The proceedings contain 253 papers. The special focus in this conference is on Computational Science. The topics include: Practical Aspects of Zero-Shot Learning;a Hypothetical Agent-Based Model Inspired by ...
ISBN:
(纸本)9783031087509
The proceedings contain 253 papers. The special focus in this conference is on Computational Science. The topics include: Practical Aspects of Zero-Shot Learning;a Hypothetical Agent-Based Model Inspired by the Abstraction of Solitary Behavior in Tigers and Its Employment as a Chain Code for Compression;analyzing the Usefulness of Public Web Camera Video Sequences for Calibrating and Validating Pedestrian Dynamics Models;a Highly Customizable Information Visualization Framework;incremental Dynamic Analysis and Fragility Assessment of Buildings with Different Structural Arrangements Experiencing Earthquake-Induced Structural Pounding;PIES with Trimmed Surfaces for Solving Elastoplastic Boundary Problems;linear Computational Cost Implicit Variational Splitting Solver with Non-regular Material Data for Parabolic Problems;a Hadamard Matrix-Based Algorithm to Evaluate the Strength of Binary Sequences;compiling Linear Algebra Expressions into Efficient Code;private and Public Opinions in a Model Based on the Total Dissonance Function: A Simulation Study;analysis of Public Transport (in)accessibility and Land-Use Pattern in Different Areas in Singapore;pseudo-Newton Method with Fractional Order Derivatives;An Energy Aware Clustering Scheme for 5G-Enabled Edge computing Based IoMT Framework;a Framework for Network Self-evolving Based on distributed Swarm Intelligence;investigating an Optimal Computational Strategy to Retrofit Buildings with Implementing Viscous Dampers;ARIMA Feature-Based Approach to Time Series Classification;a Note on Adjoint Linear Algebra;approximate Function Classification;acceleration of Optimized Coarse-grid Operators by Spatial Redistribution for Multigrid Reduction in Time;Interval Modification of the Fast PIES in Solving 2D Potential BVPs with Uncertainly Defined Polygonal Boundary Shape;networks Clustering-Based Approach for Search of Reservoirs-Analogues;KP01 Solved by an n-Dimensional Sampling and Clustering Heuristic;A Deep Neural Network as a
In the era of advanced meteorological data platforms such as Copernicus and Climate Data Store, the frontier of weather forecasting has evolved. The primary challenge is no longer the acquisition of accurate and high-...
详细信息
ISBN:
(数字)9798350365610
ISBN:
(纸本)9798350365627
In the era of advanced meteorological data platforms such as Copernicus and Climate Data Store, the frontier of weather forecasting has evolved. The primary challenge is no longer the acquisition of accurate and high-resolution data, but rather the effective integration and utilization of diverse observational datasets to enhance localized weather predictions. Crowd sensed weather data through a network of low-cost, widely distributed weather stations can provide the granular data needed for precise local forecasts. However, this approach introduces challenges such as data integration, consistency, and privacy concerns. Federated Learning (FL) addresses these issues by enabling decentralized data processing while maintaining data *** paper introduces an innovative implementation of a federated learning framework integrated with a cluster of Automated Weather Stations (AWS). The primary objective of this study is to leverage federated learning to enhance the predictive accuracy of the Weather Research and Forecasting (WRF) model by using each weather station not only as a data acquisition point but also as a computational node. This decentralized approach maintains data privacy and security while enabling local training of models, such as Crossformer, Autoformer, and DLinear. These models’ locally trained weights are periodically aggregated on the central server, which updates and redistributes the global *** on data collected over two years from two automated weather stations, the experimental results analyze the possibility of improving WRF model predictions for temperature and humidity. This research highlights the potential of Federated Learning in meteorological applications, offering a robust solution for enhancing weather forecast accuracy while ensuring data privacy and efficient resource utilization.
Software vulnerabilities are a major cyber threat and it is important to detect them. One important approach to detecting vulnerabilities is to use deep learning while treating a program function as a whole, known as ...
详细信息
ISBN:
(数字)9798400702174
ISBN:
(纸本)9798350382143
Software vulnerabilities are a major cyber threat and it is important to detect them. One important approach to detecting vulnerabilities is to use deep learning while treating a program function as a whole, known as function-level vulnerability detectors. However, the limitation of this approach is not understood. In this paper, we investigate its limitation in detecting one class of vulnerabilities known as inter-procedural vulnerabilities, where the to-be-patched statements and the vulnerability-triggering statements belong to different functions. For this purpose, we create the first Inter -Procedural Vulnerability Dataset (InterPVD) based on C/C++ open-source software, and we propose a tool dubbed VulTrigger for identifying vulnerability-triggering statements across functions. Experimental results show that VulTrigger can effectively identify vulnerability-triggering statements and inter-procedural vulnerabilities. Our findings include: (i) inter-procedural vulnerabilities are prevalent with an average of 2.8 inter-procedural layers; and (ii) function-level vulner-ability detectors are much less effective in detecting to-be-patched functions of inter-procedural vulnerabilities than detecting their counterparts of intra-procedural vulnerabilities.
The proceedings contain 253 papers. The special focus in this conference is on Computational Science. The topics include: Practical Aspects of Zero-Shot Learning;a Hypothetical Agent-Based Model Inspired by ...
ISBN:
(纸本)9783031087530
The proceedings contain 253 papers. The special focus in this conference is on Computational Science. The topics include: Practical Aspects of Zero-Shot Learning;a Hypothetical Agent-Based Model Inspired by the Abstraction of Solitary Behavior in Tigers and Its Employment as a Chain Code for Compression;analyzing the Usefulness of Public Web Camera Video Sequences for Calibrating and Validating Pedestrian Dynamics Models;a Highly Customizable Information Visualization Framework;incremental Dynamic Analysis and Fragility Assessment of Buildings with Different Structural Arrangements Experiencing Earthquake-Induced Structural Pounding;PIES with Trimmed Surfaces for Solving Elastoplastic Boundary Problems;linear Computational Cost Implicit Variational Splitting Solver with Non-regular Material Data for Parabolic Problems;a Hadamard Matrix-Based Algorithm to Evaluate the Strength of Binary Sequences;compiling Linear Algebra Expressions into Efficient Code;private and Public Opinions in a Model Based on the Total Dissonance Function: A Simulation Study;analysis of Public Transport (in)accessibility and Land-Use Pattern in Different Areas in Singapore;pseudo-Newton Method with Fractional Order Derivatives;An Energy Aware Clustering Scheme for 5G-Enabled Edge computing Based IoMT Framework;a Framework for Network Self-evolving Based on distributed Swarm Intelligence;investigating an Optimal Computational Strategy to Retrofit Buildings with Implementing Viscous Dampers;ARIMA Feature-Based Approach to Time Series Classification;a Note on Adjoint Linear Algebra;approximate Function Classification;acceleration of Optimized Coarse-grid Operators by Spatial Redistribution for Multigrid Reduction in Time;Interval Modification of the Fast PIES in Solving 2D Potential BVPs with Uncertainly Defined Polygonal Boundary Shape;networks Clustering-Based Approach for Search of Reservoirs-Analogues;KP01 Solved by an n-Dimensional Sampling and Clustering Heuristic;A Deep Neural Network as a
This work presents a new control for a battery energy storage (BES) integrated solar photovoltaic (PV) arrays-based microgrid (MG) synchronised to the three phase four wire (3P4W) grid. The maximum power is obtained v...
详细信息
ISBN:
(纸本)9781728156811
This work presents a new control for a battery energy storage (BES) integrated solar photovoltaic (PV) arrays-based microgrid (MG) synchronised to the three phase four wire (3P4W) grid. The maximum power is obtained via two PV arrays through distinctive maximum power point (MPP) tracking technique. A boost converter is utilized to connect the first PV array at the main voltage source converter (VSC) DC link, where a BES is also linked to it. In the single stage topology, the second PV array's output is integrated directly at ancillary VSC's DC link. The main VSC's control approach is based on the current control technique under the grid interactive mode and during the grid discontinuation, it shifts to the voltage control approach under an islanded mode of operation. The rating of MG is enhanced as the terminals of each VSC in parallel, are connected at the point of common coupling (PCC). The nonlinear loads are integrated VSC's terminals. The solar power is fed to the grid in the grid interactive mode and the system's operational reliability is enhanced in the standalone mode. The main VSC's dual mode smooth control is implemented via the power electronics switch. At PCC, the main VSC voltage control, sustains the frequency and voltage, therefore, the ancillary VSC's, operation is always with the current control. An incessant power is distributed to the load side. The utilization of PV array power feed-forward term in the current control of VSCs enhance the dynamic performance. The system compensates the neutral current and takes care power quality concerns i.e. alleviation of current harmonics and power factor improvement. In the MATLAB environment, the microgrid behaviour is perceived satisfactory under steady state and dynamic circumstances such as, solar power perturbation, load unbalance and load perturbation.
The outbreak of the COVID-19 pandemic has resulted in a significant impact on global health and economy. Forecasting the spread of COVID-19 cases is essential for policymakers to make informed decisions and allocate r...
The outbreak of the COVID-19 pandemic has resulted in a significant impact on global health and economy. Forecasting the spread of COVID-19 cases is essential for policymakers to make informed decisions and allocate resources accordingly. Deep learning has shown promising results in predicting the spread of infectious diseases, including COVID-19. However, selecting the most appropriate model for a given forecasting task can be challenging, as no single model is guaranteed to perform well for all scenarios. In this paper, we propose a distributed ensemble approach that combines the predictions of different deep learning models, including Autoregressive Integrated Moving Average (Auto-ARIMA), Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), to improve the accuracy of COVID-19 case forecasts. Specifically, we train each deep learning model on a subset of the data and aggregate their predictions to obtain an ensemble forecast. To achieve a distributed ensemble, we use an edge computing framework to train the deep learning models on multiple nodes in a parallel and distributed manner. We evaluate our approach on publicly available COVID-19 datasets, and our results show that the proposed ensemble model outperforms the individual models in terms of forecasting accuracy. Furthermore, our distributed ensemble approach significantly reduces the training and prediction time compared to training each model separately.
The modern Big Data ecosystem provides tools to build a flexible platform for processing data streams and batch datasets. Supporting both the functioning of modern giant particle physics experiments and the services n...
详细信息
Assigning an agent to each inverter interface power supply in the Microgrid to complete communication and data calculation;designing the communication topology among the agents based on n−1 rule;identifying the Microg...
详细信息
With the high penetration of renewable energy sources, traditional voltage regulation ancillary services provided by conventional generation may face challenges of scarcity. Microgrids (MGs), leveraging flexible resou...
详细信息
ISBN:
(数字)9798350351668
ISBN:
(纸本)9798350351675
With the high penetration of renewable energy sources, traditional voltage regulation ancillary services provided by conventional generation may face challenges of scarcity. Microgrids (MGs), leveraging flexible resources such as energy storage and generation units, inherently possess voltage support capabilities. Therefore, we propose a two-stage optimization approach to explore the potential of MGs in providing voltage regulation ancillary services. In stage 1, decentralized peer-to-peer (P2P) transactions are conducted, and profit allocation is performed using the supply-demand ratio (SDR) method. In stage 2, optimization of ancillary service trading strategies is carried out, and a secondary distribution of ancillary service subsidies is conducted using a network loss sharing method based on the Shapley value. This aims to reduce the operational costs of the distribution system operator (DSO). In addition, an improved alternating direction method of multipliers (ADMM) algorithm is proposed for the distributed solution of the two stages. Through simulation using a modified IEEE 33-node distribution system, the proposed method is validated to incentivize MGs to provide voltage regulation ancillary services at lower costs for the DSO, thereby preventing voltage violations.
The proceedings contain 253 papers. The special focus in this conference is on Computational Science. The topics include: Practical Aspects of Zero-Shot Learning;a Hypothetical Agent-Based Model Inspired by ...
ISBN:
(纸本)9783031087561
The proceedings contain 253 papers. The special focus in this conference is on Computational Science. The topics include: Practical Aspects of Zero-Shot Learning;a Hypothetical Agent-Based Model Inspired by the Abstraction of Solitary Behavior in Tigers and Its Employment as a Chain Code for Compression;analyzing the Usefulness of Public Web Camera Video Sequences for Calibrating and Validating Pedestrian Dynamics Models;a Highly Customizable Information Visualization Framework;incremental Dynamic Analysis and Fragility Assessment of Buildings with Different Structural Arrangements Experiencing Earthquake-Induced Structural Pounding;PIES with Trimmed Surfaces for Solving Elastoplastic Boundary Problems;linear Computational Cost Implicit Variational Splitting Solver with Non-regular Material Data for Parabolic Problems;a Hadamard Matrix-Based Algorithm to Evaluate the Strength of Binary Sequences;compiling Linear Algebra Expressions into Efficient Code;private and Public Opinions in a Model Based on the Total Dissonance Function: A Simulation Study;analysis of Public Transport (in)accessibility and Land-Use Pattern in Different Areas in Singapore;pseudo-Newton Method with Fractional Order Derivatives;An Energy Aware Clustering Scheme for 5G-Enabled Edge computing Based IoMT Framework;a Framework for Network Self-evolving Based on distributed Swarm Intelligence;investigating an Optimal Computational Strategy to Retrofit Buildings with Implementing Viscous Dampers;ARIMA Feature-Based Approach to Time Series Classification;a Note on Adjoint Linear Algebra;approximate Function Classification;acceleration of Optimized Coarse-grid Operators by Spatial Redistribution for Multigrid Reduction in Time;Interval Modification of the Fast PIES in Solving 2D Potential BVPs with Uncertainly Defined Polygonal Boundary Shape;networks Clustering-Based Approach for Search of Reservoirs-Analogues;KP01 Solved by an n-Dimensional Sampling and Clustering Heuristic;A Deep Neural Network as a
暂无评论