Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top

2015 | Book

Imitative Learning for Online Planning in Microgrids Read chapter Read first chapter

Data Analytics for Renewable Energy Integration

Third ECML PKDD Workshop, DARE 2015, Porto, Portugal, September 11, 2015. Revised Selected Papers

Editors: Wei Lee Woon, Zeyar Aung, Stuart Madnick

Publisher: Springer International Publishing

Book Series : Lecture Notes in Computer Science

Part of: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Login to get access
insite
SEARCH

About this book

This book constitutes revised selected papers from the third ECML PKDD Workshop on Data Analytics for Renewable Energy Integration, DARE 2015, held in Porto, Portugal, in September 2015.
The 10 papers presented in this volume were carefully reviewed and selected for inclusion in this book.

Table of Contents

Frontmatter
Imitative Learning for Online Planning in Microgrids
Abstract
This paper aims to design an algorithm dedicated to operational planning for microgrids in the challenging case where the scenarios of production and consumption are not known in advance. Using expert knowledge obtained from solving a family of linear programs, we build a learning set for training a decision-making agent. The empirical performances in terms of Levelized Energy Cost (LEC) of the obtained agent are compared to the expert performances obtained in the case where the scenarios are known in advance. Preliminary results are promising.
Samy Aittahar, Vincent François-Lavet, Stefan Lodeweyckx, Damien Ernst, Raphael Fonteneau
A Novel Central Voltage-Control Strategy for Smart LV Distribution Networks
Abstract
With the inclusion of Information and Communication Technology (ICT) components into the low-voltage (LV) distribution grid, some measurement data from smart meters are available for the control of the distribution networks with high penetration of photovoltaic (PV). This paper undertakes a central voltage-control strategy for smart LV distribution networks, by using a novel optimal power flow (OPF) methodology in combination with the information collected from smart meters for the power flow calculation. The proposed strategy can simultaneously mitigate the PV reactive power fluctuations, as well as minimize the voltage rise and power losses. The results are very promising, as voltage control is achieved fast and accurately, the reactive power is smoothed in reference to the typical optimization techniques and the local control strategies as validated with a real-time simulator.
Efrain Bernal Alzate, Qiang Li, Jian Xie
Quantifying Energy Demand in Mountainous Areas
Abstract
Despite their rich energy renewable potential, mountainous areas suffer from energy poverty. A viable solution seems to be the radical turn towards renewable resources. Any tailor-cut energy planning for mountainous areas presupposes the adequate estimation of the energy demand of buildings, which in this case is hindered by the lack of long-term meteorological data, especially in remote, high altitude areas. In this paper four case studies, namely Switzerland, Austria, Greece and north Italy, are examined, applying the method of degree-days. The scarcity of meteorological stations at higher altitudes has been overcome by calculating the lapse rates (decrease of surface temperature with altitude) for each case, which were found to vary from the common “rule” of 6.5°C/km. Based on these findings, the air temperatures of all remote, mountainous spots can be calculated, and, therefore, the estimation of the energy needs of buildings has been provided, with a high level of accuracy.
Lefkothea Papada, Dimitris Kaliampakos
Performance Analysis of Data Mining Techniques for Improving the Accuracy of Wind Power Forecast Combination
Abstract
Efficient integration of renewable energy sources into the electricity grid has become one of the challenging problems in recent years. This issue is more critical especially for unstable energy sources such as wind. The focus of this work is the performance analysis of several alternative wind forecast combination models in comparison to the current forecast combination module of the wind power monitoring and forecast system of Turkey, developed within the course of the RITM project. These accuracy improvement studies are within the scope of data mining approaches, Association Rule Mining (ARM), Distance-based approach, Decision Trees and k-Nearest Neighbor (k-NN) classification algorithms and comparative results of the algorithms are presented.
Ceyda Er Koksoy, Mehmet Baris Ozkan, Dilek Küçük, Abdullah Bestil, Sena Sonmez, Serkan Buhan, Turan Demirci, Pinar Karagoz, Aysenur Birturk
Evaluation of Forecasting Methods for Very Small-Scale Networks
Abstract
Increased levels of electrification of home appliances, heating and transportation are bringing new challenges for the smart grid, as energy supply sources need to be managed more efficiently. In order to minimize production costs, reduce the impact on the environment, and optimize electricity pricing, producers need to be able to accurately estimate their customers’ demand. As a result, forecasting electricity usage plays an important role in smart grids since it enables matching supply with demand, and thus minimize energy waste. Forecasting is becoming increasingly important in very small-scale power networks, also known as microgrids, as these systems should be able to operate autonomously, in islanded mode. The aim of this paper is to evaluate the efficiency of several forecasting methods in such very small networks. We evaluate artificial neural networks (ANN), wavelet neural networks (WNN), auto-regressive moving-average (ARMA), multi-regression (MR) and auto-regressive multi-regression (ARMR) on an aggregate of 30 houses, which emulates the demand of a rural isolated microgrid. Finally, we empirically show that for this problem ANN is the most efficient technique for predicting the following day’s demand.
Jean Cavallo, Andrei Marinescu, Ivana Dusparic, Siobhán Clarke
Classification Cascades of Overlapping Feature Ensembles for Energy Time Series Data
Abstract
The classification of high-dimensional time series data can be a challenging task due to the curse-of-dimensionality problem. The classification of time series is relevant in various applications, e.g., in the task of learning meta-models of feasible schedules for flexible components in the energy domain. In this paper, we introduce a classification approach that employs a cascade of classifiers based on features of overlapping time series steps. To evaluate the feasibility of the whole time series, each overlapping pattern is evaluated and the results are aggregated. We apply the approach to the problem of combined heat and power plant operation schedules and an artificial similarly structured data set. We identify conditions under which the cascade approach shows better results than a classic One-Class-SVM.
Judith Neugebauer, Oliver Kramer, Michael Sonnenschein
Correlation Analysis for Determining the Potential of Home Energy Management Systems in Germany
Abstract
This paper describes the implementation of a model in MATLAB that estimates the potential of home energy management systems based on different component criteria. This is done by the estimation, in a given territory, of the correlation of favorable elements for the installation of integrated systems for energy generation and electromobility. The model is applied to the territories of Germany, evaluating its potential for home energy management systems in current and future situations.
Aline Kirsten Vidal de Oliveira, Christian Kandler
Predicting Hourly Energy Consumption. Can Regression Modeling Improve on an Autoregressive Baseline?
Abstract
According to the Third Industrial Revolution, peer-to-peer electricity exchange combined with optimized local storage is the future of our electricity landscape, creating the so-called “smart grid”. Such a grid not only has to rely on predicting electricity production, but also its consumption. A growing body of literature exists on the topic of energy consumption and demand forecasting. Many contributions consist of presenting a methodology, and showing its accuracy. This paper goes beyond this common practice on two levels: first, by comparing two regression techniques to a univariate autoregressive baseline and second, by evaluating the models in term of industrial applicability, in close collaboration with domain experts. It appears that the computationally costly regression models fail to significantly beat the baseline.
Pierre Dagnely, Tom Ruette, Tom Tourwé, Elena Tsiporkova, Clara Verhelst
An OPTICS Clustering-Based Anomalous Data Filtering Algorithm for Condition Monitoring of Power Equipment
Abstract
In allusion to the widespread anomalous data in substation primary equipment condition monitoring, this paper proposes an OPTICS (Ordering Points To Identify the Clustering Structure) clustering-based condition monitoring anomalous data filtering algorithm. Through the characteristic analysis of historical primary equipment condition monitoring data, an anomalous data filtering mechanism was built based on density clustering. The effectiveness of detecting anomalous data was verified through the experiments on one 110 kV substation equipment transformer oil chromatography and the GIS (Gas Insulated Substation) SF6 density micro water. Compared with traditional anomalous data detection algorithms, the OPTICS Clustering-based algorithm has shown significant performance in identifying the features of anomalous data as well as filtering condition monitoring anomalous data. Noises were reduced effectively and the overall reliability of condition monitoring data was also improved.
Qiang Zhang, Xuwen Wang, Xiaojie Wang
Argument Visualization and Narrative Approaches for Collaborative Spatial Decision Making and Knowledge Construction: A Case Study for an Offshore Wind Farm Project
Abstract
A Geographic Information Systems (GIS) play a vital role in various applications associated with sustainable development and clean energy. In these applications, the GIS provides a capability to upload on-site geographical information collected by public into online maps. One of the major problems is how to make a decision for those reports. In this paper, we study two types of cognitive modes for decision making: argument and narrative reasoning. We investigate how various discussion representations, argumentation theoretical model, and reasoning modes of geo-graphics problems affect knowledge accumulation and argument quality. We conduct empirical tests on different groups of participants regarding their discussions on a particular offshore wind farm project as a case study. We have demonstrated that graph representation provides better results than threaded representation for collaborative work. We also illustrate that the argument theoretical model leads to reduce participants’ performance. Moreover, we conclude that there is no significant difference between narrative representation and graph representation in the participants’ performance to construct knowledge.
Aamna Al-Shehhi, Zeyar Aung, Wei Lee Woon
Backmatter
Metadata
Title
Data Analytics for Renewable Energy Integration
Editors
Wei Lee Woon
Zeyar Aung
Stuart Madnick
Copyright Year
2015
Electronic ISBN
978-3-319-27430-0
Print ISBN
978-3-319-27429-4
DOI
https://doi.org/10.1007/978-3-319-27430-0

Premium Partner

    Image Credits