Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379116684> ?p ?o ?g. }
- W4379116684 endingPage "4619" @default.
- W4379116684 startingPage "4605" @default.
- W4379116684 abstract "Deep neural networks (DNNs) are emerging as a potential solution to solve NP-hard wireless resource allocation problems. However, in the presence of intricate constraints, e.g., users’ quality-of-service (QoS) constraints, guaranteeing constraint satisfaction becomes a fundamental challenge. In this paper, we propose a novel unsupervised learning framework to solve the classical power control problem in a multi-user interference channel, where the objective is to maximize the network sum-rate under users’ minimum data rate or QoS requirements and power budget constraints. Utilizing a differentiable projection function, two novel deep learning (DL) solutions are pursued. The first is called Deep Implicit Projection Network (DIPNet), and the second is called Deep Explicit Projection Network (DEPNet). DIPNet utilizes a differentiable convex optimization layer to implicitly define a projection function. On the other hand, DEPNet uses an explicitly-defined projection function, which has an iterative nature and relies on a differentiable correction process. DIPNet requires convex constraints; whereas, the DEPNet does not require convexity and has a reduced computational complexity. To enhance the sum-rate performance of the proposed models even further, Frank-Wolfe algorithm (FW) has been applied to the output of the proposed models. Extensive simulations depict that the proposed DNN solutions not only improve the achievable data rate but also achieve zero constraint violation probability, compared to the existing DNNs. The proposed solutions outperform the classic optimization methods in terms of computation time complexity." @default.
- W4379116684 created "2023-06-03" @default.
- W4379116684 creator A5019544514 @default.
- W4379116684 creator A5039708717 @default.
- W4379116684 date "2023-08-01" @default.
- W4379116684 modified "2023-10-14" @default.
- W4379116684 title "Power Control with QoS Guarantees: A Differentiable Projection-based Unsupervised Learning Framework" @default.
- W4379116684 cites W1928152501 @default.
- W4379116684 cites W1987210641 @default.
- W4379116684 cites W2100755644 @default.
- W4379116684 cites W2129516068 @default.
- W4379116684 cites W2151278498 @default.
- W4379116684 cites W2616867685 @default.
- W4379116684 cites W2797462110 @default.
- W4379116684 cites W2883094398 @default.
- W4379116684 cites W2936329642 @default.
- W4379116684 cites W2971598376 @default.
- W4379116684 cites W2980815282 @default.
- W4379116684 cites W2983675157 @default.
- W4379116684 cites W2991155877 @default.
- W4379116684 cites W2992716901 @default.
- W4379116684 cites W3047312226 @default.
- W4379116684 cites W3091225957 @default.
- W4379116684 cites W3111499798 @default.
- W4379116684 cites W3112604001 @default.
- W4379116684 cites W3125537303 @default.
- W4379116684 cites W3135089279 @default.
- W4379116684 cites W3172159586 @default.
- W4379116684 cites W3176252472 @default.
- W4379116684 cites W3177911636 @default.
- W4379116684 cites W3201615134 @default.
- W4379116684 cites W3202428175 @default.
- W4379116684 cites W4250589301 @default.
- W4379116684 cites W4251616545 @default.
- W4379116684 cites W4378974380 @default.
- W4379116684 doi "https://doi.org/10.1109/tcomm.2023.3282220" @default.
- W4379116684 hasPublicationYear "2023" @default.
- W4379116684 type Work @default.
- W4379116684 citedByCount "0" @default.
- W4379116684 crossrefType "journal-article" @default.
- W4379116684 hasAuthorship W4379116684A5019544514 @default.
- W4379116684 hasAuthorship W4379116684A5039708717 @default.
- W4379116684 hasBestOaLocation W43791166842 @default.
- W4379116684 hasConcept C112680207 @default.
- W4379116684 hasConcept C11413529 @default.
- W4379116684 hasConcept C121332964 @default.
- W4379116684 hasConcept C126255220 @default.
- W4379116684 hasConcept C134306372 @default.
- W4379116684 hasConcept C137836250 @default.
- W4379116684 hasConcept C154945302 @default.
- W4379116684 hasConcept C157972887 @default.
- W4379116684 hasConcept C163258240 @default.
- W4379116684 hasConcept C202615002 @default.
- W4379116684 hasConcept C2524010 @default.
- W4379116684 hasConcept C31258907 @default.
- W4379116684 hasConcept C33923547 @default.
- W4379116684 hasConcept C41008148 @default.
- W4379116684 hasConcept C50644808 @default.
- W4379116684 hasConcept C5119721 @default.
- W4379116684 hasConcept C56685638 @default.
- W4379116684 hasConcept C57493831 @default.
- W4379116684 hasConcept C62520636 @default.
- W4379116684 hasConceptScore W4379116684C112680207 @default.
- W4379116684 hasConceptScore W4379116684C11413529 @default.
- W4379116684 hasConceptScore W4379116684C121332964 @default.
- W4379116684 hasConceptScore W4379116684C126255220 @default.
- W4379116684 hasConceptScore W4379116684C134306372 @default.
- W4379116684 hasConceptScore W4379116684C137836250 @default.
- W4379116684 hasConceptScore W4379116684C154945302 @default.
- W4379116684 hasConceptScore W4379116684C157972887 @default.
- W4379116684 hasConceptScore W4379116684C163258240 @default.
- W4379116684 hasConceptScore W4379116684C202615002 @default.
- W4379116684 hasConceptScore W4379116684C2524010 @default.
- W4379116684 hasConceptScore W4379116684C31258907 @default.
- W4379116684 hasConceptScore W4379116684C33923547 @default.
- W4379116684 hasConceptScore W4379116684C41008148 @default.
- W4379116684 hasConceptScore W4379116684C50644808 @default.
- W4379116684 hasConceptScore W4379116684C5119721 @default.
- W4379116684 hasConceptScore W4379116684C56685638 @default.
- W4379116684 hasConceptScore W4379116684C57493831 @default.
- W4379116684 hasConceptScore W4379116684C62520636 @default.
- W4379116684 hasFunder F4320334593 @default.
- W4379116684 hasIssue "8" @default.
- W4379116684 hasLocation W43791166841 @default.
- W4379116684 hasLocation W43791166842 @default.
- W4379116684 hasOpenAccess W4379116684 @default.
- W4379116684 hasPrimaryLocation W43791166841 @default.
- W4379116684 hasRelatedWork W1601283844 @default.
- W4379116684 hasRelatedWork W2036712732 @default.
- W4379116684 hasRelatedWork W2083419449 @default.
- W4379116684 hasRelatedWork W2093508149 @default.
- W4379116684 hasRelatedWork W2105639983 @default.
- W4379116684 hasRelatedWork W2160044169 @default.
- W4379116684 hasRelatedWork W2347828807 @default.
- W4379116684 hasRelatedWork W2513356504 @default.
- W4379116684 hasRelatedWork W3106270855 @default.
- W4379116684 hasRelatedWork W4310281905 @default.
- W4379116684 hasVolume "71" @default.