Short-term load forecasting using diagonal recurrent neural network

Lee, K.Y.; Choi, Tae-Il; Ku, Chao-Chee; Park, J.H.

doi:10.1109/ann.1993.264286

Cited by 21 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most significant aspects of the model fall into the following two areas: training process and selection of the input variables. At the same time Lee et al [11] presented a diagonal recurrent ANN with an adaptive learning rate. In 1993, Chaudhary et al [4] presented a fast & accurate method of STLF using combinations of self-organising maps (SOM) & multi-layer perception model.…”

Section: Modification Of W Rmentioning

confidence: 98%

Improved generalized neuron model for short-term load forecasting

Chaturvedi¹,

Mohan²,

Singh³

et al. 2004

Soft Computing - A Fusion of Foundations, Methodologies and App

View full text Add to dashboard Cite

The conventional neural networks consisting of simple neuron models have various drawbacks like large training time for complex problems, huge data requirement to train a non linear complex problems, unknown ANN structure, the relatively larger number of hidden nodes required, problem of local minima etc. To make the Artificial Neural Network more efficient and to overcome the above-mentioned problems the new improved generalized neuron model is proposed in this work. The proposed neuron models have both summation (S) and product (p) as aggregation function. The generalized neuron models have flexibility at both the aggregation and activation function level to cope with the non-linearity involved in the type of applications dealt with. The training and testing performance of these models have been compared for Short Term Load Forecasting Problem.

show abstract

Section: Modification Of W Rmentioning

confidence: 98%

Improved generalized neuron model for short-term load forecasting

Chaturvedi¹,

Mohan²,

Singh³

et al. 2004

Soft Computing - A Fusion of Foundations, Methodologies and App

View full text Add to dashboard Cite

show abstract

“…This RNN seems difficult to use for forecasts of large horizon because of stability problems. In [23,24] each neuron is only fed back to himself. A comparison between a feed forward technique and this recurrent network is also made [24].…”

Section: Single Multi-input Single-output Models (Miso)mentioning

confidence: 99%

A Review of Connectionist Models for Short Term Electrical Load Forecasting

Piras¹,

Czernichow²,

Imhof³

et al. 1998

Industrial Applications of Neural Networks

View full text Add to dashboard Cite

Mastering the production, transmission and distribution of electrical energy is a challenge to which the electrical engineer is perpetually confronted with. A precise Short Term electrical Load Forecasting (STLF) results in economic cost savings and increased security operation's conditions, allowing electrical companies to commit their own production resources in order to optimize energy prices and exchanges with vendors and clients. In this review, we expose a classification in six sub-groups of Artificial Neural Networks based models used for short term electrical load forecasting, proposed in the last four years. 143Industrial Applications of Neural Networks Downloaded from www.worldscientific.com by UNIVERSITY OF BIRMINGHAM LIBRARY -INFORMATION SERVICES on 03/21/15. For personal use only. Industrial Applications of Neural Networks Downloaded from www.worldscientific.com by UNIVERSITY OF BIRMINGHAM LIBRARY -INFORMATION SERVICES on 03/21/15. For personal use only.

show abstract

“…Recurrent Neural Network is widely used in forecasting these years [5] and it can well done the non-stationary time series prediction, providing satisfactory results [6]. In the RNN modeling, all available indicators can be used as the inputs of RNN, but irrelevant or correlated features could deteriorate the generalization performance of RNN due to the "curse of dimensionality" problem [7].…”

Section: Introductionmentioning

confidence: 99%

Forecasting the Area Flowing of Graduate Employment Based on KRNN method

Qing

Sun²

2008

2008 4th International Conference on Wireless Communications, Networking and Mobile Computing

View full text Add to dashboard Cite

It is hard to search the influence variables and to forecast the flowing of graduate employment due to the time series and complex factor inputs. Recently the neural network method has been successfully employed to solve the problem. However the forecasting result is not ideal due to the nonlinearity and noise. In this work, by combining Recurrent Neural Network (RNN) with Kernel Principal Component Analysis (KPCA), a KRNN model is presented, based on which, the area flowing of graduate employment is tried to be forecasted, and both the complex factor problem and time series problem has been dealt with. In the model, RNN with Kernel Principal Component Analysis (KPCA) and Principal Component Analysis (PCA) as the feature extraction is introduced in as comparison. And then by an empirical study with actual data from some high school of China, it is shown that the proposed methods can both achieve good forecasting performance comparing with NN method. And the KPCA method performs better than the PCA method.

show abstract

Short-term load forecasting using diagonal recurrent neural network

Cited by 21 publications

References 11 publications

Improved generalized neuron model for short-term load forecasting

Improved generalized neuron model for short-term load forecasting

A Review of Connectionist Models for Short Term Electrical Load Forecasting

Forecasting the Area Flowing of Graduate Employment Based on KRNN method

Contact Info

Product

Resources

About