Fuzzy and Neuro-fuzzy Computing Models for Electric Load Forecasting
نویسندگان
چکیده
Two new computing models, namely a fuzzy expert system and a hybrid neural network-fuzzy expert system for time series forecasting of electric load, are presented in this paper. The fuzzy-logic-based expert system utilizes the historical relationship between load and dry-bulb temperature, and predicts electric loads fairly accurately, 1-24 h ahead. In the case of the hybrid neural network-fuzzy expert system, the input vector consists of the membership values of the linguistic properties of the past load and weather parameters, and the output vector is defined in terms of the fuzzy class membership values of the forecasted load. Linear and nonlinear adaptive fuzzy correction schemes are then used to augment the output from the neuro-fuzzy computing model to yield the final forecast. Extensive studies have been performed for load prediction for all seasons, and the results for a typical winter day are given to confirm the effectiveness of these models.
منابع مشابه
Electricity Load Forecasting by Combining Adaptive Neuro-fuzzy Inference System and Seasonal Auto-Regressive Integrated Moving Average
Nowadays, electricity load forecasting, as one of the most important areas, plays a crucial role in the economic process. What separates electricity from other commodities is the impossibility of storing it on a large scale and cost-effective construction of new power generation and distribution plants. Also, the existence of seasonality, nonlinear complexity, and ambiguity pattern in electrici...
متن کاملShort-term Electrical Load Forecasting Using Neuro-Fuzzy Model with Error Compensation
This paper proposes a method to improve the accuracy of a short-term electrical load forecasting (STLF) system based on neuro-fuzzy models. The proposed method compensates load forecasts based on the error obtained during the previous prediction. The basic idea behind this approach is that the error of the current prediction is highly correlated with that of the previous prediction. This simple...
متن کاملNeuro - Fuzzy Elman Network for Short - Term Electric Load Forecasting
The problem of short-term electric load forecasting (STLF) is considered. A modified architecture of Elman-type recurrent neural network is proposed. It utilizes a special fuzzification layer to deal with quantitative as well as ordinal and nominal data. The second hidden layer of the network consists of standard Rosenblatt-type neurons with sigmoidal activation functions. The context layer is ...
متن کاملPrediction Intervals for Short-Term Load Forecasting Neuro-Fuzzy Models
In the paper the problem of estimation of the prediction intervals (error bars) for the family neuro-fuzzy Short-Term Load Forecasting (STLF) models is discussed. We investigate two neuro-fuzzy networks: Fuzzy Basis Function (FBF) Networks, and linear neuro-fuzzy model with Tagagi-Sugeno reasoning. The paper contains comparison of selected most important methods for error bars calculation (anal...
متن کاملSoft Computing for Developing Short Term Load Forecasting Models in Czech Republic
This paper presents a comparative study of six soft computing models namely multilayer perceptron networks, Elman recurrent neural network, radial basis function network, Hopfield model, fuzzy inference system and hybrid fuzzy neural network for the hourly electricity demand forecast of Czech Republic. The soft computing models were trained and tested using the actual hourly load data obtained ...
متن کامل