Modified prioritized DDPG algorithm for joint beamforming and RIS phase optimization in MISO downlink systems.

Piezoelectric inkjet printing has important applications in high-precision manufacturing, but precise control of droplet quality faces challenges such as the nonlinear coupling between drive waveform parameters and droplet characteristics, as well as environmental disturbances. To address these issues, this paper proposes a closed-loop droplet control method based on a curriculum deep deterministic policy gradient (DDPG) algorithm, with the standard deviation of droplet volume and velocity as the main optimization objectives. To tackle the complex mapping relationships and boost training efficiency, we first built a high-fidelity simulation environment using a four-layer deep residual network trained on real-world industrial ink droplet data. Following that, we designed a dynamic weight-adaptive composite reward mechanism and integrated a curriculum learning strategy with the Deep Deterministic Policy Gradient (DDPG) algorithm. Relying on our self-developed droplet observation platform, we achieve closed-loop control of the standard deviation of droplet volume and velocity. Experimental results show that this method can precisely control the droplet volume within ±0.1 pl of the target value, while keeping the velocity standard deviation below 40 mm/s. The adjustment process is stable without severe oscillations, and the method demonstrates strong robustness against environmental disturbances such as ink supply pressure. This provides an efficient and practical solution for the automated control of droplet quality in piezoelectric inkjet printing.

Reconfigurable intelligent surface (RIS) partitioning offers a strategic solution for serving multiple users equipment (UEs) simultaneously in blockage-prone wireless environments, leveraging multiple-input multiple-output (MIMO) and non-orthogonal multiple access (NOMA) technologies within the millimeter-wave (mmWave) spectrum. However, deploying RIS partitioning (RISP) in MIMONOMA is hindered by the exacerbated computational complexity involved in acquiring accurate channel state information (CSI). This paper proposes a novel learning framework based on multi-agent deep reinforcement learning (MA-DRL) that maximizes the sum rate of the RISP-aided MIMO-NOMA system without requiring UEs’ CSI. The proposed framework jointly optimizes RIS phase shifts, number of RIS partitions, UEs beamformers, and NOMA power allocation (PA), transforming the challenge into a high-dimensional combinatorial optimization problem. The MA-DRL algorithm integrates double deep Q networks (DDQN) and deep deterministic policy gradient (DDPG) agents, where each UE acts as a DDQN agent optimizing its beamformer, while the RIS serves as a DDPG agent handling partitioning and power control. An experimental testbed is developed to gather real-world data for training and evaluation. Results show that the MA-DRL algorithm closely approaches optimal performance, trailing the exhaustive search by only 8%, while reducing complexity by 95% and improving the sum rate by an average of 18% compared to traditional full RIS setups.

In this work, we investigate the performance of cognitive satellite-aerial networks (CSAN), where the satellite operates as the primary network (PN) and the unmanned aerial vehicle (UAV) acts as an aerial base station in the secondary network (SN), employing rate-splitting multiple access (RSMA) to serve user equipment (UEs). We address the problem of joint beamforming, rate allocation, UAV trajectory design, and reconfigurable intelligent surface (RIS) phase shift optimization in a CSAN. To maximize the sum rate while satisfying power and interference constraints, we propose a deep reinforcement learning (DRL) framework based on the twin delayed deep deterministic policy gradient (TD3) algorithm. Simulation results show that the proposed TD3-based scheme outperforms other DRL-based benchmarks.

In recent years, the Integrated Satellite Aerial Terrestrial (I‐SAT) network has garnered significant attention as an innovative and integrated communication system. However, it still encounters interference in the face of the complex external environment. In this context, reconfigurable intelligent surface (RIS) provides a key way of solving this problem and effectively improves the performance and stability of the I‐SAT network. This article considers the combination of unmanned aerial vehicle (UAV) and RIS and proposes a novel architecture for sub‐connected active RIS (ARIS) under the energy consumption constraints of UAV and ARIS. The authors first provide a UAV‐ARIS based position prediction strategy for the vehicle. Then, a joint RIS phase shift, amplification and UAV trail optimization algorithm is proposed to pursue a high achievable rate. The interference between each link and the total energy consumption are all taken into consideration. In addition, a deep deterministic policy gradient (DDPG) algorithm is utilized for the optimization problem, and achieves convergence in continuous action space. Finally, the simulation results affirm the precision of the proposed method in significantly enhancing performance compared to other schemes.

In this paper, we propose a novel computer vision-based approach to aid reconfigurable intelligent surface (RIS) for dynamic beam tracking and implement the corresponding prototype verification system. A camera is attached at the RIS to obtain the visual information about the surroundings, with which RIS identifies the incident beam direction and the desired reflected beam direction, and then adjusts the reflection coefficients according to the pre-designed codebooks. We build a 20-by-20 RIS running at 5.4 GHz and develop a high-speed control board to ensure the real-time refresh of the reflection coefficients. Meanwhile we implement an independent peer-to-peer communications system to simulate the physical link between the base station and the user equipment. The vision-aided RIS prototype system is tested in two mobile scenarios: RIS works in near-field conditions as a passive array antenna of the base station; RIS works in far-field conditions to assist the communication between the base station and the user equipment. The experimental results show that RIS can quickly adjust the reflection coefficients for dynamic beam tracking with the help of visual information.

Reconfigurable Intelligent Surface (RIS) is an emerging technology that can improve the spectrum and energy efficiency of next-generation wireless networks. However, attaining accurate channel state information (CSI) for the cascaded RIS channel is particularly challenging. Imperfect CSI is a major bottleneck to achieving the spectral efficiency benefit of RIS-assisted networks. Rate splitting (RS), a promising multiple access technology, has been shown to be able to achieve an improved spectrum efficiency and be robust to channel uncertainties. This paper investigates the interplay between RIS and RS by considering a RIS-assisted RS beamforming problem. Active beamforming at the base station (BS) and passive beamforming at the RIS are jointly considered to maximize the minimum user rate under both the perfect CSI case and the imperfect CSI case. A block coordinate descent (BCD) algorithm is developed to solve this non-convex problem. Compared with the conventional semi-definite relaxation (SDR) approach, the proposed method does not require that the covariance matrix of the common beamforming vector be rank-one. Moreover, we present theoretical results to help reveal the impact of the system parameters and explain the performance gain resulting from the integration of RIS and RS. Extensive simulation results are also provided to show that RIS-assisted RS can improve the max-min rate performance significantly compared with conventional multiple access technologies, such as non-orthogonal multiple access (NOMA) and space division multiple access (SDMA) with/without RIS, especially in overloaded systems. With the proposed method, RS shows great potential in combating realistic CSI errors in RIS-assisted networks.

The research on autonomous driving based on deep reinforcement learning algorithms is a research hotspot. Traditional autonomous driving requires human involvement, and the autonomous driving algorithms based on supervised learning must be trained in advance using human experience. To deal with autonomous driving problems, this paper proposes an improved end-to-end deep deterministic policy gradient (DDPG) algorithm based on the convolutional block attention mechanism, and it is called multi-input attention prioritized deep deterministic policy gradient algorithm (MAPDDPG). Both the actor network and the critic network of the model have the same structure with symmetry. Meanwhile, the attention mechanism is introduced to help the vehicles focus on useful environmental information. The experiments are conducted in the open racing car simulator (TORCS)and the results of five experiment runs on the test tracks are averaged to obtain the final result. Compared with the state-of-the-art algorithm, the maximum reward increases from 62,207 to 116,347, and the average speed increases from 135 km/h to 193 km/h, while the number of success episodes to complete a circle increases from 96 to 147. Also, the variance of the distance from the vehicle to the center of the road is compared, and the result indicates that the variance of the DDPG is 0.6 m while that of the MAPDDPG is only 0.2 m. The above results indicate that the proposed MAPDDPG achieves excellent performance.

This paper considers a reconfigurable intelligent surface (RIS)-aided millimeter wave (mmWave) downlink communication system where hybrid analog-digital beamforming is employed at the base station (BS). We formulate a power minimization problem by jointly optimizing hybrid beamforming at the BS and the response matrix at the RIS, under signal-to-interference-plus-noise ratio (SINR) constraints. The problem is highly challenging due to the non-convex SINR constraints as well as the non-convex unit-modulus constraints for both the phase shifts at the RIS and the analog beamforming at the BS. A penalty-based algorithm in conjunction with the manifold optimization technique is proposed to handle the problem, followed by an individual optimization method with much lower complexity. Simulation results show that the proposed algorithm outperforms the state-of-art algorithm. Results also show that the joint optimization of RIS response matrix and BS hybrid beamforming is much superior to individual optimization.

This study presents a novel approach to enhance the power level at millimeter waves (mm-waves) with very low cost. Considering an mm-wave base station (BS) in a fixed location and the user equipment (UE) in the far-field (FF) region, a plane wave with a known direction of propagation reaches a specific region. A very large, predesigned fixed focal spot passive surface (S1) is designed and installed within the viewing angle of the plane wave to reflect and focus it in the near-field (NF) region on another wall. A small reconfigurable intelligent surface (RIS) device is installed on the other wall to be illuminated by the focused beam, and the RIS steers the beam dynamically inside the desired region toward the UE. By using this scheme, a large amount of power can be focused on the UEs to enhance the signal level. The components are modeled with full-wave electromagnetic simulation, and the best approach to design the mm-wave system is discussed. A prototype was fabricated and measured at 26 GHz to demonstrate the 2-D beam steering. The large passive fixed-beam surface is a single-layer printed circuit board (PCB) with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$20\times 20$</tex-math> </inline-formula> cm, and the RIS is <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$7\times 7$</tex-math> </inline-formula> cm (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$14\times 14$</tex-math> </inline-formula> elements). For demonstration, 1-bit mechanical tuning elements are used for simplicity. Measurement results show <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\approx \pm 50^{\circ }$</tex-math> </inline-formula> of 2-D beam steering with around 10% gain bandwidth. The radiation characteristics of both surfaces are analyzed, and an expression for received power under the general condition is obtained. The entire system can be implemented at a very low cost due to its simple PCB design and small-scale RIS. Moreover, due to the large passive surface and small RIS, the power consumption can be significantly reduced compared to conventional RIS.

Reconfigurable intelligent surface (RIS) is thought to be a potential key technique for future wireless communications due to its ability for manipulating the electromagnetic environment smartly. This paper focuses on the rank and capacity analysis when a RIS is introduced into a multiple-input multiple-output (MIMO) system. By establishing a system model for this communication system, various simulations are conducted for identifying the characteristics of the channel. The simulations of different distance between the access point (AP) and user equipment (UE) show that the condition number of the channel is worsen when the distance increases and the role of the RIS in rank improvement is weaken. The spatial distributions of the reciprocal condition number of the channel which corresponds to the RIS locations are obtained and rank-deficient zones are found in different AP, UE and RIS configurations, which depicts the spatial characteristics of the RIS-assisted MIMO channel. The simulations also indicate that the condition number of the channel not only varies with the RIS location, but is also affected by the antenna array size and orientation of AP and UE. In addition, when the AP has a larger amount of antennas than UE, it is advantageous to place the RIS near the UE rather than the AP to achieve better channel condition. Modulation and coding schemes are applied in the simulations for comparison and capacity improvement is witnessed. Beneficial suggestions for RIS deployment in the MIMO system are concluded according to the simulation results.

The incorporation of reconfigurable intelligent surface (RIS) into massive multiple-input-multiple-output (mMIMO) systems can unleash the potential of next-generation networks by improving the performance of user equipments (UEs) in service dead zones. However, their requirement for accurate channel state information (CSI) is critical, and especially, applications with UE mobility that induce channel aging make challenging the achievement of adequate quality of service. Hence, in this work, we investigate the impact of channel aging on the performance of RIS-assisted mMIMO systems under both spatial correlation and imperfect CSI conditions. Specifically, by accounting for channel aging during both uplink training and downlink data transmission phases, we first perform minimum mean square error (MMSE) channel estimation to obtain the UE effective channels with low overhead similar to conventional systems without RIS. Next, we derive the downlink achievable sum spectral efficiency (SE) with regularized zero-forcing (RZF) precoding in closed-form being dependent only on large-scale statistics by using the deterministic equivalent (DE) analysis. Subsequently, we present the attractive optimization of the achievable sum SE with respect to the phase shifts and the total transmit power that can be performed every several coherence intervals due to the slow variation of the large-scale statistics. Numerical results validate the analytical expressions and demonstrate the performance while allowing the extraction of insightful design conclusions for common scenarios including UE mobility. In particular, channel aging degrades the performance but its impact can be controlled by choosing appropriately the frame duration or by increasing the number of RIS elements.

A novel framework is proposed for the deployment and passive beamforming design of a reconfigurable intelligent surface (RIS) with the aid of non-orthogonal multiple access (NOMA) technology. The problem of joint deployment, phase shift design, as well as power allocation in the multiple-input-single-output (MISO) NOMA network is formulated for maximizing the energy efficiency with considering users particular data requirements. To tackle this pertinent problem, machine learning approaches are adopted in two steps. Firstly, a novel long short-term memory (LSTM) based echo state network (ESN) algorithm is proposed to predict users' tele-traffic demand by leveraging a real dataset. Secondly, a decaying double deep Q-network (D <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> QN) based position-acquisition and phase-control algorithm is proposed to solve the joint problem of deployment and design of the RIS. In the proposed algorithm, the base station, which controls the RIS by a controller, acts as an agent. The agent periodically observes the state of the RIS-enhanced system for attaining the optimal deployment and design policies of the RIS by learning from its mistakes and the feedback of users. Additionally, it is proved that the proposed D <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> QN based deployment and design algorithm is capable of converging within mild conditions. Simulation results are provided for illustrating that the proposed LSTM-based ESN algorithm is capable of striking a tradeoff between the prediction accuracy and computational complexity. Finally, it is demonstrated that the proposed D <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> QN based algorithm outperforms the benchmarks, while the NOMA-enhanced RIS system is capable of achieving higher energy efficiency than orthogonal multiple access (OMA) enabled RIS system.

In this paper, we explore the use of reconfigurable intelligent surface (RIS) in unmanned aerial vehicle (UAV) based multiuser downlink communications, where a flying UAV serves multiple single antenna users through multiple RISs mounted on various buildings. More specifically, we consider the selection of RISs based on the outdated and imperfect channel state information (CSI) of the composite UAV-RIS-User channels at the UAV. After selection process, the UAV communicates to the user via the selected RISs and also with the direct link. Particularly, we derive an infinite series based expression for selection probability of RISs under both the outdated and imperfect CSI of composite channels based selection scheme. We also derive the statistical distribution of instantaneously received signal-to-noise ratio (SNR) under outdated and imperfect CSI conditions of both the direct and composite links at the user. Next, using the derived statistics, we analyze the network’s performance in terms of the average coverage probability (ACP) and average bit error rate (ABER) over the complete UAV flight time. Moreover, we discuss the behavior of ACP and ABER for very small and very large values of UAV transmit power, respectively. It is depicted through numerical results that selecting more RISs from a group of small-sized RISs may not be as advantageous as selecting fewer RISs from a group of large-sized RISs. Moreover, we also demonstrate the effect of several system parameters such as number of RIS reflecting elements, number of selected RISs, the severity of UAV-RIS and RIS-User links, and the severity of imperfect and outdated CSI on the network’s performance. The analytical results are corroborated with Monte-Carlo simulations.

Active reconfigurable intelligent surface (RIS) emerges as an effective technique to resist the double-fading attenuation of passive RIS. By embedding with power harvesting function, it further evolves to zero-power active RIS, which can effectively enhance the flexibility of RIS deployment without external power demand. Nevertheless, existing works neglected the inherent difficulty of channel estimation (CE) for RIS-assisted systems, and the discrete phase shift constraint in practical deployment. In this paper we design a new element-wise RIS architecture and propose a distributed location-aided transmission scheme with low complexity to enhance the reflected gain for channel state information (CSI)-limited RIS-assisted near-field communications. Specifically, the new element-wise RIS provides dynamic element selection capability with low hardware resources. Based on Fresnel diffraction theory, we construct the mapping from locations in space-domain to phase distributions of waves in phase-domain and reveal the priority of elements for harvesting and reflecting. Then, the distributed beamforming design with the phase of determine-then-align is proposed, where the estimation overhead reduction stems from exempted requirements of RIS-associated CE at base station (BS). The asymptotic analysis indicates that the proposed scheme can achieve the optimal gain with a fixed proportion of reflective elements when RIS is large, followed by simulations to verify its superiority to other protocols.

In this paper, we study the uplink transmission scheme and channel estimation design for reconfigurable intelligent surfaces (RIS)-aided orthogonal time frequency space (OTFS) systems in high-mobility scenarios. To this end, we first propose an efficient and reliable transmission scheme which utilizes the delay-Doppler information in OTFS to facilitate the configuration of RIS. Specifically, the proposed scheme exploits the estimated delay and Doppler shifts of the cascaded channel to sense the channel parameters, and the sensing parameters are then used for RIS passive beamforming. It is noteworthy that we estimate the channel state information (CSI) by employing only one OTFS frame and configure the RIS based on the predicted channel parameters, leading to substantially reduced channel training overhead and more real-time RIS configuration. To obtain the essential information for channel information sensing, we then propose a low-complexity algorithm which determines the Doppler and delay shifts of the channel between the user and RIS based on linear systems and the mapping relationship of the delay-Doppler pairs, respectively. With the delay-Doppler information in hand, a user localization algorithm constructed by the least square (LS) and a channel tracking method relying on extended Kalman filter (EKF) are then presented to obtain the spatial angle information. By making use of the channel parameters acquired at the base station (BS), the RIS reflection vector is designed to maximize the achievable rate. The results obtained from the simulation experiments affirm the efficacy of the proposed scheme, thereby confirming its capability to attain efficient communications under high Doppler channels.