Cognitive radio network is an intelligent wireless communication system which can adjust its transmission parameters according to the environment thanks to its learning ability. It is a feasible and promising direction to solve the spectrum scarcity issue and has become a research focus in communication community. However, cognitive radio network is vulnerable to jamming attack, resulting in serious degradation of spectrum utilization. In this paper, we view the anti-jamming task of cognitive radio as a Markov decision process and propose an intelligent anti-jamming scheme based on deep reinforcement learning. We aim to learn a policy for users to maximize their rate of successful transmission. Specifically, we design Double Deep Q Network (Double DQN) to model the confrontation between the cognitive radio network and the jammer. The Q network is implemented using Transformer encoder to effectively estimate action-values from raw spectrum data. The simulation results indicate that our approach can effectively defend against several kinds of jamming attacks.
Rural household biogas (RHB) systems are at a crossroads in China, yet there has been a lack of holistic evaluation of their energy and climate (greenhouse gas mitigation) efficiency under typical operating conditions. We combined data from monitoring projects and questionnaire surveys across hundreds of households from two typical Chinese villages within a consequential life cycle assessment (LCA) framework to assess net GHG (greenhouse gas) mitigation by RHB systems operated in different contexts. We modelled biogas production, measured biogas losses and used survey data from biogas and non-biogas households to derive empirical RHB system substitution rates for energy and fertilizers. Our results indicate that poorly designed and operated RHB systems in northern regions of China may in fact increase farm household GHG emissions by an average of 2668 kg·CO 2 -eq·year −1 , compared with a net mitigation effect of 6336 kg·CO 2 -eq per household and year in southern regions. Manure treatment (104 and 8513 kg·CO 2 -eq mitigation) and biogas leakage (−533 and −2489 kg·CO 2 -eq emission) are the two most important factors affecting net GHG mitigation by RHB systems in northern and southern China, respectively. In contrast, construction (−173 and −305 kg·CO 2 -eq emission), energy substitution (−522 emission and 653 kg·CO 2 -eq mitigation) and nutrient substitution (−1544 and −37 kg·CO 2 -eq emission) made small contributions across the studied systems. In fact, survey data indicated that biogas households had higher energy and fertilizer use, implying no net substitution effect. Low biogas yields in the cold northern climate and poor maintenance services were cited as major reasons for RHB abandonment by farmers. We conclude that the design and management of RHB systems needs to be revised and better adapted to local climate (e.g., digester insulation) and household energy demand (biogas storage and micro power generators to avoid discharge of unburned biogas). More precise nutrient management planning could ensure that digestate nutrients are more effectively utilized to substitute synthetic fertilizers.
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.