检索结果-内蒙古大学图书馆

International Conference on European Electricity Market, EEM

作者： Hugo Algarvio António Couto Ana Estanqueiro Rui Carvalho Gabriel Santos Ricardo Faia Pedro Faria Zita Vale Renewable Energy and Energy Efficiency Unit LNEG-National Laboratory of Energy and Geology Lisboa Portugal GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development LASI - Intelligent Systems Associate Laboratory Polytechnic of Porto Porto Portugal

ISBN: (数字)9798350381740

ISBN: (纸本)9798350381757

Typically, Transmission System Operators apply power flow models with Seasonal Line Rating prescriptions to compute the ampacity of power lines, in a process that enables to obtain the cross-border capacity for trading between different countries or market zones. These seasonal-dependent models rely on fixed conservative meteorological conditions throughout the year, underestimating the real-time transmission capacity of overhead lines. This can contribute to market splitting occurrences, i.e., a situation where the cleared power flow between different market zones of the coupled market is superior to the cross-border capacity, separating markets, which brings economic losses to market participants. Dynamic Line Rating analysis allows computing the overhead lines’ capacity considering the weather conditions that influence the power line's thermal dynamics. This work presents a study that applies the CIGRÉ 601 model in cross-border power lines between Portugal and Spain to quantify the reduction in market splitting occurrences in the day-ahead Iberian market considering based on the installed capacities from the 2030 national energy and climate plans. Comparing with the seasonal approach, dynamic line rating enabled to reduce the number of market splitting occurrences from 1512 to 514, reducing the electricity costs by more than 1% and the price difference from 19 to 12 €/MWh.

关键词： Costs Computational modeling Biological system modeling Electricity Europe Real-time systems Thermal analysis

来源：评论

学校读者我要写书评

暂无评论

An adaptive language model-based intelligent medication assistant for the decision support of antidepressant prescriptions

引用

Computers in Biology and Medicine 2025年 190卷 110065-110065页

作者： Silva, Regina Gomes, Luis Centro Hospitalar Universitário de Santo António Unidade Local de Saúde de Santo António Porto Portugal GECAD – Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development LASI – Intelligent Systems Associate Laboratory ISEP Polytechnic of Porto Porto Portugal

Background: Depression, a pervasive mental disorder affecting millions worldwide, requires a holistic and personalized approach to treatment. Combining therapy and antidepressant medication is crucial, but selecting the right medication remains a complex task due to the variety of options available, each with unique, contraindications and drug interactions. While intelligent clinical decision support systems exist, there is a gap in medication-specific solutions. This paper proposes an innovative intelligent medication assistant, leveraging retrieval-augmented generation and large language models to provide personalized recommendations considering patient records and current health situation. Method: The proposed assistant tailors recommendations based on individual context by injecting patient-specific documents into large language models, enhancing efficiency and minimizing adverse effects. Our approach adapts to various query formats and dynamically incorporates relevant sources, empowering healthcare providers to make informed decisions. The analysis covers 40 clinical cases of patients requiring psychiatric monitoring. The patient's basic biography, clinical context, and ongoing situation were presented for each model, followed by questions about antidepressant pharmacological treatment. Results: The case study used 40 mental health patient clinical cases, and the results showed that the proposed assistant represents a significant advancement for the health provider, enabling the support, fast search, and consultation of medication information leaflets in almost real-time. A total of ten large language models with two configurations each were evaluated. Two commercial models and eight open local models were used. Conclusions: The commercial model gpt4o had a total score of 4.10/5.00, while the open model llama3 had a total score of 2.92/5.00. The results showed that commercial models present better results than open models, providing more accurate answers, cons

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Distributed Energy Resource Scheduling with Focus on Demand Response Complex Contracts

引用

Journal of Modern Power Systems and Clean Energy 2021年第5期9卷 1172-1182页

作者： Pedro Faria Zita Vale GECAD–Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development R.Dr.António Bernardino de Almeida4314249-015PortoPortugal Polytechnic of Porto R.Dr.António Bernardino de Almeida4314249-015PortoPortugal

Demand response(DR)is a flexible way to improve distributed energy resource *** innovative contribution of this paper is to include complex contracts in the model,which can accommodate the constraints according to the special expectations of each *** contracts are included in the optimization of distributed energy resource scheduling to dispatch DR according to the expectations of ***-period DR events are *** this way,consumers can specify the limits on the time,power,and remuneration regarding participation in DR events,which has not been considered in the *** state of the art treats these aspects separately or uses a statistical approach,without providing consumers with options to combine their preferences regarding different aspects of their flexibility *** model has been validated for 218 consumers using several scenarios and different types of distributed generation,showing that it is possible to increase DR with respect to the preferences of consumers.

关键词： Complex contracts demand response distributed generation virtual power player

来源：评论

学校读者我要写书评

暂无评论

Defining an Architecture for a Remote Monitoring Platform to Support the Self-management of Vascular Diseases

Defining an Architecture for a Remote Monitoring Platform to...

引用

International Conference on Practical Applications of Agents and Multi-Agent Systems, PAAMS 2021

作者： Vieira, Ana Carneiro, João Conceição, Luís Martins, Constantino Souza, Julio Freitas, Alberto Marreiros, Goreti GECAD – Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development Institute of Engineering Polytechnic of Porto Porto Portugal CINTESIS – Center for Health Technology and Services Research Porto Portugal

ISBN: (纸本)9783030857097

The aging of the worldwide population has led to a growing prevalence of vascular diseases, negatively impacting national healthcare systems and patients. The application of information technologies in the health sector has the potential to allow the remote monitoring of patients and the personalization of healthcare. This work proposes the architecture for a remote monitoring platform that supports the self-management of vascular diseases in the context of the Inno4Health project, with the goal of stimulating the innovation in the continuous monitoring of the patients’ health. The platform aims to support health professionals and patients with vascular diseases through the continuous monitoring of their health condition and presentation of monitoring reports. Self-management tools will be provided to patients through the presentation of personalized recommendations adapted to their current health condition. By doing so, we believe it will be possible to improve the patients’ self-management of their disease as well as decrease the risk of disease-related complications. © 2021, Springer Nature Switzerland AG.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Virtual Sensor for Door Opening Detection and Anomaly Detection Using Machine Learning

Virtual Sensor for Door Opening Detection and Anomaly Detect...

引用

International Conference on intelligent Systems Applications to Power Systems (ISAP)

作者： Almir Neto Luis Gomes Zita Vale Federal Institute of Education Science and Technology of Maranhão (IFMA) São Luís Brazil GECAD-Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development Polytechnic of Porto (P.PORTO) Porto Portugal

ISBN: (数字)9798331531751

ISBN: (纸本)9798331531768

Currently, several studies are being developed using machine Learning with the aim of replacing real sensors with virtual sensors. One of the biggest challeng.s is obtaining quality data to enable the system modeling. This article proposes the replacement of a light dependent resistor sensor, applied to a refrigerator, which detects whether the door is open or closed and an anomaly test when the door is forgotten open for too long. The use of tiny machine learning is applied to ESP32 to enable the use of regression and classification models to detect the door opening and anomaly. The tested metrics for the regression were the root mean squared error. The comparative results between the virtual and real sensors are satisfactory with an accuracy of 99.59% for classification and a root mean squared error value of 0.01 for regression. Furthermore, a prototype was developed, and the model was embedded in the ESP32 microcontroller.

关键词： Temperature sensors Temperature measurement Microcontrollers Soft sensors Tiny machine learning Neural networks Prototypes Virtualization intelligent sensors Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Contextual adaptative interfaces for industry 4.0 17th

Contextual adaptative interfaces for industry 4.0

引用

17th International Symposium on Distributed computing and Artificial Intelligence, DCAI 2020

作者： Canito, Alda Mota, Daniel Marreiros, Goreti Corchado, Juan M. Martins, Constantino GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development Institute of Engineering Polytechnic of Porto Porto Portugal Department of Computer Science University of Salamanca Salamanca Spain

ISBN: (纸本)9783030538286

Information technologies are intrinsically connected to the manufacturing processes, with more data generated each second. To efficiently operate machines, users must sort out information that is relevant to them in specific moments and contexts. In this paper, we propose an architecture that combines context – e.g. location, type of order, available assets, previous actions – with information established through user stereotypes. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

关键词： Industry 4.0

来源：评论

学校读者我要写书评

暂无评论

Comparison of PV Power Generation Forecasting in a Residential Building using ANN and DNN

引用

IFAC-PapersOnLine 2022年第9期55卷 291-296页

作者： Inês Tavares Ricardo Manfredini José Almeida João Soares Sérgio Ramos Zahra Foroozandeh Zita Vale GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development School of Engineering Polytechnic of Porto Porto Portugal IFRS-Campus Farroupilha Rio Grande do Sul Brasil

Due to the fast growth of energy consumption in buildings, it is crucial to ensure sustainability demands through the use of renewable energies. The solar energies have been standing out and, as a result, the forecast of photovoltaic (PV) production has received broad attention. However, the intermittent nature of the generated power brings some uncertainty. This paper presents two PV generation forecasting methodologies based on a multi-layer feed-forward Artificial Neural Networks (ANN) and a Deep Neural Networks (DNN) combined with a Convolution Neural Network layer and a Recurrent Neural Network layer. Both techniques were implemented based on a data set of a PV production from a panel installed at a residential building. The main objective of this paper is to analyze and compare the forecasting results precision of both techniques. The accuracy of both models was evaluated through the calculated errors. The comparative analysis between the two networks demonstrated that the ANN technique is capable of predicting the PV generation with low forecasting errors.

关键词： Machine learning PV power generation forecast Artificial Neural Networks Deep Neural Networks

来源：评论

学校读者我要写书评

暂无评论

A Brief Review on Optimal Network Planning Considering Energy Storage Systems and Uncertainty

A Brief Review on Optimal Network Planning Considering Energ...

引用

Future Energy Solutions (FES), International Conference on

作者： Fábio Castro João Soares Bruno Canizes Zita Vale GECAD -Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development LASI – Intelligent Systems Associate Laboratory Polytechnic of Porto R. Dr. António Bernardino de Almeida 431 Porto Portugal

The topic of optimal planning has always been relevant ever since modern-day electricity markets were established. With the increasing awareness for a stable future, environmentally renewable sources of electricity production have seen a major uprise in latest years. Along with its inherent benefits, this increase in penetration of renewable energy sources also causes some unforeseen issues, such as lower network flexibility since most renewable production is intermittent and unpredictable, and harder generation forecasting for the same reasons. Many authors have researched ways to mitigate these issues, and most point to utilizing energy storage systems. Energy storage and uncertainty are not necessarily new topics, but they are now more prominent than ever and a must in recent optimal planning models regarding electricity networks. This paper aims to highlight some contributions made by literature regarding the topic, focusing on models studying energy storage systems, models that consider uncertainty, and models that consider both.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hourly uncertainty applied to optimal expansion planning considering energy storage and seasonal network impacts

Hourly uncertainty applied to optimal expansion planning con...

引用

IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe)

作者： Fábio Castro Bruno Canizes João Soares Zita Vale GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development LASI – Intelligent Systems Associate Laboratory Polytechnic of Porto R. Dr. António Bernardino de Almeida 431 Porto Portugal

The prevalence of renewable energy on most networks has grown exponentially in recent years. This introduces previously unknown issues, such as how unpredictable output may be and the fact that it is not continuous, necessitating extra preparation for network planning. This study presents a stochastic methodology to enable the network to consider investments in new lines and any energy storage systems it sees fit. Sixteen alternative situational scenarios are produced by segmenting the study into seasonal phases, which are then broken into four circumstances (morning, peak, afternoon, and night) for each of the four seasons. However, these are divided into hourly scenarios (totaling 8760), with different states for generation, load, storage, and electric vehicles. The model is evaluated on a 180bus network in Portugal that includes distributed generation, a substation, and a number of the distribution operator's biomass generators in addition to the distributed generation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Cascading Artificial Neural Networks for Enhanced Distribution Network State Estimation

A Novel Cascading Artificial Neural Networks for Enhanced Di...

引用

Mediterranean Electrotechnical Conference (MELECON)

作者： Mohamad El Iaali Reza Razi Antoine Bruyere Bruno Francois Joao Soares Centrale Lille Junia ULR 2697 - L2EP Univ. Lille Arts et Metiers Institute of Technology Lille France GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development LASI - Intelligent Systems Associate Laboratory Polytechnic of Porto Porto Portugal

ISBN: (数字)9798350387025

ISBN: (纸本)9798350387032

The growing integration of renewable energy sources and the widespread adoption of electric vehicles add complexity to power flows in distribution systems. Understanding the system dynamics and implementing control actions are imperative for effective grid management. While measurements in specific nodes are facilitated by smart meters, accurate sensors, communication networks, and electric vehicles, it is costly and, in some cases, impossible to obtain measurements at all nodes. In response to these challeng.s, this paper introduces a machine learning-based state estimation method, utilizing available measurements and estimating others. By harnessing data-driven techniques, the proposed method aims to provide accurate estimations of voltages and currents in distribution networks, offering valuable insights into flexibilities management and control processes. Specific case study is considered, confirming the efficiency of the suggested state estimation approach and providing insights into its flexibility across a range of scenarios. In addition to the mentioned benefits, the results validate the proposed method, demonstrating a small margin of error. This approach holds significant promises in improving situational awareness for power system operators and enhancing their understanding of the evolving grid dynamics.

关键词： Accuracy System dynamics Current measurement Power system dynamics Distribution networks Electric vehicles Smart meters

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：