Hybrid Advanced Techniques for Forecasting in Energy Sector

Accurate forecasting performance in the energy sector is a primary factor in the modern restructured power market, accomplished by any novel advanced hybrid techniques. Particularly in the Big Data era, forecasting models are always based on a complex function combination, and energy data are always...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Wei-Chiang Hong (Ed.)
التنسيق: Online
اللغة:الإنجليزية
منشور في: MDPI - Multidisciplinary Digital Publishing Institute 2021
الموضوعات:
الوصول للمادة أونلاين:29149
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1869515802246381568
author Wei-Chiang Hong (Ed.)
author_browse Wei-Chiang Hong (Ed.)
author_facet Wei-Chiang Hong (Ed.)
author_sort Wei-Chiang Hong (Ed.)
collection Directory of Open Access Books
description Accurate forecasting performance in the energy sector is a primary factor in the modern restructured power market, accomplished by any novel advanced hybrid techniques. Particularly in the Big Data era, forecasting models are always based on a complex function combination, and energy data are always complicated by factors such as seasonality, cyclicity, fluctuation, dynamic nonlinearity, and so on. To comprehensively address this issue, it is insufficient to concentrate only on simply hybridizing evolutionary algorithms with each other, or on hybridizing evolutionary algorithms with chaotic mapping, quantum computing, recurrent and seasonal mechanisms, and fuzzy inference theory in order to determine suitable parameters for an existing model. It is necessary to also consider hybridizing or combining two or more existing models (e.g., neuro-fuzzy model, BPNN-fuzzy model, seasonal support vector regression–chaotic quantum particle swarm optimization (SSVR-CQPSO), etc.). These advanced novel hybrid techniques can provide more satisfactory energy forecasting performances. This book aimed to attract researchers with an interest in the research areas described above. Specifically, we were interested in contributions towards recent developments, i.e., hybridizing or combining any advanced techniques in energy forecasting, with the superior capabilities over the traditional forecasting approaches, with the ability to overcome some embedded drawbacks, and with the very superiority to achieve significant improved forecasting accuracy.
format Online
id doab-20.500.12854ir-49698
institution Directory of Open Access Books
language eng
publishDate 2021
publishDateRange 2021
publishDateSort 2021
publisher MDPI - Multidisciplinary Digital Publishing Institute
publisherStr MDPI - Multidisciplinary Digital Publishing Institute
record_format ojs
spelling doab-20.500.12854ir-496982024-04-14T10:28:02Z Hybrid Advanced Techniques for Forecasting in Energy Sector Wei-Chiang Hong (Ed.) QA75.5-76.95 TA1-2040 hybrid models autoregressive moving average with exogenous variable (ARMAX) energy forecasting fuzzy group quantile forecasting evolutionary algorithms quantum computing mechanism cluster validity support vector regression / support vector machines artificial neural networks principal component analysis bayesian inference thema EDItEUR::U Computing and Information Technology::UY Computer science Accurate forecasting performance in the energy sector is a primary factor in the modern restructured power market, accomplished by any novel advanced hybrid techniques. Particularly in the Big Data era, forecasting models are always based on a complex function combination, and energy data are always complicated by factors such as seasonality, cyclicity, fluctuation, dynamic nonlinearity, and so on. To comprehensively address this issue, it is insufficient to concentrate only on simply hybridizing evolutionary algorithms with each other, or on hybridizing evolutionary algorithms with chaotic mapping, quantum computing, recurrent and seasonal mechanisms, and fuzzy inference theory in order to determine suitable parameters for an existing model. It is necessary to also consider hybridizing or combining two or more existing models (e.g., neuro-fuzzy model, BPNN-fuzzy model, seasonal support vector regression–chaotic quantum particle swarm optimization (SSVR-CQPSO), etc.). These advanced novel hybrid techniques can provide more satisfactory energy forecasting performances. This book aimed to attract researchers with an interest in the research areas described above. Specifically, we were interested in contributions towards recent developments, i.e., hybridizing or combining any advanced techniques in energy forecasting, with the superior capabilities over the traditional forecasting approaches, with the ability to overcome some embedded drawbacks, and with the very superiority to achieve significant improved forecasting accuracy. 2021-02-11T15:40:30Z 2021-02-11T15:40:30Z 2018-10-19 10:39:42 2018 book 29149 9783038972914 9783038972907 https://directory.doabooks.org/handle/20.500.12854/49698 eng image/jpeg Attribution-NonCommercial-NoDerivatives 4.0 International https://play.google.com/books/publish/a/14935057684283403269#details/ISBN:9783038972907 https://www.mdpi.com/books/pdfview/book/841 https://www.mdpi.com/books/pdfview/book/841 MDPI - Multidisciplinary Digital Publishing Institute 10.3390/books978-3-03897-291-4 10.3390/books978-3-03897-291-4 46cabcaa-dd94-4bfe-87b4-55023c1b36d0 9783038972914 9783038972907 250 open access
spellingShingle QA75.5-76.95
TA1-2040
hybrid models
autoregressive moving average with exogenous variable (ARMAX)
energy forecasting
fuzzy group
quantile forecasting
evolutionary algorithms
quantum computing mechanism
cluster validity
support vector regression / support vector machines
artificial neural networks
principal component analysis
bayesian inference
thema EDItEUR::U Computing and Information Technology::UY Computer science
Wei-Chiang Hong (Ed.)
Hybrid Advanced Techniques for Forecasting in Energy Sector
title Hybrid Advanced Techniques for Forecasting in Energy Sector
title_full Hybrid Advanced Techniques for Forecasting in Energy Sector
title_fullStr Hybrid Advanced Techniques for Forecasting in Energy Sector
title_full_unstemmed Hybrid Advanced Techniques for Forecasting in Energy Sector
title_short Hybrid Advanced Techniques for Forecasting in Energy Sector
title_sort hybrid advanced techniques for forecasting in energy sector
topic QA75.5-76.95
TA1-2040
hybrid models
autoregressive moving average with exogenous variable (ARMAX)
energy forecasting
fuzzy group
quantile forecasting
evolutionary algorithms
quantum computing mechanism
cluster validity
support vector regression / support vector machines
artificial neural networks
principal component analysis
bayesian inference
thema EDItEUR::U Computing and Information Technology::UY Computer science
topic_facet QA75.5-76.95
TA1-2040
hybrid models
autoregressive moving average with exogenous variable (ARMAX)
energy forecasting
fuzzy group
quantile forecasting
evolutionary algorithms
quantum computing mechanism
cluster validity
support vector regression / support vector machines
artificial neural networks
principal component analysis
bayesian inference
thema EDItEUR::U Computing and Information Technology::UY Computer science
url 29149
work_keys_str_mv AT weichianghonged hybridadvancedtechniquesforforecastinginenergysector