基于元认知二型模糊神经网络的电力负荷区间预测方法OA

The prediction of the key indicators is a challenging problem due to the high nonlinearity and strong un-certainties in power load data.To solve this problem,a metacognitive type-2 fuzzy neural network(MCT2FNN)-based interval prediction method is proposed.First,a type-2 fuzzy rule based on multi-value mapping is designed to extend rule consequents from scalar values to interval vectors by using interval estimation technology.It can handle the variable correlation bias caused by uncertainty and capture the nonlinear relationship between the variables in the load series.Second,a type-2 fuzzy neural network(T2FNN)with an error compensation mechanism is estab-lished.In this network,a dynamic feedback structure is introduced to perceive and compensate for cumulative er-rors and model biases in real time,which can achieve high precision prediction of key indicators.Then,an interval coverage probability and interval width-based metacognitive learning algorithm is designed to adaptively optimize the boundary estimates of T2FNN through the real-time assessment of interval reliability,which can improve the confidence level of interval predictions.Finally,the proposed MCT2FNN is applied to interval prediction tasks for the urban power system.The experimental results demonstrate that the method can provide high-confidence and precise prediction intervals for power systems.