A new approach to electric load forecasting which combines the powers of neural network and fuzzy logic techniques is proposed. Expert knowledge represented by fuzzy rules is used for preprocessing input data fed to a neural network. For training the neural network for one-day ahead load forecasting, fuzzy if-then rules such as 'If x/sub 1/ is high and x/sub 2/ is low, then y is positive small' are used, in addition to historical load and weather data that are usually employed in conventional supervised learning methods. The fuzzy front-end processor maps both fuzzy and numerical input data to a fuzzy output. The input vector to the neural network consists of these membership values to linguistic properties. To deal with the linguistic values such as high, low, and medium, an architecture of neural network that can handle fuzzy input vectors is propounded. The proposed method effectively deals with trends and special events that occur annually. The fuzzy-neural network is trained on real data from a power system and evaluated for forecasting next-day load profiles based on forecast weather data and other parameters. Simulation results are presented to illustrate the performance and applicability of this approach. A comparison of results with other commonly used forecasting techniques establishes its superiority.
展开▼
机译:提出了一种结合神经网络和模糊逻辑技术的电力负荷预测新方法。由模糊规则表示的专家知识用于预处理输入到神经网络的输入数据。为了训练神经网络进行提前一天的负荷预测,除了使用模糊的if-then规则,例如“如果x / sub 1 /为高,而x / sub 2 /为低,则y为正小”,传统的有监督学习方法中通常使用的历史负荷和天气数据。模糊前端处理器将模糊和数字输入数据映射到模糊输出。神经网络的输入向量包括这些隶属度值和语言属性。为了处理诸如高,低和中等语言值,提出了一种可以处理模糊输入矢量的神经网络体系结构。所提出的方法有效地处理了每年发生的趋势和特殊事件。模糊神经网络接受了来自电力系统的真实数据训练,并根据天气预报数据和其他参数进行了评估,以预测次日的负荷曲线。仿真结果表明了该方法的性能和适用性。将结果与其他常用的预测技术进行比较可以确定其优势。
展开▼