables devices to interact and schedule behaviors through the network, and facilitates easy customization of both machine learning and nonmachine learning offloading strategies. Additionally, EdgeSim++ supports network topology visualization and result visualization, providing intuitive displays of task transmission processes and offloading results, and real-time monitoring of device resource changes. To test the effectiveness of EdgeSim++, we provided default machine learning and nonmachine learning offloading strategies, detailed simulation steps, demonstrated scenario construction, showcased process control, monitored resource changes, and compared algorithm effects. The results illustrated that our simulator could realistically simulate complex edge computing scenarios, flexibly control decision processes, and customize complex offloading algorithms, exhibiting good scalability and reusability.

Multi-access Edge Computing (MEC) is an emerging and promising computing paradigm that distributes computational resources closer to users at the network edge, effectively reducing both computation and communication latency. In practical Internet of Things (IoT) systems, many applications consist of interdependent subtasks. Therefore, determining how to offload these tasks while maintaining their dependencies to minimize latency becomes a challenging problem. Particularly in a dynamic environment with multiple users and MEC servers. Most existing studies rely on heuristic approaches, which lack adaptability in dynamic MEC environments, while machine learning-based methods often overlook task dependencies. Unlike previous work, our research focuses on the problem of offloading dependent tasks in multi-user, multi-MEC server scenarios. In this article, we first model the dependent task offloading problem as a Markov Decision Process (MDP). Then we propose a deep reinforcement learning (DRL)-based framework called GDDTO, with the aim of reducing task completion time. Specifically, this framework employs a Graph Convolutional Network (GCN) to extract task dependencies and dynamic MEC environment features, combined with a Double Deep Q-learning Network (DDQN) model and an optimized experience replay mechanism to select and evaluate task offloading strategies. Finally, comparative experiments demonstrate that this method significantly reduces task completion latency across various scenarios, proving its effectiveness.

In forest monitoring networks, the computational capabilities of sensors cannot meet the latency requirements for complex tasks, and the limited battery capacity of these sensors hinders the long-term execution of monitoring tasks. Mobile edge computing (MEC) acts as an effective solution for this issue by offloading tasks to edge servers, significantly reducing both task latency and energy consumption. However, the computational capacity of MEC servers and the bandwidth in the system are limited, and the communication environment in forested areas is complex. To simulate the complexity of the forest communication environment, we incorporate empirical path loss and multipath fading into the calculation of signal transmission rates. The computational offloading problem is then converted into a minimum-cost optimization problem with multiple constraints related to energy consumption and latency, which we formulate as an NP-hard problem. We propose a dung beetle optimization (DBO) strategy for computational offloading, enhancing it with an improved circle chaotic mapping, a dimension decomposition strategy, and Cauchy disturbance. This algorithm has the beauty of symmetry in the search range, and the symmetrical features can comprehensively search for existing solutions. Experimental results demonstrate that the improved dung beetle optimization algorithm (IDBO) achieves better convergence, lower complexity, and superior optimization outcomes compared to local offloading strategies and other metaheuristic algorithms, confirming the effectiveness of the proposed algorithm and ensuring the service quality of the forest monitoring network.

This work addresses the need for high recall with low false alarms in early wildfire monitoring and presents AsymmetricFPN, an asymmetric feature pyramid centered on parameter efficiency. Within a RetinaNet framework, we replace Smooth L1 with CIoU to stabilize small object localization and perform lightweight post-fusion refinement at key sites where multiscale context is already integrated. We construct a composite dataset with perceptual hash deduplication and evaluate all models under a unified protocol. Results show that AsymmetricFPN achieves mAP@0.5 of 85.5% and recall of 81.2%, reaches mAP@[0.5:0.95] of 44.0%, attains the highest parameter efficiency (η = 2.34), and delivers 26.10 FPS end-to-end. In addition, the localization-aware efficiency, defined as η@[0.5:0.95] = mAP@[0.5:0.95]/Params(M), reaches ≈ 1.21 and is the highest under the unified protocol. Compared with representative one stage baselines under identical settings, it provides comparable core detection capability with fewer parameters and fewer false positives in confounding backgrounds such as water glare and sunset. We conclude that task-oriented asymmetric architecture with lightweight post-fusion refinement offers a reusable route to reconcile accuracy, efficiency, and deployment cost for practical wildfire detection.