Optimal Resource Allocation of 5G Machine-Type Communications for Situation Awareness in Active Distribution Networks

Li, Qiyue; Tang, Haochen; Liu, Zhi; Li, Jie; Xu, Xiaoli; Sun, Wei

doi:10.1109/jsyst.2021.3110502

Cited by 8 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data augmentation results: First we perform data augmentation on IFPD and SGAH datasets, and the results are shown in Table II. 2 https://github.com/smartlab-hfut/AD-TFM-AT-Model Then we select the original data and augmented data on a pro-rata basis (8:2) to train and test our proposed AD-TFM-AT neural network. The performance is shown in the Table III.…”

Section: B Experimental Resultsmentioning

confidence: 99%

Incipient Fault Detection in Power Distribution System: A Time–Frequency Embedded Deep-Learning-Based Approach

Luo

Cheng

et al. 2023

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

Incipient fault detection in power distribution systems is crucial to improve the reliability of the grid. However, the non-stationary nature and the inadequacy of the training dataset due to the self-recovery of the incipient fault signal, make the incipient fault detection in power distribution systems a great challenge. In this paper, we focus on incipient fault detection in power distribution systems and address the above challenges.In particular, we propose an ADaptive Time-Frequency Memory (AD-TFM) cell by embedding wavelet transform into the Long Short-Term Memory (LSTM), to extract features in time and frequency domain from the non-stationary incipient fault signals.We make scale parameters and translation parameters of wavelet transform learnable to adapt to the dynamic input signals.Based on the stacked AD-TFM cells, we design a recurrent neural network with ATtention mechanism, named AD-TFM-AT model, to detect incipient fault with multi-resolution and multi-dimension analysis. In addition, we propose two data augmentation methods, namely phase switching and temporal sliding, to effectively enlarge the training datasets. Experimental results on two open datasets show that our proposed AD-TFM-AT model and data augmentation methods achieve state-of-theart (SOTA) performance of incipient fault detection in power distribution system. We also disclose one used dataset logged at State Grid Corporation of China to facilitate future research.

show abstract

Section: B Experimental Resultsmentioning

confidence: 99%

Incipient Fault Detection in Power Distribution System: A Time–Frequency Embedded Deep-Learning-Based Approach

Luo

Cheng

et al. 2023

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The overarching aim is to minimize the overall energy consumption of the system. In [28], the authors have presented a 5G framework. This framework is adept at reserving RBs for emergency data while formulating the resource allocation strategy as a task focused on maximizing energy efficiency.…”

Section: Related Workmentioning

confidence: 99%

An Energy-Aware Tailored Resource Management for Cellular-Based Zero-Touch Deterministic Industrial M2M Networks

Prathiba,

Raja,

Saiabirami

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Zero-Touch Deterministic Industrial Machine-to-Machine (ZT-DI-M2M) serves as a customized communication solution designed to meet the specific needs of industrial settings. Though 5G is the promising solution for ZT-DI-M2M, optimized scheduling in 5G remains challenging to design over aspects such as network overload and congestion control, especially in the uplink transmission of ZT-DI-M2M. Effective allocation of resources for Machine-Type Communication (MTC) devices stands out as a pivotal hurdle within the domain of 5G networks. This challenge directly influences the longevity of batteryoperated devices and the Quality of Service (QoS) experienced by applications. This paper aims to develop a Group-Based and Energy Aware (GBEA) resource allocation algorithm for M2M communication in the 5G networks. The GBEA algorithm solves the resource allocation problem by initially clustering the active nodes concerning their delays. Consequently, inter and intra-cluster resource distribution occurs through the Gaussian Mixture Model Expectation Maximization (GMM-EM) algorithm. The GBEA algorithm optimizes the resource allocation of M2M devices by factoring delay, energy, proximity, and fairness into the allocation process. The simulation outcomes unveil the superiority of the GBEA scheduling algorithm over established state-of-the-art resource allocation methods. It showcases remarkable enhancements in terms of throughput, delay sensitivity, and energy efficiency, boasting nearly 1.5-fold, 1.75-fold, and 6.5-fold respective improvements.

show abstract

“…5 is the constraint on the data queue number of high-concurrency access of of cloud server , i.e., at most data queues are allowed to access to . 6 is the constraint on the data queue backlogs of high-concurrency access of cloud server . A data queue is not allowed to access to if the total data queue backlog exceeds max .…”

Section: Cloud-edge-device Collaborative High-concurrency Access Mana...mentioning

confidence: 99%

“…The large-scale integration of renewable energy into distribution grid has spurred new types of services such as distributed renewable energy control, intelligent load demand response, and high-frequency electric information acquisition [1]- [5]. These services involve thousands of internet of things (IoT) devices for data collection, transmission, and computation, which impose high requirements on high-concurrency access of massive data [6]- [9]. Cloud-edge-device collaboration has provided a feasible solution by combining advantages of edge computing and cloud computing [10]- [14].…”

Section: Introductionmentioning

confidence: 99%

Cloud-Edge-Device Collaborative High Concurrency Access Management for Massive IoT Devices in Distribution Grid

LI,

YOU,

ZHANG

et al. 2024

IEICE Trans. Fundamentals

View full text Add to dashboard Cite

Emerging data-intensive services in distribution grid impose requirements of high-concurrency access for massive internet of things (IoT) devices. However, the lack of effective high-concurrency access management results in severe performance degradation. To address this challenge, we propose a cloud-edge-device collaborative high-concurrency access management algorithm based on multi-timescale joint optimization of channel pre-allocation and load balancing degree. We formulate an optimization problem to minimize the weighted sum of edge-cloud load balancing degree and queuing delay under the constraint of access success rate. The problem is decomposed into a large-timescale channel pre-allocation subproblem solved by the device-edge collaborative access priority scoring mechanism, and a small-timescale data access control subproblem solved by the discounted empirical matching mechanism (DEM) with the perception of high-concurrency number and queue backlog. Particularly, information uncertainty caused by externalities is tackled by exploiting discounted empirical performance which accurately captures the performance influence of historical time points on present preference value. Simulation results demonstrate the effectiveness of the proposed algorithm in reducing edgecloud load balancing degree and queuing delay.

show abstract

Optimal Resource Allocation of 5G Machine-Type Communications for Situation Awareness in Active Distribution Networks

Cited by 8 publications

References 25 publications

Incipient Fault Detection in Power Distribution System: A Time–Frequency Embedded Deep-Learning-Based Approach

Incipient Fault Detection in Power Distribution System: A Time–Frequency Embedded Deep-Learning-Based Approach

An Energy-Aware Tailored Resource Management for Cellular-Based Zero-Touch Deterministic Industrial M2M Networks

Cloud-Edge-Device Collaborative High Concurrency Access Management for Massive IoT Devices in Distribution Grid

Contact Info

Product

Resources

About