检索结果-内蒙古大学图书馆

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

Short-term electricity demand forecasting via variational autoencoders and batch training-based bidirectional long short-term memory

引用

SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS 2022年第PartC期52卷

作者： Moradzadeh, Arash Moayyed, Hamed Zare, Kazem Mohammadi-Ivatloo, Behnam [a]Faculty of Electrical and Computer Engineering University of Tabriz *** Tabriz Iran [b]GECAD-Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development Polytechnic of Porto (P. PORTO) P-4200-072 Porto Portugal [c]Information Technologies Application and Research Center İstanbul Ticaret University Istanbul Turkey

Electricity load forecasting is a key aspect for power producers to maximize their economic efficiency in deregulated markets. So far, many solutions have been employed to forecast the consumption load in power grids. However, most of these methods have suffered in modeling the time-series state of data and removing noise from real-world data. Thus, the forecasting results in most cases did not have acceptable accuracy due to the mentioned problems. In this paper, in order to short-term electricity load forecast in Tabriz, Iran, a hybrid technique based on deep learning applications called Variational Autoencoder Bidirectional Long Short-Term Memory (VAEBiLSTM) is presented. Pre-processing, noise cancellation, and time-series state modeling of the data are prominent features of the developed load forecasting model. In addition, in order to prevent overfitting problems in the process of training large amounts of data, the training process is developed in the form of batch training. Load forecasting is done using meteorological and environmental data of Tabriz city as well as historical information and days of the week as input variables. In the hybrid method structure, the Variational Autoencoders are applied to the data for data preprocessing and reconstruction. Then, the normalized, noise-free data is utilized as a dataset for training the Bidirectional Long Short-Term Memory (BiLSTM) network. The proposed training method for BiLSTM is based on batch training. To present the effectiveness of the proposed technique in a comparative approach, the conventional LSTM and Support Vector Regression (SVR) algorithms are also applied to the data. Each network is trained with input data related to the years of 2017 and 2018 to predict the electricity load of the Tabriz city separately for each of the four seasons of the 2019 year. The forecasting results obtained from each method are evaluated by different statistical performance indicators. It can be seen that the proposed

关键词： Electricity demand Load forecasting Deep learning Variational Autoencoders (VAE) Bidirectional long short-term memory (BiLSTM)

来源：评论

学校读者我要写书评

暂无评论

Reduction of the Market Splitting Occurrences: A Dynamic Line Rating Approach for the 2030 Iberian Day-ahead Market Scenarios

Reduction of the Market Splitting Occurrences: A Dynamic Lin...

引用

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

Feature Selection on Epistatic Problems Using Genetic Algorithms with Nested Classifiers 26th

Feature Selection on Epistatic Problems Using Genetic Algor...

引用

26th International Conference on Applications of Evolutionary Computation, EvoApplications 2023, held as part of EvoStar 2023

作者： Carvalho, Pedro Ribeiro, Bruno Rodrigues, Nuno M. Batista, João E. Vanneschi, Leonardo Silva, Sara University of Coimbra Centre for Informatics and Systems of the University of Coimbra Department of Informatics Engineering Coimbra Portugal GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development LASI - Intelligent Systems Associate LAboratory Polytechnic of Porto Rua Dr. António Bernardino de Almeida 431 Porto4249-015 Portugal LASIGE Department of Informatics Faculty of Sciences University of Lisbon Lisbon Portugal Universidade Nova de Lisboa Campus de Campolide Lisboa1070-312 Portugal

ISBN: (纸本)9783031302282

Feature selection is becoming an essential part of machine learning pipelines, including the ones generated by recent AutoML tools. In case of datasets with epistatic interactions between the features, like many datasets from the bioinformatics domain, feature selection may even become crucial. A recent method called SLUG has outperformed the state-of-the-art algorithms for feature selection on a large set of epistatic noisy datasets. SLUG uses genetic programming (GP) as a classifier (learner), nested inside a genetic algorithm (GA) that performs feature selection (wrapper). In this work, we pair GA with different learners, in an attempt to match the results of SLUG with less computational effort. We also propose a new feedback mechanism between the learner and the wrapper to improve the convergence towards the key features. Although we do not match the results of SLUG, we demonstrate the positive effect of the feedback mechanism, motivating additional research in this area to further improve SLUG and other existing feature selection methods. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

AIRDOC: Smart mobile application for individualized support and monitoring of respiratory function and sounds of patients with chronic obstructive disease 12

AIRDOC: Smart mobile application for individualized support ...

引用

12th IADIS International Conference e-Health 2020, EH 2020, Part of the 14th Multi Conference on Computer Science and Information Systems, MCCSIS 2020

作者： Almeida, Rute Jácome, Cristina Martinho, Diogo Vieira-Marques, Pedro Jacinto, Tiago Ferreira, Ana Almeida, Ana Martins, Constantino Pereira, Mariana Pereira, Ana Valente, José Almeida, Rafael Vieira, Ana Amaral, Rita Sá-Sousa, Ana Gonçalves, Ivânia Rodrigues, Pedro Alves-Correia, Magna Freitas, Alberto Marreiros, Goreti Fonseca, Susana Caldas Pereira, Altamiro Costa Fonseca, João Almeida CINTESIS Center for Health Technology and Services Research Faculty of Medicine University of Porto Porto Portugal MEDCIDS Department of Community Medicine Health Information and Decision Faculty of Medicine University of Porto Porto Portugal GECAD Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development Institute of Engineering Polytechnic of Porto Portugal MEDIDA Serviços em Medicina EDucação Investigação Desenvolvimento e Avaliação LDA Porto Portugal Porto Health School Polytechnic Institute of Porto Porto Portugal

ISBN: (纸本)9789898704184

Current tools for self-management of chronic obstructive respiratory diseases (CORD) are difficult to use, not individualized and requiring laborious analysis by health professionals, discouraging their use in healthcare. There is an opportunity for cost-effective and easy-to-disseminate advanced technological solutions directed to patients and attractive to different stakeholders. The strategy of AIRDOC is to develop and integrate self-monitoring and self-managing tools, making use of the smartphone's presence in everyday life. AIRDOC intends to innovate on: i) technologies for remote monitoring of respiratory function and computerized lung auscultation;ii) coaching solutions, integrating psychoeducation, gamification and disease management support systems;and iii) management of personal health data, focusing on security, privacy and interoperability. It is expected that AIRDOC results will contribute for the innovation in CORD healthcare, with increased patient involvement and empowerment while providing quality prospective information for better clinical decisions, allowing more efficient and sustainable healthcare delivery. © Proceedings of the 12th IADIS International Conference e-Health 2020, EH 2020 - Part of the 14th Multi Conference on Computer Science and Information Systems, MCCSIS 2020. All rights reserved.

关键词： mHealth

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 challenges 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

Lighting consumption optimization using fish school search algorithm

Lighting consumption optimization using fish school search a...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Pedro Faria Ângelo Pinto Zita Vale Mahsa Khorram Fernando B. de Lima Neto Tiago Pinto GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development ISEP/IPP - Polytechnic of Porto Porto Portugal Polytechnic School of Engineering University of Pernambuco Recife Brazil BISITE Research Centre University of Salamanca (USAL) Salamanca Calle Espejo 12 Spain

Electricity consumption has increased all around the world in the last decades. This has caused a rise in the use of fossil fuels and in the harming of the environment. In the past years the use of renewable energies and reduction of consumption has growth in order to deal with that problem. The change in the production paradigm led to an increasing search of ways to shorten consumption and adapt to the production. One of the solutions for this problem is to use Demand Response systems. Lighting systems have a major role in electricity consumption, so they are very suitable to be applied in a Demand Response system, optimizing their use. This optimization can be made in different ways being one of them by using a heuristic algorithm. This paper focuses on the use of Fish School Search algorithm to optimize a lighting system, in order to understand its capability of dealing with a problem of this nature and compare it with other algorithms to evaluate its performance.

关键词： Fish Frequency selective surfaces Optimization Lighting Linear programming Production Load management

来源：评论

学校读者我要写书评

暂无评论

A Residential Energy Management System with Offline Population-Based Optimization

A Residential Energy Management System with Offline Populati...

引用

IEEE Symposium Series on Computational Intelligence

作者： Joao Soares Fernando Lezama Sergio Ramos Zita Vale Andre Lopes GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development Polytechnic of Porto Porto Portugal

Expectable improvements in battery technology and lower prices will certainly contribute to increase the interest in residential energy storage systems in the near future. The installment of photovoltaic panels and the use of energy storage systems will help to reduce power losses in distribution and transmission power grid and increase network availability, and consequently, to reduce the dependency on the use of fossil fuels. The paper presents a light implementation of residential energy management system that integrates photovoltaic generation, an energy storage system and an electric vehicle. The goal of the system is to reduce the costs of electric consumer energy bill. The effectiveness of the system is verified through its application in several scenarios for the Portuguese context. An offline population-based algorithm, namely differential evolution method is used to adjust the objective function for the online control of the energy devices in the residential house.

关键词： Differential evolution Energy management system Energy costs Energy storage Electric vehicle Photovoltaic

来源：评论

学校读者我要写书评

暂无评论

Day-ahead stochastic scheduling model considering market transactions in smart grids

Day-ahead stochastic scheduling model considering market tra...

引用

Power Systems Computation Conference

作者： Joao Soares Fernando Lezama Bruno Canizes M. Ali Fotouhi Ghazvini Zita Vale Tiago Pinto GECAD-Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development Polytechnic of Porto (ISEP/I PP)

The integration of renewable generation and electric vehicles (EVs) into smart grids poses an additional challenge to the stochastic energy resource management problem due to the uncertainty related to weather forecast and EVs user-behavior. Moreover, when electricity markets are considered, market price variations cannot be disregarded. In this paper, a two-stage stochastic programming approach to schedule the day-ahead operation of energy resources in smart grids under uncertainty is presented. A realistic case study is performed using a large-scale scenario with nearly 4 million variables with the goal to minimize expected operation cost of energy aggregators. Three scenarios are analyzed to understand the effect of market transactions and external suppliers on the aggregator model. The results suggest that the market transactions can reduce expected cost, while the external supplier offers risk-free price. In addition, the performance metric shows the superiority of the stochastic approach over an equivalent deterministic model.

关键词： Energy scheduling Smart grid Uncertainty Electric vehicles Two-stage stochastic programming

来源：评论

学校读者我要写书评

暂无评论

Model for the Integration of Distributed Energy Resources in Energy Markets by an Aggregator

Model for the Integration of Distributed Energy Resources in...

引用

IEEE Manchester PowerTech Conference

作者： Joao Spinola Pedro Faria Zita Vale GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development Institute of Engineering - Polytechnic of Porto (ISEP/IPP)

ISBN: (纸本)9781509042388

The increase of distributed energy resources in energy systems and current legislation concerning the participation in energy markets, is causing a high wasted potential of energy supply and flexibility services. In this paper, it is proposed a methodology for the management and integration of distributed energy resources in energy systems and markets, through the application of an aggregator. Also, the aggregator provides demand response programs based on tariffs, thus enabling different types of participations. Aggregation is performed using K-Means clustering algorithm, and serves as basis for remuneration, where the aggregated energy and cost of resources is obtained. Given this methodology, the aggregator obtains the energy available and the minimum sell cost to negotiate in market, with the intent of obtaining profit in its operation. The methodology is validated through a case study, with 20 consumers and 25 distributed generators.

关键词： Aggregator Clustering Demand response Distributed generation Energy markets

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：