Deep Learning Based Power Allocation for Workload Driven Full-Duplex D2D-Aided Underlaying Networks

A Self-Regulating Power-Control Scheme Using Reinforcement Learning for D2D Communication Networks

“…On the other hand, new power-control schemes based on deep learning for D2D networks have been proposed to overcome the limitations of the conventional schemes such as optimization of threshold values, computational complexity, or signaling overhead [11][12][13][14][15][16]. Deep reinforcement learning (DRL)-based power control schemes for D2D communications underlying cellular networks were investigated [11][12][13]. A joint scheme for resource block scheduling and power control to improve the sum-rate of D2D underlay communication networks was proposed based on a deep Q-network considering users' fairness [11].…”

“…However, this proposed scheme requires coordination by cellular base stations. A deep-learning-based transmission power allocation method was proposed to automatically determine the optimal transmission powers for D2D networks underlying full duplex cellular networks [12]. It was shown that the performance of the proposed scheme is comparable with that of the traditional iterative algorithms, but the intervention of cellular base stations is also required.…”

“…Despite intensive investigations on the power control problem in D2D communication networks, the closed-form solutions of general power control problems to maximize the sum-rate of D2D communication networks in which multiple D2D links share the same radio resource are not available, as they are typically NP-hard. As an alternative, new power-control schemes have prepared to overcome the limitations of conventional schemes using deep learning have been proposed [11][12][13][14][15][16]. However, they unfortunately do not allow each D2D user to autonomously determine its transmission power level because cellular base stations (BSs) play a key role in coordinating the transmission power levels of cellular and D2D users or each D2D pair needs to collect not only local information that can be obtained directly by the transmitter or receiver of a D2D pair but also non-local information that can be obtained from neighboring D2D pairs, thereby causing extra signaling overhead.…”

A Deep Learning-Based Transmission Scheme Using Reduced Feedback for D2D Networks

“…On the other hand, deep reinforcement learning (DRL) has been widely used as an alternative approach to solve many mathematically intractable problems in wireless networks [12], [13]. Especially, various challenging problems such as resource allocation and interference mitigation in D2D networks can't be solved by conventional optimization methods because most of them are non-convex [14], and many studies thus relied to DRL to solve non-convex problems in D2D networks [15]- [17]. A previous study investigated a joint problem of resource block allocation and power control and proposed a DRL-based scheme to solve the joint problem [15].…”

“…A distributed DRL-based transmission scheme that allows each D2D pair to make optimal decisions autonomously was proposed, achieving approximate performance of the state-of-art fractional programming-based algorithm. A deep learning based transmit power allocation scheme that can automatically determine the optimal transmit power levels of co-spectrum cellular users and D2D users based on a deep neural network was proposed [17].…”