检索结果-内蒙古大学图书馆

Clemson University Power Systems Conference (PSC)

作者： Fábio Pereira João Soares Pedro Faria Zita Vale GECAD — Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development IPP-Polytechnic Institute of Porto Porto Portugal

In the present context the distribution networks are characterized by the increasing penetration of Distributed Generation (DG) resources, which imposes important changes in operation practice. Moreover, the concept of Demand Response (DR) is currently a very important resource. The present paper proposes a methodology that makes possible the allocation of fixed costs in distribution networks considering the integration of DG and DR resources. It considers several possibilities for consumers DR remuneration. The fixed cost allocation is determined in three phases - DC Optimal Power Flow (DC-OPF), Kirschen's tracing method, and MW-mile method. The presented case study contemplates a distribution network with 49 buses, 47 DG units, 4 external suppliers and 50 consumers.

关键词： Remuneration Resource management Density estimation robust algorithm Load flow Indexes Distributed power generation Optimal scheduling

来源：评论

学校读者我要写书评

暂无评论

Risk assessment model based on centrifugal governors and artificial neural networks

Risk assessment model based on centrifugal governors and art...

引用

Artificial Intelligence (CAI), IEEE Conference on

作者： Francisco Oliveira Fernando Lezama Luis Gomes 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 Portugal

In today’s industry, old machines, that were not manufactured according to Industry 4.0 standards, may not be equipped with sophisticated sensors for monitoring critical values and ensuring the machine's proper health and operation. As a result, third-party sensors, such as thermometers and vibration sensors, are often integrated into these machines. Unfortunately, despite being able to obtain effective measurements, such sensors lack relativization of these values to the contextual values of each machine. This paper proposes a risk assessment model that digitally mimics a real-life centrifugal governor's operation. The system combines machine learning and data analysis and uses a context-aware algorithm that can work with single or multiple sensors to output aggregated information on a machine’s health.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analyzing Electric Vehicle Charging Behaviour Using advanced Clustering Tools 20th

Analyzing Electric Vehicle Charging Behaviour Using Advanced...

引用

20th International Symposium on Distributed computing and Artificial Intelligence, DCAI 2023

作者： da Veiga, Carlos Ernani Ramos, Carlos Corchado, Juan Manuel Fernandes, Piara Soares, João DAE - Academic Department of Electrotechnics IFSC - Federal Institute of Santa Catarina Florianopolis Brazil GECAD - Research Group On Intelligent Engineering and Computing for Advanced Innovation and Development LASI - Intelligent Systems Associate Laboratory Polytechnic of Port Porto Portugal BISITE Research Group University of Salamanca Edificio I+D+I Salamanca37008 Spain

ISBN: (纸本)9783031383175

Electric vehicle (EV) owners often have electric vehicle charging stations (EVCS) in their homes and leave the EV connected when it remains in the garage. This procedure does not guarantee that EV charging is adequate, and monitoring this period is necessary to identify anomalies. A study was developed where the EV charging curves was analyzed by clustering with K-means. The advantage presented in this work is that the necessary data for the charging analysis come from the EVCS power supply circuit. This proposal allows monitoring and rapidly classifying the data according to the form of the EV charging curves, with no need for the supervision of the input data. The unsupervised machine learning method can classify any situation by collecting data on the electrical power supplied to the EVCS. In this study, the classification was applied with learning performed in the history, identifying the clusters representing abnormal situations to identify anomalies in future charging curves. The results of the proposed approach presented around 27.8% as an anomaly in the EV charging, allowing to identify the moment in which it occurs and to make the necessary adjustments to avoid them. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Intensive summer course in robotics – Robotcraft

引用

Applied computing and Informatics 2018年第1-2期16卷 155-179页

作者： Ferreira, N.M. Fonseca Araujo, André Couceiro, M.S. Portugal, David Department of Electrical Engineering (DEE) Engineering Institute of Coimbra (ISEC) Polytechnic of Coimbra (IPC) Rua Pedro Nunes – Quinta da Nora Coimbra Portugal GECAD - Knowledge Research Group on Intelligent Engineering and Computing for Advanced Innovation Development of the Engineering Institute of Porto (ISEP) Polytechnic Institute of Porto (IPP) Porto Portugal INESC TEC – Institute for Systems and Computer Engineering Technology and Science Porto Portugal Ingeniarius Lda Coimbra Portugal

This paper describes a two-month summer intensive course designed to introduce participants with a hands-on technical craft on robotics and to acquire experience in the low-level details of embedded systems. Attendants started this course with a brief introduction to robotics;learned to draw, design and create a personalized 3D structure for their mobile robotic platform and developed skills in embedded systems. They were familiarize with the practices used in robotics, learning to connect all sensors and actuator, developing a typical application on differential kinematic using Arduino, exploring ROS features under Raspberry Pi environment and Arduino – Raspberry Pi communication. Different paradigms and some real applications and programming were addressed on the topic of Artificial Intelligence. Throughout the course, participants were introduced to programming languages (including Python and C++), advanced programming concepts such as ROS, basic API development, system concepts such as I2C and UART serial interfaces, PWM motor control and sensor fusion to improve robotic navigation and localization. This paper describes not just the concept, layout and methodology used on RobotCraft 2017 but also presents the participants knowledge background and their overall opinions, leading to focus on lessons learned and suggestions for future editions. © 2018, N.M. Fonseca Ferreira, André Araujo, M.S. Couceiro and David Portugal.

关键词： International trends in educational robotics Project-based learning ROS

来源：评论

学校读者我要写书评

暂无评论

Clustering Optimization of Distributed Energy Resources in Support of an Aggregator

Clustering Optimization of Distributed Energy Resources in S...

引用

IEEE Symposium Series on Computational Intelligence

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

Power systems have witnessed a gradual increase of the relevance and number of energy aggregators. Moreover, with the large-scale installation of distributed energy resources, energy aggregators integrate several features that can improve power system's operation. The present paper addresses this topic through a clustering optimization for the aggregator's scheduling. The costs of aggregated distributed energy resources are minimized through a group tariff, i.e. the same tariff is applied to all within a group. Given the context of aggregators participating in energy markets and the requirements that it involves, often compose issues for the aggregator that may prevent it from participating. The proposed algorithm guarantees the amount of energy and number of resources by group needed, by using metaheuristics combined with k-means clustering. The algorithm is tested in a day-ahead case study composed of 20,310 consumers, 548 distributed generators, and 10 retailers, of which, the obtained results show an improvement in the energy costs of the aggregator.

关键词： Aggregator Demand response Distributed generation Metaheuristics Clustering

来源：评论

学校读者我要写书评

暂无评论

Enhance Demand Response Participants Performance Using a Personalized Recommendation Method

Enhance Demand Response Participants Performance Using a Per...

引用

International Conference on Environment and Electrical engineering (EEEIC)

作者： Cátia Silva Pedro Faria Zita Vale Intelligent Systems Associated Laboratory (LASI) Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development (GECAD) Polytechnic of Porto Porto Portugal

For a successful implementation of Demand Response (DR) in the real markets, the uncertainty from the players' response must be reduced. From the community manager's perspective, the proposed methodology focuses on selecting trustworthy participants according to their availability for the triggered DR event. As innovation from previous works, the authors focus now on the consumer perspective. The present paper introduces a tool developed for performance enhancement by displaying the expected rewards according to consumer participation. In other words, the tool performs a sensitivity analysis to study all the possibilities and achieve the player's goal. For example, the tool might suggest the optimal one according to the frequency and type of DR programs triggered, but the participation is voluntary and depends on player availability. The case study results discuss the perspective of four players with distinct objectives.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysing the Impact of Local Electricity Transactions with EV Penetration on the Electrical Grid

Analysing the Impact of Local Electricity Transactions with ...

引用

International Conference on European Electricity Market, EEM

作者： Fernando Lezama Ricardo Faia Pedro Faria Zita Vale GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development LASI – Intelligent Systems Associate Laboratory Polytechnic of Porto Porto Portugal

This article analysis, through simulation, the impact that local transactions and the penetration of EVs have on the distribution network and the costs and incomes of local market participants. An auction-based competitive market and mathematical model are provided to simulate end-user transactions with EVs on the low-voltage grid. The proposed framework is validated in a scenario considering 55 end-users (some with PV generation and EVs) and six combined heat and power generators trading energy in the IEEE European Low Voltage Test Feeder system. Furthermore, a distribution system operator is considered by defining network constraints (voltage limits and lines overloading) that ensure the correct operation of the distribution grid.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Production and Maintenance Scheduling for Total Cost and Machine Longevity Optimization

Production and Maintenance Scheduling for Total Cost and Mac...

引用

Future Energy Solutions (FES), International Conference on

作者： Bruno Mota Pedro Faria Bruno Canizes Carlos Ramos LASI - Intelligent Systems Associate Laboratory Polytechnic of Porto GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development Porto Portugal

Production and maintenance scheduling for total cost-effective and machine longevity manufacturing is a key aspect in dealing with the ever-increasing energy prices, competitiveness, added maintenance costs, and environmental pressures that the manufacturing sector faces nowadays. This paper addresses these issues by proposing a novel intelligent production scheduling system for joint optimization of production and maintenance for overall cost minimization and machine longevity improvement. To achieve this, it is proposed a Genetic Algorithm (GA) for production and maintenance scheduling of flexible job shop manufacturing environments. The proposed GA takes into account volatile market energy prices, Renewable Energy Resources (RERs), surplus energy selling, maintenance activities, and constraints imposed on the production plan. A case study from the literature is used as a baseline scenario to validate the proposed scheduler. It uses real-production data and considers three unique machines with 275 tasks to be scheduled among them. Using the baseline scenario, it was possible to demonstrate the robustness of the proposed scheduler in reducing total costs, by taking advantage of the volatility of energy prices, as well as utilizing RERs to cover energy expenses or for selling excess energy. Furthermore, it highlights the ability to reduce the overload of single machines. Accordingly, it was possible to achieve cost reductions of up to 11.0% and improvements of 24.4% in machine longevity when compared to the baseline scenario.

关键词：

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

Optimizing House Energy Management with MILP Considering Shifting of Electric Appliances and Battery Storage System

Optimizing House Energy Management with MILP Considering Shi...

引用

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

作者： Ricardo Faia Pedro Faria Zita Vale GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development LASI - Intelligent Systems Associate Laboratory Polytechnic of Porto Porto Portugal

The integration of renewable energy sources into the power grid has led to the need for efficient energy management systems that consider the presence of energy storage systems and controllable loads. In this paper, the authors propose a mixed-integer linear programming optimization model for energy management that takes into account the operation of shift electric appliances and battery storage systems. The proposed model aims to minimize the overall electricity cost while ensuring that the energy demand of the system is met, the battery state of charge is maintained within safe operating limits, and the shift electric appliance met with the user requirements. The authors consider the operational constraints of shifting electric appliances, which can be scheduled to operate during periods of low electricity prices. Additionally, they account for the energy storage system, which can be charged during periods of excess renewable energy production and discharged during periods of high demand. Four different scenarios are tested to prove the value of the model.

关键词：

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：