Realizing digital-twin services is one of promising applications in 6 G mobile communication and network scenarios. In addition, the use of unmanned aerial vehicles (UAVs) is essential for enabling the services e...
详细信息
Realizing digital-twin services is one of promising applications in 6 G mobile communication and network scenarios. In addition, the use of unmanned aerial vehicles (UAVs) is essential for enabling the services even in the extreme areas where humans cannot reach. In this emerging scenario, it is necessary to design collaborative algorithms for autonomous UAV trajectory control and a centralized computing platform (e.g., cloud) in digital-twin networks. For this system, it is required to build energy-efficient algorithms due to the power-hungry nature in UAVs. Based on this requirements and system characteristics, this paper proposes autonomous UAV charging algorithms and systems where the UAVs are classified into two types, i.e., cluster UAVs (for main image recording operations in digital-twin services, and some of them take the roles of mobile edge computing) and charging UAVs (for charging the cluster UAVs). Our proposed charging should be (i) fully distributed for practical, scalable, and low-overhead operations and (ii) trustworthy for secure and privacy-preserving computation;where these are essential for collaborative operations. Therefore, a novel auction-based charging algorithm for UAV-based digital-twin networks is proposed in order to realize the distributed and truthful operations, which cannot be achieved by the convex optimization-based centralized algorithms in the literature. Our performance evaluation verifies that the proposed algorithm achieves performance improvements (at most 15.53%). IEEE
The power grid is undergoing a transformation from synchronous generators(SGs) toward inverter-based resources(IBRs). The stochasticity, asynchronicity, and limited-inertia characteristics of IBRs bring about challeng...
详细信息
The power grid is undergoing a transformation from synchronous generators(SGs) toward inverter-based resources(IBRs). The stochasticity, asynchronicity, and limited-inertia characteristics of IBRs bring about challenges to grid resilience. Virtual power plants(VPPs) are emerging technologies to improve the grid resilience and advance the transformation. By judiciously aggregating geographically distributed energy resources(DERs) as individual electrical entities, VPPs can provide capacity and ancillary services to grid operations and participate in electricity wholesale markets. This paper aims to provide a concise overview of the concept and development of VPPs and the latest progresses in VPP operation, with the focus on VPP scheduling and control. Based on this overview, we identify a few potential challenges in VPP operation and discuss the opportunities of integrating the multi-agent system(MAS)-based strategy into the VPP operation to enhance its scalability, performance and resilience.
Since the fault dynamic of droop-controlled inverter is different from synchronous generators (SGs), protection devices may become invalid, and the fault overcurrent may damage power electronic devices and threaten th...
详细信息
Since the fault dynamic of droop-controlled inverter is different from synchronous generators (SGs), protection devices may become invalid, and the fault overcurrent may damage power electronic devices and threaten the safety of the microgrid. Therefore, it is imperative to conduct a comprehensive fault analysis of the inverter to guide the design of protection schemes. However, due to the complexity of droop control strategy, existing literatures have simplified asymmetric fault analysis of droop-controlled inverters to varying degrees. Therefore, accurate fault analysis of a droop-controlled inverter is needed. In this paper, by analyzing the control system, an accurate fault model is established. Based on this, a calculation method for instantaneous asymmetrical fault current is proposed. In addition, the current components and current characteristics are analyzed. It was determined that fault currents are affected by control loops, fault types, fault distance and nonlinear limiters. In particular, the influences of limiters on the fault model, fault current calculation and fault current characteristics were analyzed. Through detailed analysis, it was found that dynamics of the control loop cannot be ignored, the fault type and fault distance determine fault current level, and part of the limiters will totally change the fault current trend. Finally, calculation and experimental results verify the correctness of the proposed method.
This paper presents a novel supervised learning framework for real-time optimization of multi-parametric mixed-integer quadratic programming (mp-MIQP) problems. The framework utilizes a multi-layer perceptron (MLP) mo...
详细信息
Federated learning is widely accepted as a privacy-preserving paradigm for training a shared global model across multiple client devices in a collaborative fashion. However, in practice, the significantly limited comp...
详细信息
Federated learning is widely accepted as a privacy-preserving paradigm for training a shared global model across multiple client devices in a collaborative fashion. However, in practice, the significantly limited computational power on client devices has been a major barrier when we wish to train large models with potentially hundreds of millions of parameters. In this paper, we propose a new architecture, referred to as Infocomm, that incorporates locally supervised learning in federated learning. With locally supervised learning, the disadvantages of split learning can be avoided by using a more flexible way to offload training from resource constrained clients to a more capable server. Infocomm enables parallel training of different modules of the neural network in both the server and clients in a gradient-isolated fashion. The efficacy in reducing both training time and communication time is supported by our theoretical analysis and empirical results. In the scenario involving larger models and fewer available local data, Infocomm has been observed to reduce the elapsed time per round by over 37% without sacrificing accuracy compared to both conventional federated learning or directly combining federated learning and split learning, which showcases the advantages of Infocomm under power-constrained IoT scenarios. IEEE
Unmanned Aerial Vehicles(UAvs)as aerial base stations to provide communication services for ground users is a flexible and cost-effective paradigm in ***,dynamic resource allocation and multi-connectivity can be adopt...
详细信息
Unmanned Aerial Vehicles(UAvs)as aerial base stations to provide communication services for ground users is a flexible and cost-effective paradigm in ***,dynamic resource allocation and multi-connectivity can be adopted to further harness the potentials of UAVs in improving communication capacity,in such situations such that the interference among users becomes a pivotal disincentive requiring effective *** this end,we investigate the Joint UAV-User Association,Channel Allocation,and transmission Power Control(J-UACAPC)problem in a multi-connectivity-enabled UAV network with constrained backhaul links,where each UAV can determine the reusable channels and transmission power to serve the selected ground *** goal was to mitigate co-channel interference while maximizing long-term system *** problem was modeled as a cooperative stochastic game with hybrid discrete-continuous action space.A Multi-Agent Hybrid Deep Reinforcement Learning(MAHDRL)algorithm was proposed to address this *** simulation results demonstrated the effectiveness of the proposed algorithm and showed that it has a higher system utility than the baseline methods.
This study addresses the critical need for robust safeguarding of sensitive data stored on personal computing devices and during data transmissions, alongside the increasing need for secure digital interactions. Conve...
详细信息
The survival rate of lung cancer relies significantly on how far the disease has spread when it is detected, how it reacts to the treatment, the patient’s overall health, and other factors. Therefore, the earlier the...
详细信息
The survival rate of lung cancer relies significantly on how far the disease has spread when it is detected, how it reacts to the treatment, the patient’s overall health, and other factors. Therefore, the earlier the lung cancer diagnosis, the higher the survival rate. For radiologists, recognizing malignant lung nodules from computed tomography (CT) scans is a challenging and time-consuming process. As a result, computer-aided diagnosis (CAD) systems have been suggested to alleviate these burdens. Deep-learning approaches have demonstrated remarkable results in recent years, surpassing traditional methods in different fields. Researchers are currently experimenting with several deep-learning strategies to increase the effectiveness of CAD systems in lung cancer detection with CT. This work proposes a deep-learning framework for detecting and diagnosing lung cancer. The proposed framework used recent deep-learning techniques in all its layers. The autoencoder technique structure is tuned and used in the preprocessing stage to denoise and reconstruct the medical lung cancer dataset. Besides, it depends on the transfer learning pre-trained models to make multi-classification among different lung cancer cases such as benign, adenocarcinoma, and squamous cell carcinoma. The proposed model provides high performance while recognizing and differentiating between two types of datasets, including biopsy and CT scans. The Cancer Imaging Archive and Kaggle datasets are utilized to train and test the proposed model. The empirical results show that the proposed framework performs well according to various performance metrics. According to accuracy, precision, recall, F1-score, and AUC metrics, it achieves 99.60, 99.61, 99.62, 99.70, and 99.75%, respectively. Also, it depicts 0.0028, 0.0026, and 0.0507 in mean absolute error, mean squared error, and root mean square error metrics. Furthermore, it helps physicians effectively diagnose lung cancer in its early stages and allows spe
The rapid growth of digital data necessitates advanced natural language processing(NLP)models like BERT(Bidi-rectional Encoder Representations from Transformers),known for its superior performance in text ***,BERT’s ...
详细信息
The rapid growth of digital data necessitates advanced natural language processing(NLP)models like BERT(Bidi-rectional Encoder Representations from Transformers),known for its superior performance in text ***,BERT’s size and computational demands limit its practicality,especially in resource-constrained *** research compresses the BERT base model for Bengali emotion classification through knowledge distillation(KD),pruning,and quantization *** Bengali being the sixth most spoken language globally,NLP research in this area is *** approach addresses this gap by creating an efficient BERT-based model for Bengali *** have explored 20 combinations for KD,quantization,and pruning,resulting in improved speedup,fewer parameters,and reduced memory *** best results demonstrate significant improvements in both speed and *** instance,in the case of mBERT,we achieved a 3.87×speedup and 4×compression ratio with a combination of Distil+Prune+Quant that reduced parameters from 178 to 46 M,while the memory size decreased from 711 to 178 *** results offer scalable solutions for NLP tasks in various languages and advance the field of model compression,making these models suitable for real-world applications in resource-limited environments.
Direct training of Spiking Neural Networks (SNNs) is a challenging task because of their inherent temporality. Added to it, the vanilla Back-propagation based methods are not applicable either, due to the non-differen...
详细信息
Direct training of Spiking Neural Networks (SNNs) is a challenging task because of their inherent temporality. Added to it, the vanilla Back-propagation based methods are not applicable either, due to the non-differentiability of the spikes in SNNs. Surrogate-Derivative based methods with Backpropagation Through Time (BPTT) address these direct training challenges quite well;however, such methods are not neuromorphic-hardware friendly for the On-chip training of SNNs. Recently formalized Three-Factor based Rules (TFR) for direct local-training of SNNs are neuromorphic-hardware friendly;however, they do not effectively leverage the depth of the SNN architectures (we show it empirically here), thus, are limited. In this work, we present an improved version of a conventional three-factor rule, for local learning in SNNs which effectively leverages depth - in the context of learning features hierarchically. Taking inspiration from the Back-propagation algorithm, we theoretically derive our improved, local, three-factor based learning method, named DALTON (Deep LocAl Learning via local WeighTs and SurrOgate-Derivative TraNsfer), which employs weights and surrogate-derivative transfer from the local layers. Along the lines of TFR, our proposed method DALTON is also amenable to the neuromorphic-hardware implementation. Through extensive experiments on static (MNIST, FMNIST, & CIFAR10) and event-based (N-MNIST, DVS128-Gesture, & DVSCIFAR10) datasets, we show that our proposed local-learning method DALTON makes effective use of the depth in Convolutional SNNs, compared to the vanilla TFR implementation. IEEE
暂无评论