parallel and distributed computing has become a necessity when it comes to high-performance computing, artificial intelligence, big data analytics, machine learning, deep learning, signal processing and bioengineering...
详细信息
With the increasing complexity of global procurement chains, the efficiency and security of financial information sharing have become key to improving procurement chain management. This study aims to explore the appli...
详细信息
Traditional decision support systems (DSS) show obvious limitations in dealing with increasingly complex and dynamic decision-making scenarios. By integrating graph neural networks (GNNs) and expert systems (ESs), thi...
详细信息
The large-scale penetration of distributed photovoltaic (PV) power generation systems has brought new challenges to the topology identification and detection of traditional distribution networks. This article mainly s...
详细信息
ISBN:
(纸本)9798350375145;9798350375138
The large-scale penetration of distributed photovoltaic (PV) power generation systems has brought new challenges to the topology identification and detection of traditional distribution networks. This article mainly studies the topology identification technology (TIT) of distributed PV low-voltage (LV) distribution network lines, aiming to design a topology identification method that can adapt to the dynamic changes of the power grid, have large-scale capacity, and improve system accuracy under the same conditions. At the same time, the data processing speed has been improved. This article first constructs a system model, including node model, edge model, and parameter model. It mathematically represents the topology structure of the power grid using graph theory and designs a topology recognition algorithm based on optimization techniques and state estimation. This algorithm is used to solve the distributed characteristics of power grid topology recognition, the difficulty of data collection, the dynamic diversity of power grid structure, the uncertainty of equipment parameters, the high computational complexity of data processing, and the communication constraints of power grid topology recognition. This algorithm adopts modern programming languages and parallel computing frameworks, making it easy to implement efficiently. The results on the simulation platform show that the highest recall rate for 22 test cases is 93.8%, and the response time for test cases is 425 ms to 980 ms, providing a fast response to the information space of the grid.
This paper introduces a framework designed to address the challenges posed by numerous small-capacity distributed energy resources (DERs), which significantly complicate management for distribution system operators. T...
详细信息
The proceedings contain 68 papers. The topics discussed include: effect of the downstream blockage induced under-rib convection on oxygen feeding in a PEMFC with parallel flow field;simulation and analysis of the dete...
The proceedings contain 68 papers. The topics discussed include: effect of the downstream blockage induced under-rib convection on oxygen feeding in a PEMFC with parallel flow field;simulation and analysis of the detection effect of seafloor shallow thermal origin gas release by marine resistivity method;dual-objective optimal scheduling of grid-connected distributed photovoltaic systems considering life loss cost of energy storage;research on security protection strategies for household distributed photovoltaic clusters;short-term wind speed prediction based on time series trends and periodic characteristics;experimental research on heating performance of solar energy coupled with water source heat pump system;research on variable pressure oil supply servo system based on accumulator;and optimal scheduling of building integrated energy system considering the interaction of electric energy and heat energy.
A malicious traffic intrusion detection method based on packet payload is proposed to address the current flow based intrusion detection models that overly rely on statistical information from packet headers and ignor...
详细信息
ISBN:
(纸本)9798400718212
A malicious traffic intrusion detection method based on packet payload is proposed to address the current flow based intrusion detection models that overly rely on statistical information from packet headers and ignore the characteristics of packet payloads. Firstly, by using the packet payload labeling algorithm, the labeled payload data is obtained, and then the data is cleaned and standardized;Input it into the constructed composite neural network, use parallel neural networks to extract spatial features of payloads, and finally input the extracted features into the fully connected layer for classification. To demonstrate the feasibility of this research method, experimental results on the UNSW-NB15 dataset of the Internet of Things showed that the method is practical and feasible, achieving a higher F1 score compared to the comparative method.
Apache Flink is one of the mainstream big data distributed computing engines. In distributed computing systems, task scheduling is crucial, and uneven load is a common scenario caused by heterogeneous clusters and une...
详细信息
The proceedings contain 61 papers. The topics discussed include: research on new distributed distribution network hidden fault remote automatic recovery technology;research on high-resolution capacitance detection cir...
The proceedings contain 61 papers. The topics discussed include: research on new distributed distribution network hidden fault remote automatic recovery technology;research on high-resolution capacitance detection circuit based on T-type network;parallel circuit currents in stator windings of a pumped storage power station;a current-mode bandgap reference with robust start-up behavior;a novel boost power converter suitable for bearingless switched reluctance motor with wider rotor teeth;research on discharge characteristics of synthetic ester-paper insulation under power frequency and low frequency;research on the application of balanced windings in wind farm booster stations;simulation of temperature rise in low voltage winding of natural oil circulation transformer and analysis of oil flow heat dissipation;and optimum frequency tracking of the ultrasonic motor based on a three-level constant voltage drive.
The proceedings contain 46 papers. The topics discussed include: building a cancer type prediction model based on machine learning algorithms by analyzing the origin genes of multiple cancers including prostate cancer...
ISBN:
(纸本)9798350388725
The proceedings contain 46 papers. The topics discussed include: building a cancer type prediction model based on machine learning algorithms by analyzing the origin genes of multiple cancers including prostate cancer;cross-domain specific emitter identification based on domain adversarial multi-constraint;a robust defense algorithm for backdoor erasure based on attention alignment in federated learning;research and design of data link twin system;a simple image denoising method associated with image edge protection;research on optimal allocation of integrated resources of mergers and acquisitions based on distributed cloud computing;power control based on deep Q learning in heterogeneous networks;HybridTrajNet: enhancing pedestrian trajectory prediction with multi-scale attention and large selective kernel;and a method for essential proteins identification by integrating topological and biological characteristics in PPI network.
暂无评论