This paper discusses the analysis, simulation and experimental investigation of selective harmonics elimination with pulse width modulation using Newton-Raphson algorithm for three phase inverter. The purpose of using...
详细信息
Recent advances in deep learning (DL) have resulted in a proliferation of techniques able to colourise achromatic or monotone images. This was a previously dormant area of image processing due to the under-constrained...
详细信息
This paper presents a multiband metamaterial (MM) absorber that displays the metamaterial characteristics at each resonance frequency. Broadband absorption is achieved in the X band at the range of 10.373 GHz to 10.82...
详细信息
The need for a communication system using VSAT technology on the Ku-Band band is now starting to develop in Indonesia, both the need for pay TV or internet provision, The problem in using VSAT Ku-band technology is pr...
详细信息
Data-driven network slicing has been recently explored as a major driver for beyond 5G networks. Nevertheless, we are still a long way before such solutions are practically applicable in real problems. Most solutions ...
详细信息
Data-driven network slicing has been recently explored as a major driver for beyond 5G networks. Nevertheless, we are still a long way before such solutions are practically applicable in real problems. Most solutions addressing the problem of dynamically placing virtual network function chains (‘‘slices’’) on top of a physical topology still face one or more of the following hurdles: (i) they focus on simple slicing setups (e.g. single domain, single slice, simple VNF chains and performance metrics);(ii) solutions based on modern reinforcement learning theory have to deal with astronomically high action spaces, when considering multi-VNF, multi-domain, multi-slice problems;(iii) the training of the algorithms is not particularly data-efficient, which can hinder their practical application given the scarce(r) availability of cellular network related data (as opposed to standard machine learning problems). To this end, we attempt to tackle all the above shortcomings in one common framework. For (i), we propose a generic, queuing network based model that captures the inter-slice orchestration setting, supporting complex VNF chain topologies and end-to-end performance metrics. For (ii), we explore multi-agent DQN algorithms that can reduce action space complexity by orders of magnitude compared to standard DQN. For (iii), we investigate two mechanisms to store to and select from the experience replay buffer, in order to speed up the training of DQN agents. The proposed scheme was validated to outperform both vanilla DQN (by orders of magnitude faster convergence) and static heuristics (3× cost improvement). 2024 The Authors. This work is licensed under a Creative Commons Attribution 4.0 License.
We present here the main research topics and activities on the design, security, safety, and robustness of machine learning models developed at the Pattern Recognition and Applications Laboratory (PRALab) of the Unive...
详细信息
Multi-agent cyber-physical systems are present in a variety of applications. Agent decision-making can be affected due to errors induced by uncertain, dynamic operating environments or due to incorrect actions taken b...
详细信息
Global water scarcity presents a considerable challenge, with direct implications to human health, socioeconomic development, and food insecurity on a massive scale. Now more than ever, sustainable engineering solutio...
详细信息
Electromagnetic actuators based on levitation are widely employed for precision applications because of their extremely high positioning resolution. While the majority of these actuators require measurement and contro...
详细信息
The production of electrical energy is now a crucial component of the power system due to the rising demand brought on by population expansion and economic development. Experts are looking for new and more sustainable...
详细信息
暂无评论