The porous carbons (PCs) with tunable
morphologies and pore sizes
were prepared by the sol–gel process via a freeze-drying technique
for microwave absorption applications. The results of Raman spectroscopy
and nitrogen sorption analysis showed that the graphitization degree
was barely influenced as the ratio of tert-butanol
(T) to resorcinol (R) decreased, while the pore morphologies changed
from the disordered slit-shaped pores to the uniform cage-like pores.
Dielectric properties of the as-prepared carbon samples were determined
by a vector network analyzer in the frequency range of 8.2–12.4
GHz. Results showed that the effect of pore morphology on the dielectric
loss of PCs was dominant in the case of similar graphitization. When
the T/R ratio was 7.5, the sample with cage-like pores revealed the
maximum values in the real part ε′ and the imaginary
part ε″ of complex permittivity, which were 13.2–6.5
and 15.6–10.1, respectively, suggesting a better capacity of
dielectric loss in the 8.2–12.4 GHz range. The proposed mechanism
for the effect of the pore morphologies on microwave absorption performance
was discussed.
With the development of the Internet of Things (IoT) and the birth of various new IoT devices, the capacity of massive IoT devices is facing challenges. Fortunately, edge computing can optimize problems such as delay and connectivity by offloading part of the computational tasks to edge nodes close to the data source. Using this feature, IoT devices can save more resources while still maintaining the quality of service. However, since computation offloading decisions concern joint and complex resource management, we use multiple Deep Reinforcement Learning (DRL) agents deployed on IoT devices to guide their own decisions. Besides, Federated Learning (FL) is utilized to train DRL agents in a distributed fashion, aiming to make the DRL-based decision making practical and further decrease the transmission cost between IoT devices and Edge Nodes. In this article, we first study the problem of computation offloading optimization and prove the problem is an NP-hard problem. Then, based on DRL and FL, we propose an offloading algorithm that is different from the traditional method. Finally, we studied the effects of various parameters on the performance of the algorithm and verified the effectiveness of both the DRL and FL in the IoT system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.