Unmanned aerial vehicles (UAVs) furnished with computational servers enable user equipment (UE) to offload complex computational tasks, thereby addressing the limitations of edge computing in remote or resource-constrained environments. The application of value decomposition algorithms for UAV trajectory planning has drawn considerable research attention. However, existing value decomposition algorithms commonly encounter obstacles in effectively associating local observations with the global state of UAV clusters, which hinders their task-solving capabilities and gives rise to reduced task completion rates and prolonged convergence times. To address these challenges, this paper introduces an innovative multi-agent deep learning framework that conceptualizes multi-UAV trajectory optimization as a decentralized partially observable Markov decision process (Dec-POMDP). This framework integrates the QTRAN algorithm with a large language model (LLM) for efficient region decomposition and employs graph convolutional networks (GCNs) combined with self-attention mechanisms to adeptly manage inter-subregion relationships. The simulation results demonstrate that the proposed method significantly outperforms existing deep reinforcement learning methods, with improvements in convergence speed and task completion rate exceeding 10%. Overall, this framework significantly advances UAV trajectory optimization and enhances the performance of multi-agent systems within UAV-assisted edge computing environments.

The anti-fouling performance of membranes is an important performance in the separation of oil/water. However, the membrane with anti-fouling performance will also have surface scaling phenomenon when it runs for a long time. Therefore, there is still a great demand for stain-resistant membranes with good self-cleaning ability and high flux recovery rate. Based on this, this paper firstly prepared a hydrophilic membrane with carboxyl group and carboxyl ion by blending poly(ethylene-alt-maleic anhydride) (PEMA) and polyvinylidene fluoride (PVDF), and then prepared a self-cleaning composite membrane by in situ mineralization of β-FeOOH particles on the surface of the membrane for efficient oil-in-water emulsion separation. A large number of –COOH/COO⁻ and β-FeOOH particles on the membrane surface make the composite membrane have strong hydrophilic properties (WCA = 20.34°) and underwater superoleophobicity (UOCA = 155.10°). These composite membranes have high separation efficiency (98.8%) and high flux (694.56 L m⁻² h⁻¹ bar⁻¹) for soybean oil-in-water emulsion. Importantly, the as-prepared membrane shows excellent flux recovery rate (over 99.93%) attributed to the robust photo-Fenton catalytic activity of β-FeOOH, and the β-FeOOH is chemically bonded to the as-prepared membrane, which makes the as-prepared membrane have good reusability. This work provides hope for the application of self-cleaning membranes in the construction of anti-fouling membranes for wastewater remediation.

Mobile edge computing (MEC), which sinks the functions of cloud servers, has become an emerging paradigm to solve the contradiction between delay-sensitive tasks and resource-constrained terminals. Task offloading assisted by service caching in a collaborative manner can reduce delay and balance the edge load in MEC. Due to the limited storage resources of edge servers, it is a significant issue to develop a dynamical service caching strategy according to the actual variable user demands in task offloading. Therefore, this paper investigates the collaborative task offloading problem assisted by a dynamical caching strategy in MEC. Furthermore, a two-level computing strategy called joint task offloading and service caching (JTOSC) is proposed to solve the optimized problem. The outer layer in JTOSC iteratively updates the service caching decisions based on the Gibbs sampling. The inner layer in JTOSC adopts the fairness-aware allocation algorithm and the offloading revenue preference-based bilateral matching algorithm to get a great computing resource allocation and task offloading scheme. The simulation results indicate that the proposed strategy outperforms the other four comparison strategies in terms of maximum offloading delay, service cache hit rate, and edge load balance.

This letter proposes a multi-features space domain fusion network (MFSDF-Net) to address impulsive noise suppression issues in power line communication (PLC) systems. As an end-to-end model, the proposed deep learning algorithm eliminates the need for designing null subcarriers in the original signals and fitting the data distribution at the receiver side. By utilizing parallel convolutional kernels to extract and fuse details from different domains of the signals, MFSDF-Net effectively captures dynamic changes. This enables it to more accurately and effectively identify and suppress impulsive noise, thus addressing the shortcomings of existing algorithms that inadequately identify impulsive noise and exhibit the bit error ratio (BER) floor effect. Simulation results show that with perfect channel estimation, the signal-to-noise ratio (SNR) at a BER of 1e-5 is 18 dB for this model, compared to 26 dB or higher for others, indicating an 8 dB improvement. With imperfect channel estimation, this model achieves an SNR of 30 dB at a BER of 1e-5, while other algorithms exhibit a BER floor effect.

Aiming at the problems of low permeation flux and low salt rejection of polyamide (PA) nanofiltration (NF) membrane, this study improved the surface properties and structure of PA layer by adding hydrophilic GO nanosheets. Polyethylimide (PEI), GO and trimethylchloride (TMC) were prepared on the surface of polyether sulfone (PES) substrate by interfacial polymerization. After adding GO, the hydrophilicity and zeta potential of NF membrane were improved. The NF test showed that when the amount of GO was 0.1%, the permeation flux of the membrane was increased from 7.06 to 12.285 L·m⁻²·h⁻¹ (improve 73.94%), and the rejection of MgSO₄ was increased from 90.23% to 95.9%. In the test of repulsion of univalent ion and bivalent ion, the repulsion value of bivalent ion is above 95%, and the repulsion degree of univalent ion is moderate. Compared with the original TFC membrane, the composite membrane also showed higher anti-fouling. This study provides a shortcut for improving the hydrophilicity and anti-fouling properties of NF membranes by using GO nanosheets.