Highly Accurate Short-term Electric Load Forecasting in Consideration of Equalization of Learning Data

考虑学习数据均衡的高精度短期电力负荷预测

基本信息

  • 批准号:
    16560257
  • 负责人:
  • 金额:
    $ 2.18万
  • 依托单位:
  • 依托单位国家:
    日本
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
  • 财政年份:
    2004
  • 资助国家:
    日本
  • 起止时间:
    2004 至 2005
  • 项目状态:
    已结题

项目摘要

This project deals with the preconditioned intelligent systems and the equalization of learning data. Under competitive and deregulated power systems, short-term load forecasting plays a key role to provide input information with generation scheduling. To compete with other players in power markets, minimizing the maximum error of load forecasting is of main concern. The erroneous results bring about keeping extra power generation reserve in their own company or purchasing more expensive electricity from other companies. As result, power system operators are interested in the reduction of the errors. The preconditioned intelligent system proposed by the author is one of good solutions. By classifying learning data into some clusters, an intelligent system is constructed at each cluster. The method is more effective in terms of model accuracy and computational time. However, it has a drawback that each duster has different performance that comes from underlearning due to the available data. In this study, a method for equalizing the number of learning data is proposed to alleviate underlearning. According to the Kohonen network of artificial neural network, a set of similar data is constructed to reconstruct learning data. In addition, several methods for clustering and the application of the preconditioned intelligent system to fault location in power systems are investigated
本计画主要研究智能系统之预处理与学习资料之均衡化。在竞争激烈的电力系统中,短期负荷预测是为发电计划提供输入信息的关键。为了在电力市场中与其他参与者竞争,最小化负荷预测的最大误差是主要关注的问题。错误的结果导致在自己的公司保留额外的发电储备或从其他公司购买更昂贵的电力。因此,电力系统运营商感兴趣的是减少误差。作者提出的预处理智能系统就是一个很好的解决方案。通过对学习数据进行聚类,在每个聚类上构造一个智能系统。该方法在模型精度和计算时间方面更有效。然而,它有一个缺点,即每个duster具有不同的性能,这是由于可用数据而导致的学习不足。在这项研究中,均衡的学习数据的数量的方法,提出了减轻欠学习。根据人工神经网络的Kohonen网络,构造一组相似数据来重构学习数据。此外,还研究了聚类的几种方法以及预处理智能系统在电力系统故障定位中的应用

项目成果

期刊论文数量(25)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
A Precondition Technique with Reconstruction of Data Similarity Based Classification for Short-term Load Forecasting
一种基于数据相似性重​​构的短期负荷预测分类前置技术
A Hybrid Method of Deterministic Anealing and Fuzzy Inference Neural Network for Electric Power System Fault Detection
电力系统故障检测的确定性退火和模糊推理神经网络混合方法
  • DOI:
  • 发表时间:
    2004
  • 期刊:
  • 影响因子:
    0
  • 作者:
    H.Mori;T.Itagaki
  • 通讯作者:
    T.Itagaki
短期電力負荷予測におけるクラスタ再構成前処理手法
短期电力负荷预测的聚类重构预处理方法
ANNモデルを用いた短期電力負荷予測におけるリスクの定量化
使用 ANN 模型量化短期电力负荷预测的风险
ガウシアンプロセスによる不確定性を表現した短期電力負荷予測
使用高斯过程表达不确定性的短期电力负荷预测
{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

MORI Hiroyuki其他文献

PiXie Analysis for Monitoring Dynamic Protein Interaction and Folding in a Living Cell
用于监测活细胞中动态蛋白质相互作用和折叠的 PiXie 分析
  • DOI:
    10.2142/biophys.61.036
  • 发表时间:
    2021
  • 期刊:
  • 影响因子:
    0
  • 作者:
    MIYAZAKI Ryoji;MORI Hiroyuki;AKIYAMA Yoshinori
  • 通讯作者:
    AKIYAMA Yoshinori

MORI Hiroyuki的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('MORI Hiroyuki', 18)}}的其他基金

Developmental disorder traits and social capital in association with depression/quality of life in elementary and middle school students.
发育障碍特征和社会资本与中小学生抑郁/生活质量的关系。
  • 批准号:
    20K14043
  • 财政年份:
    2020
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Grant-in-Aid for Early-Career Scientists
Prevention, Compensation and Relief Policy for Asbestos Disaster and International Relations
石棉灾害的预防、补偿、救济政策与国际关系
  • 批准号:
    15H01757
  • 财政年份:
    2015
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Grant-in-Aid for Scientific Research (A)
Degradation mechanisms of sigma 32 by membrane targeting via SRP pathway
通过 SRP 途径膜靶向降解 sigma 32 的机制
  • 批准号:
    23657128
  • 财政年份:
    2011
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Grant-in-Aid for Challenging Exploratory Research
Studies on Calculation of a Set of the Pareto Solutions for Multi-objective Optimization in Transmission Network Expansion Planning with the Uncertainties
含不确定性的输电网络扩容规划多目标优化帕累托解集计算研究
  • 批准号:
    23560342
  • 财政年份:
    2011
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
SecDF function and roles of the proton motive force in protein translocation
SecDF 的功能以及质子动力在蛋白质易位中的作用
  • 批准号:
    22370070
  • 财政年份:
    2010
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Grant-in-Aid for Scientific Research (B)
Static and dynamical properties characteristic to Bose-Fermi atoms on optical lattices
光学晶格上玻色费米原子的静态和动态特性
  • 批准号:
    21540410
  • 财政年份:
    2009
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Structural analysis of SecA-SecYE complex from Thermus thermophilus
嗜热栖热菌 SecA-SecYE 复合物的结构分析
  • 批准号:
    19370085
  • 财政年份:
    2007
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Grant-in-Aid for Scientific Research (B)
Studies on Highly accurate Short-term Electric Power Load Forecasting with Fuzzy Data Mining
模糊数据挖掘高精度短期电力负荷预测研究
  • 批准号:
    13650319
  • 财政年份:
    2001
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Studies on a Load Forecasting Method with the Evolutionary Parallel Algorithm
一种进化并行算法的负荷预测方法研究
  • 批准号:
    09650331
  • 财政年份:
    1997
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
ROLE OF DYSFUNCTIOINAL DOPAMINERGIC SYSTEM ON PATHOGENESIS OF POLYCYSTIC OVARIAN SYNDROME
功能障碍的多巴胺能系统在多囊卵巢综合征发病机制中的作用
  • 批准号:
    63570790
  • 财政年份:
    1988
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Grant-in-Aid for General Scientific Research (C)

相似海外基金

CRII: RI: TRUST—TRustworthy Uncertainty Propagation for Sequential Time-Series Analysis
CRII:RI:TRUST – 用于顺序时间序列分析的值得信赖的不确定性传播
  • 批准号:
    2401828
  • 财政年份:
    2023
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Standard Grant
Outcomes After Emergency Department Visits for Dyspnea: Population-Based Interrupted Time-Series Analysis of Implementation of B-Type Natriuretic Peptide Assays
因呼吸困难而急诊就诊后的结果:实施 B 型利尿钠肽测定的基于人群的间断时间序列分析
  • 批准号:
    493119
  • 财政年份:
    2023
  • 资助金额:
    $ 2.18万
  • 项目类别:
Mapping the active universe with time series analysis of huge dataset based on wide field optical surveys
基于广域光学巡天的海量数据集时间序列分析绘制活跃宇宙图
  • 批准号:
    23H01217
  • 财政年份:
    2023
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Grant-in-Aid for Scientific Research (B)
Collaborative Research: Linking 3He/4He with eruptive behavior: A time series analysis of recent Kilauea, Iceland, and La Palma eruptions
合作研究:将 3He/4He 与喷发行为联系起来:对近期基拉韦厄火山、冰岛火山和拉帕尔马火山喷发的时间序列分析
  • 批准号:
    2232532
  • 财政年份:
    2023
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Standard Grant
Exposure to Low Dose Ionizing Radiation In Adult Patients with Congenital Heart Disease - A Time Series Analysis Assessing the Past and Projecting the Future
成年先天性心脏病患者接触低剂量电离辐射 - 评估过去和预测未来的时间序列分析
  • 批准号:
    479720
  • 财政年份:
    2023
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Operating Grants
Collaborative Research: Linking 3He/4He with eruptive behavior: A time series analysis of recent Kilauea, Iceland, and La Palma eruptions
合作研究:将 3He/4He 与喷发行为联系起来:对近期基拉韦厄火山、冰岛火山和拉帕尔马火山喷发的时间序列分析
  • 批准号:
    2232531
  • 财政年份:
    2023
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Standard Grant
Time-series analysis of trends for polypharmacy using real-world data and establishment of a regional model for correction of potentially inappropriate medications
使用真实世界数据对复方用药趋势进行时间序列分析,并建立纠正潜在不当用药的区域模型
  • 批准号:
    23K14411
  • 财政年份:
    2023
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Grant-in-Aid for Early-Career Scientists
AE2Vec: Medical concept embedding and time-series analysis for automated adverse event detection
AE2Vec:用于自动不良事件检测的医学概念嵌入和时间序列分析
  • 批准号:
    10751964
  • 财政年份:
    2023
  • 资助金额:
    $ 2.18万
  • 项目类别:
CRII: RI: TRUST—TRustworthy Uncertainty Propagation for Sequential Time-Series Analysis
CRII:RI:TRUST – 用于顺序时间序列分析的值得信赖的不确定性传播
  • 批准号:
    2153413
  • 财政年份:
    2022
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Standard Grant
Machine learning framework and time series analysis for adaptive radiation therapy in head and neck cancer
头颈癌适应性放射治疗的机器学习框架和时间序列分析
  • 批准号:
    559195-2021
  • 财政年份:
    2022
  • 资助金额:
    $ 2.18万
  • 项目类别:
    Postgraduate Scholarships - Doctoral
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了