The cloud-network-end integrated system is the inevitable result of integrating cloud-based Internet of Things (IoT) systems and new-generation network communication architectures. It can achieve wide-area coverage to...
详细信息
ISBN:
(纸本)9798350396041;9798350396034
The cloud-network-end integrated system is the inevitable result of integrating cloud-based Internet of Things (IoT) systems and new-generation network communication architectures. It can achieve wide-area coverage to enable efficient control and secure communication between various manned/unmanned end systems. For example, as a typical application in such systems, cloud-based Unmanned aerial vehicles (UAVs) surpass the payload limitations of traditional unmanned end systems by leveraging the computing and storage capabilities of cloud servers. This enables a significant enhancement in the diversity and complexity of various types of manned/unmanned end systems, leading to promising development prospects. In particular, the establishment and development of the space-air-ground integrated network (SAGIN) has greatly expanded and improved the communication range and quality between end systems. With a control paradigm centered on cloud servers, it can effectively meet the control requirements of various end systems in all areas and at all times. And further achieve secure data sharing among multiple end systems, as well as secure collaboration between multiple end systems. This paper proposes two lightweight authentication and key establishment (AKE) protocols for two typical scenarios of cloud-network-end integration systems to ensure secure communication between end systems based on SM2. We briefly analyze the correctness of our schemes and conduct a basic performance analysis. The results show that our schemes are reliable, effective, and very suitable for use in cloud-network integrated systems.
The advancing industrial digitalization enables evolved process control schemes that rely on accurate models learned through data-driven approaches. While they provide high controlperformance and are robust to smalle...
详细信息
ISBN:
(纸本)9798350363029;9798350363012
The advancing industrial digitalization enables evolved process control schemes that rely on accurate models learned through data-driven approaches. While they provide high controlperformance and are robust to smaller deviations, a larger change in process behavior can pose significant challenges, in the worst case even leading to a damaged process plant. Hence, it is important to frequently assess the fit between the model and the actual process behavior. As the number of controlled processes and associated data volumes increase, the need for lightweight and fast reacting assessment solutions also increases. In this paper, we propose CIVIC, an in-network computing-based solution for Continuous In-situ Validation of Industrial control models. In short, CIVIC monitors relevant process variables and detects different process states through comparison with a priori knowledge about the desired process behavior. This detection can then be leveraged to, e.g., shut down the process or trigger a reconfiguration. We prototype CIVIC on an Intel Tofino-based switch and apply it to a lab-scale water treatment plant. Our results show that we can achieve a high detection accuracy, proving that such monitoring systems are feasible and sensible.
The surge in renewable energy and distributed generation necessitates advanced controlsystems for networkperformance enhancement. However, the lack of a standardized evaluation framework hampers comparisons, especia...
详细信息
ISBN:
(纸本)9798350363647;9798350363630
The surge in renewable energy and distributed generation necessitates advanced controlsystems for networkperformance enhancement. However, the lack of a standardized evaluation framework hampers comparisons, especially in complex hybrid networks. Hybrid energy systems offer greener and more reliable networks but require sophisticated control methods. To address this challenge, research explores novel linear and nonlinear techniques. This overview focuses on heuristic evolutionary optimization methods for Microgrids, covering AC, DC, and hybrid AC-DC systems, highlighting current research and future control requirements.
Sensor networks are the backbone of emerging Internet of Things (IoT) ecosystems, serving as critical components in various applications ranging from environmental monitoring to smart cities. However, the Quality of S...
详细信息
Optimal control for high-dimensional nonlinear systems remains a fundamental challenge. One bottleneck is that classical approaches for solving the Hamilton-Jacobi-Bellman (HJB) equation suffer from the curse of dimen...
详细信息
Optimal control for high-dimensional nonlinear systems remains a fundamental challenge. One bottleneck is that classical approaches for solving the Hamilton-Jacobi-Bellman (HJB) equation suffer from the curse of dimensionality. Recently, physics -informed neural networks have demonstrated potential in overcoming the curse of dimensionality in solving certain classes of PDEs, including special cases of HJB equations. However, one perceived limitation of neural networks is their lack of formal guarantees in the solutions they provide. To address this issue, we have built LyZNet, a Python tool that combines physics-informed learning with formal verification. The previous version of the tool demonstrated the capability for stability analysis and region of attraction estimates. In this paper, we present the tool for solving optimal control problems. We expand the functionalities of the tool to support the formulation and solving of optimal control problems for control-affine systems via physics-informed neural network policy iteration (PINN-PI). We outline the methodology that enables the learning and verification of PINN for optimal stabilization tasks. We demonstrate with a classical control example that the learned optimal controller indeed has significantly improved performance and verifiable regions of attraction. Copyright (c) 2024 The Authors.
Reconfigurable Intelligent Surfaces (RIS) stand out among the key technologies driving 6G mobile network development. In this paper, we develop and assess radio resource management solutions aimed to exploit the poten...
详细信息
ISBN:
(纸本)9798350344998;9798350345001
Reconfigurable Intelligent Surfaces (RIS) stand out among the key technologies driving 6G mobile network development. In this paper, we develop and assess radio resource management solutions aimed to exploit the potential of RIS deployments for coverage and throughput enhancement for indoor users in 6G mobile networks. We introduce two heuristic algorithms that jointly control the cell-RIS-user association, user scheduling, transmit beamforming and the RIS's reflective configuration, and compare these algorithms against a RIS-free benchmark. Simulation results are presented to (i) demonstrate the promising potential of RIS deployments in multi-cell/multiuser scenarios;(ii) reveal the inherent trade-off between coverage and throughput enhancement;and (iii) show the performance impact of distinct RIS deployment locations. Our study provides valuable insights for efficiently leveraging RIS in evolving mobile network architectures.
This work proposes a novel approach to enhance grid-connected wind-solar PV charging stations that face challenges like fluctuating energy supply, inefficient resource usage, and the necessity for adaptive real-time c...
详细信息
ISBN:
(纸本)9798350391558;9798350379990
This work proposes a novel approach to enhance grid-connected wind-solar PV charging stations that face challenges like fluctuating energy supply, inefficient resource usage, and the necessity for adaptive real-time control. Traditional control methods like PI controllers, often fall short in optimizing the system performance under the dynamic conditions, resulting in inadequate power supply for EV charging. To tackle these challenges, this study proposes a novel approach by employing Neural network (NN) controllers to enhance grid-connected wind-solar PV charging stations' operation. NN controllers dynamically adjust charging station operations based on real-time data inputs, offering superior adaptability and efficiency. By integrating wind and solar power generation with intelligent NN control mechanisms, the system adeptly responds to varying environmental conditions and grid demands, ensuring more effective utilization of renewable energy sources. The proposed NN controller-based system targets enhancing the reliability, sustainability, and economic feasibility of grid-connected charging stations. Simulations showcase the effectiveness and stability of this approach in integrating renewable energy into transportation infrastructure. performance evaluation can be conducted using Matlab/Simulink Software.
Linear proportional-integral-derivative (PID) controllers often fail to provide adequate controlperformance for nonlinear and time-varying systems due to their constant parametric nature. To address the challenges po...
详细信息
In recent years, the introduction of neural networks (NNs) into the field of speech enhancement has brought significant improvements. However, many of the proposed methods are quite demanding in terms of computational...
详细信息
ISBN:
(纸本)9798350344868;9798350344851
In recent years, the introduction of neural networks (NNs) into the field of speech enhancement has brought significant improvements. However, many of the proposed methods are quite demanding in terms of computational complexity and memory footprint. For the application in dedicated communication devices, such as speakerphones, hands-free car systems, or smartphones, efficiency plays a major role along with performance. In this context, we present an efficient, high-performance hybrid joint acoustic echo control and noise suppression system, whereby our main contribution is the post-filter NN, performing both noise and residual echo suppression. The preservation of nearend speech is improved by a Bark-scale auditory filterbank for the NN postfilter. The proposed hybrid method is benchmarked with state-of-the-art methods and its effectiveness is demonstrated on the ICASSP 2023 AEC Challenge blind test set. We demonstrate that it offers high-quality nearend speech preservation during both double-talk and nearend speech conditions. At the same time, it is capable of efficient removal of echo leaks, achieving a comparable performance to already small state-of-the-art models such as the end-to-end DeepVQE-S, while requiring only around 10% of its computational complexity. This makes it easily realtime implementable on a speakerphone device.
In the past decade, there has been significant advancement in designing wearable neural interfaces for controlling neurorobotic systems, particularly bionic limbs. These interfaces function by decoding signals capture...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
In the past decade, there has been significant advancement in designing wearable neural interfaces for controlling neurorobotic systems, particularly bionic limbs. These interfaces function by decoding signals captured non-invasively from the skin's surface. Portable high-density surface electromyography (HD-sEMG) modules combined with deep learning decoding have attracted interest by achieving excellent gesture prediction and myoelectric control of prosthetic systems and neurorobots. However, factors like small electrode size and unstable electrode-skin contacts make HD-sEMG susceptible to pixel electrode drops. The sparse electrode-skin disconnections rooted in issues such as low adhesion, sweating, hair blockage, and skin stretch challenge the reliability and scalability of these modules as the perception unit for neurorobotic systems. This paper proposes a novel deep-learning model providing resiliency for HD-sEMG modules, which can be used in the wearable interfaces of neurorobots. The proposed 3D Dilated Efficient CapsNet model trains on an augmented input space to computationally 'force' the network to learn channel dropout variations and thus learn robustness to channel dropout. The proposed framework maintained high performance under a sensor dropout reliability study conducted. Results show conventional models' performance significantly degrades with dropout and is recovered using the proposed architecture and the training paradigm.
暂无评论