Grid-forming control demonstrates higher stability compared to grid-following control in expanding inverter-dominated power grids. However, parameters are not harmoniously adjusted for large-scale inverter-dominated g...
详细信息
ISBN:
(纸本)9798350360875;9798350360868
Grid-forming control demonstrates higher stability compared to grid-following control in expanding inverter-dominated power grids. However, parameters are not harmoniously adjusted for large-scale inverter-dominated grids. For instance, while the damping factor can enhance the stability of local inverters, it may lead to instability in other inverters. Furthermore, existing literature fails to consider other performance metrics such as response speed and overshoot. Therefore, this letter proposes an online adaptive control based on reinforcement learning. Leveraging the flexible computing paradigm of cloud-edge-terminal systems, the proposed approach comprehensively assesses the performance of grid-forming inverters.
The filtered-x least mean L-p -norm (FxLMP) algorithm, renowned for its widespread usage, exhibits superior performance over the filtered-x Least Mean Square (FxLMS) algorithm in impulsive noise-afflicted environments...
详细信息
The filtered-x least mean L-p -norm (FxLMP) algorithm, renowned for its widespread usage, exhibits superior performance over the filtered-x Least Mean Square (FxLMS) algorithm in impulsive noise-afflicted environments. Nevertheless, the FxLMP algorithm experiences performance degradation when confronted with nonlinearity in either the primary or secondary path. In response to this challenge, we propose a novel algorithm known as the minimum output variance filtered-s LMP (MOV-FsLMP), which effectively tackles nonlinear active noise control problems by imposing constraints on variance or power. Notably, this proposed algorithm exhibits improved convergence and stability even in impulsive noise environments, all while maintaining lower computational complexity. Extensive simulations validate the efficacy of the proposed MOV-FsLMP method, surpassing that of state-of-the-art alternatives.
Research and development of Space-Air-Ground Integrated network (SAGIN) systems, which can provide a wide range of communication support from space and the air, have been progressing as a way to achieve the 6G require...
详细信息
ISBN:
(纸本)9798350304060;9798350304053
Research and development of Space-Air-Ground Integrated network (SAGIN) systems, which can provide a wide range of communication support from space and the air, have been progressing as a way to achieve the 6G requirements of ultra coverage extension and ultra-large capacity. Additionally, the use of Intelligent Reflecting Surfaces (IRS) in SAGIN is expected to improve the overall system performance. An IRS is a radio-wave reflection device that can control the phase of an incident radio wave, and the direction of the radio-wave reflection can be arbitrarily selected by appropriate phase control. However, IRS cannot reflect radio waves in multiple directions at the same time basically, it is difficult to communicate with multiple simultaneous connections. Therefore, IRS dividing control is proposed as a control method to realize multiple simultaneous connections. The communication performance of IRS divisions depends on three control parameters: the number of the IRS divisions, the division pattern, and the beam assign pattern. Therefore, in this study the relationship between IRS dividing control and control parameters is discussed and verified by simulations. The simulation results show that the optimal number of divisions depends on the communication demand of the User Equipments (UEs) and their distance from the IRS. Further, the optimal division pattern and the beam assign pattern depend on the UE distribution.
This paper proposes a method for calibrating control parameters. Examples of such control parameters are gains of PID controllers, weights of a cost function for optimal control, filter coefficients, the sliding surfa...
详细信息
This paper proposes a method for calibrating control parameters. Examples of such control parameters are gains of PID controllers, weights of a cost function for optimal control, filter coefficients, the sliding surface of a sliding mode controller, or weights of a neural network. Hence, the proposed method can be applied to a wide range of controllers. The method uses a Kalman filter that estimates control parameters, using data of closed-loop system operation. The control parameter calibration is driven by a training objective, which encompasses specifications on the performance of the dynamical system. The performance-driven calibration method tunes the parameters online and robustly, is computationally efficient, has low data storage requirements, and is easy to implement making it appealing for many real-time applications. Simulation results show that the method is able to learn control parameters quickly, is able to tune the parameters to compensate for disturbances, and is robust to noise. A simulation study with the high-fidelity vehicle simulator CarSim shows that the method can calibrate controllers of a complex dynamical system online, which indicates its applicability to a real-world system. We also verify the real-time feasibility on an embedded platform with automotive-grade processors by implementing our method on a dSPACE MicroAutoBox-ii rapid prototyping unit.
As deep neural networks (DNNs) are black-box models, ensuring closed-loop stability and optimality when learning DNN controllers is a critical issue. Previous work has proposed DNN controllers for specific systems, wh...
详细信息
ISBN:
(纸本)9798350366907;9789887581581
As deep neural networks (DNNs) are black-box models, ensuring closed-loop stability and optimality when learning DNN controllers is a critical issue. Previous work has proposed DNN controllers for specific systems, where closed-loop stability is guaranteed by carefully designing the structure of the DNN controller. However, since the controller's structure is fixed, the DNN controller needs to be retrained for changing initial states, making it unsuitable for receding horizon control. In this paper, we propose an improved structured DNN controller design to address this issue. The proposed controller comprises a primary and a secondary neural network. The primary neural network simulates the conventional structured controller, with weights determined by the output of the secondary neural network. The input of the secondary neural network is the initial state of the system. Using this approach, the primary neural network provides stability guarantees, and the secondary neural network can be optimized to allow for improved adaptability to changing initial states. The method is validated through several experiments, demonstrating its effectiveness in improving the performance of the conventional structured DNN controller.
This paper addresses the control of diesel engine nitrogen oxides (NOx) and Soot emissions through the application of Model Predictive control (MPC). The developments described in the paper are based on a high-fidelit...
详细信息
ISBN:
(纸本)9798350382662;9798350382655
This paper addresses the control of diesel engine nitrogen oxides (NOx) and Soot emissions through the application of Model Predictive control (MPC). The developments described in the paper are based on a high-fidelity model of the engine airpath and torque response in GT-Power, which is extended with a feedforward neural network (FNN)-based model of engine out (feedgas) emissions identified from experimental engine data to enable the controller co-simulation and performance verification. A Recurrent Neural network (RNN) is then identified for use as a prediction model in the implementation of a nonlinear economic MPC that adjusts intake manifold pressure and EGR rate set-points to the inner loop airpath controller as well as the engine fueling rate. Based on GT-Power engine model and FNN emissions model, the closed-loop simulations of the control system and the plant model, over different driving cycles, demonstrate the capability to shape engine out emissions response by adjusting weights and constraints in economic MPC formulation.
In 5G and beyond systems, network slicing plays a key role as it enables infrastructure providers (InPs) to create logical networks (slices) and virtually share network resources to their tenants. However, due to the ...
详细信息
ISBN:
(纸本)9798350302547
In 5G and beyond systems, network slicing plays a key role as it enables infrastructure providers (InPs) to create logical networks (slices) and virtually share network resources to their tenants. However, due to the limited nature of network resources of the InP, resource management algorithms like resource allocation and admission control are required to ensure efficient management of the InP's scarce resources. Indeed, admission control algorithms play a critical role of regulating access to the network, by determining whether a slice request should be accepted or not with respect to some standards such as maximizing the InP's revenue and maintaining service level agreements (SLAs). In this paper, we propose an admission control algorithm that employs the concept of overbooking which allows the InP to admit slice requests beyond it's nominal available resources. Moreover, we employ a dynamic queue adaption priority, step-wise pooling and dynamic buyback price mechanism to ensure efficient and profitable admission decision for the InP. We assess the performance of the proposed algorithm against state of the art (SOTA) solution considering different priority schemes. The results show that the proposed solution outperforms the SOTA solution as it yields i) higher revenue, ii) lower buyback cost and iii) higher net revenue for the InP while still maintaining a marginally higher slice acceptance rate.
The deployment of beyond 5G and 6G networks introduces many new services with stringent Quality of Service (QoS) requirements. Recently machine learning has been shown to be a viable solution in proposing adaptable so...
详细信息
ISBN:
(纸本)9798350377330;9798350377323
The deployment of beyond 5G and 6G networks introduces many new services with stringent Quality of Service (QoS) requirements. Recently machine learning has been shown to be a viable solution in proposing adaptable solutions. However, centralized machine learning based solutions still encounter hurdles in achieving real-time responsiveness due to their need of a global network view. In this paper, we explore a distributed approach aimed at optimizing networkperformance in real-time scenarios. By using Multi-Agent systems (MAS), our method targets near-real-time end-to-end delay assurance across diverse network domains, without the need for prior traffic profile knowledge. Evaluated results highlight the effectiveness of our approach in reducing routing costs and ensuring desired end-to-end delay levels.
The effective deployment of wireless sensor networks (WSNs) is a crucial foundation for the intelligent development of power systems. To address the optimization of wireless sensor distribution in power systems, this ...
详细信息
ISBN:
(纸本)9798350350319;9798350350302
The effective deployment of wireless sensor networks (WSNs) is a crucial foundation for the intelligent development of power systems. To address the optimization of wireless sensor distribution in power systems, this paper proposes a novel method named the Distributed Particle Swarm Optimization algorithm (D-PSO). This method mitigates the premature convergence issue of heuristic algorithms by introducing a regional operator. Additionally, considering the high-interference environment in power systems, relay node strategy (RNS) is incorporated to ensure communication quality. Simulation results validate the effectiveness and superiority of the D-PSO method and demonstrate the necessity of the RNS. Compared to some advanced particle swarm algorithms, this method better balances energy consumption, coverage, and communication quality, thereby significantly enhancing the overall performance of the wireless sensor network.
Pneumatic artificial muscles (PAMs) have been introduced as actuators due to their low weight, low mass-toforce ratio, compliance, high prevalence in nature and ability to closely mimic the functions of human biologic...
详细信息
ISBN:
(纸本)9798350358513;9798350358520
Pneumatic artificial muscles (PAMs) have been introduced as actuators due to their low weight, low mass-toforce ratio, compliance, high prevalence in nature and ability to closely mimic the functions of human biological muscles. When PAMs are applied in robotics and rehabilitation applications, it is essential that the actuator is operated according to user requirements. PAMs, however, present significant challenges in modeling and control due to their time- varying parameters, complex hysteresis, and highly nonlinear properties. This paper proposes an approach for controlling the motion of a PAM. This method applies a hybrid control algorithm to control a fluiddriven origami-inspired artificial muscle (FOAM). By combining a PI controller with feed-forward neural networkcontrol, the controller can learn and adapt through the system's behavior. The control algorithm was tested to observe the performance of the controller for displacement control of FOAM via different signals. Additionally, experiments were conducted to evaluate its performance under different load conditions. The results demonstrate exceptional controllability, even when the system faces increased loads, demonstrating the adaptability of the controller to load variations.
暂无评论