负荷密度预测的方案比较冲突度交互评价方法
发布时间：2019-05-10 21:31
【摘要】：针对电力负荷密度预测中收集大量有效数据样本困难以及专家一次性评判难以获得合理结果的问题,提出了一种以方案比较冲突度为度量指标的交互式专家语言评判电力负荷密度预测法。该方法在采用语言评判方式评价城市小区不同类型指标时,以方案比较冲突度来度量专家在评判小区某指标更优(更劣)时的冲突程度,从中选取冲突较大的小区,以一致度标准修改其评价信息和专家权重,实现专家之间的交互式评判,并在预测时,将交互后的评价信息经信息集成算子集成后同负荷密度代入BP神经网络中训练,以训练后的结构预测城市各小区的负荷密度。算例表明,该方法不仅能有效解决缺乏数据的问题,同时能克服交互式决策中仅从整体角度考虑专家一致性问题的局限性,具有很好的实践意义。
[Abstract]:In order to solve the problem that it is difficult to collect a large number of effective data samples in power load density forecasting and it is difficult for experts to obtain reasonable results in one-off evaluation, An interactive expert language evaluation method for power load density forecasting based on the conflict degree of scheme comparison is proposed in this paper. When the language evaluation method is used to evaluate different types of indicators in urban residential areas, the conflict degree of experts is measured when a certain index is better (worse), and the community with greater conflict is selected from the conflict degree. The evaluation information and expert weight are modified by consistency standard to realize the interactive evaluation among experts. In the prediction, the interactive evaluation information is integrated by information integration operator and the same load density is replaced into BP neural network for training. The structure after training is used to predict the load density of each district in the city. Numerical examples show that this method can not only effectively solve the problem of lack of data, but also overcome the limitation of considering the consistency of experts only from the whole point of view in interactive decision-making, which has a good practical significance.
【作者单位】： 智能电网运行与控制湖南省重点实验室(长沙理工大学);国网湖南省电力公司;
【基金】：国家自然科学基金资助项目(51277016,71331001)
【分类号】：TM715
[Abstract]:In order to solve the problem that it is difficult to collect a large number of effective data samples in power load density forecasting and it is difficult for experts to obtain reasonable results in one-off evaluation, An interactive expert language evaluation method for power load density forecasting based on the conflict degree of scheme comparison is proposed in this paper. When the language evaluation method is used to evaluate different types of indicators in urban residential areas, the conflict degree of experts is measured when a certain index is better (worse), and the community with greater conflict is selected from the conflict degree. The evaluation information and expert weight are modified by consistency standard to realize the interactive evaluation among experts. In the prediction, the interactive evaluation information is integrated by information integration operator and the same load density is replaced into BP neural network for training. The structure after training is used to predict the load density of each district in the city. Numerical examples show that this method can not only effectively solve the problem of lack of data, but also overcome the limitation of considering the consistency of experts only from the whole point of view in interactive decision-making, which has a good practical significance.
【作者单位】： 智能电网运行与控制湖南省重点实验室(长沙理工大学);国网湖南省电力公司;
【基金】：国家自然科学基金资助项目(51277016,71331001)
【分类号】：TM715
【相似文献】
相关期刊论文 前10条
1 姚艳;孙志能;;宁波市电力负荷指标体系之空间负荷密度研究[J];华东电力;2007年06期
2 符杨;朱兰;曹家麟;;基于模糊贴近度理论的负荷密度指标求取新方法[J];电力系统自动化;2007年19期
3 李双伟;范斗;王康元;邱家驹;鄢安河;;基于数据分区的负荷密度显示的实现[J];继电器;2008年03期
4 汤波;胡荣;符杨;宓佳t，
本文编号：2474011
本文链接：https://www.wllwen.com/kejilunwen/dianlidianqilunwen/2474011.html
