MPC Built Frequency Regularization Studies of Multi-Area Electric Power System Base on Short Term Load Forecasting Using ANN

2020 ◽  
Vol 50 ◽  
pp. 145-161
Author(s):  
Gulshan Sharma
Keyword(s):  
Frequency Control ◽  
Load Forecasting ◽  
Electric Power System ◽  
Load Frequency Control ◽  
Short Term ◽  
Look Ahead ◽  
Control Framework ◽  
Short Term Load Forecasting ◽  
Load Pattern ◽  
Artificial Neural Network Ann

This article presents the plan to design model predictive control (MPC) built load frequency control (LFC) action for a multi-area interconnected control framework. The multi-area control framework comprises of plants with differing sources of vitality. The HVDC tie-lines are considered as an interconnection within the control framework. Further, the most of the past studies in this area was to evaluate the performance of LFC based on step load disturbance and these strategies does not speak to the genuine time circumstances of the control framework operation which may cause the over regulation of the control framework. To improve the execution of LFC, a short term load forecasting (STLF) founded LFC using artificial neural network (ANN) is proposed in this paper. Assist, the real load pattern data is collected on hourly basis and process with the help of ANN for LFC studies. The predicted hourly load is utilized to supply future load to the LFC framework by means of look-ahead control calculation on the premise of 10 miniature interim and MPC based LFC are design to alter the set point to zero in order to match the generation with real load pattern in a best possible manner. The comparison between real and forecasted load utilizing MPC is given through computer reenactments for LFC and the application results of real scenario is presented to show efficacy of the proposed work.

scholarly journals Survey on short-term load forecasting using hybrid neural network techniques

2018 ◽  
Vol 7 (2.8) ◽  
pp. 464
Author(s):  
Shaive Dalela ◽  
Aditya Verma ◽  
A L.Amutha
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Load Forecasting ◽  
Theoretical Data ◽  
Electric Power System ◽  
Support Vector ◽  
Short Term ◽  
Load Demand ◽  
Short Term Load Forecasting ◽  
Artificial Neural

Load forecasting is an issue of great importance for the reliable operation of the electric power system grids. Various forecasting methodologies have been proposed in the international research bibliography, following different models and mathematical approaches. In the current work, several latest methodologies based on artificial neural networks along with other techniques have be discussed, in order to obtain short-term load forecasting. In this paper, approaches taken by different researchers considering different parameters in means of predicting the lease error has been shown.  The paper investigates the application of artificial neural networks (ANN) with fuzzy logic (FL), Genetic Algorithm(GA), Particle Swarm Optimization(PSO) and Support Vector Machines(SVM) as forecasting tools for predicting the load demand in short term category. The extracted outcomes indicate the effectiveness of the proposed method, reducing the relative error between real and theoretical data

scholarly journals Layer Recurrent Neural Network based Power System Load Forecasting

2015 ◽  
Vol 16 (3) ◽  
pp. 423
Author(s):  
Nikita Mittal ◽  
Akash Saxena
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Load Forecasting ◽  
Absolute Error ◽  
Percentage Error ◽  
Short Term ◽  
Short Term Load Forecasting ◽  
Load Pattern ◽  
Facility Expansion ◽  
Large Distribution

This paper presents a straight forward application of Layer Recurrent Neural Network (LRNN) to predict the load of a large distribution network. Short term load forecasting provides important information about the system’s load pattern, which is a premier requirement in planning periodical operations and facility expansion. Approximation of data patterns for forecasting is not an easy task to perform. In past, various approaches have been applied for forecasting. In this work application of LRNN is explored. The results of proposed architecture are compared with other conventional topologies of neural networks on the basis of Root Mean Square of Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE). It is observed that the results obtained from LRNN are comparatively more significant.

Short-term load forecasting for microgrids based on DA-SVM

2019 ◽  
Vol 38 (1) ◽  
pp. 68-80 ◽  
Author(s):  
Anan Zhang ◽  
Pengxiang Zhang ◽  
Yating Feng
Keyword(s):  
Load Forecasting ◽  
Electric Power System ◽  
Support Vector ◽  
Short Term ◽  
Optimal Position ◽  
Content Type ◽  
Svm Algorithm ◽  
Short Term Load Forecasting ◽  
Factor C ◽  
Mean Square Errors

Purpose The study aims to accomplish the short-term load forecasting for microgrids. Short-term load forecasting is a vital component of economic dispatch in microgrids, and the forecasting error directly affects the economic efficiency of operation. To some extent, short-term load forecasting is more difficult in microgrids than in macrogrids. Design/methodology/approach This paper presents the method of Dragonfly Algorithm-based support vector machine (DA-SVM) to forecast the short-term load in microgrids. This method adopts the combination of penalty factor C and kernel parameters of SVM which needs to be optimized as the position of dragonfly to find the solution. It takes the forecast accuracy calculated by SVM as the current fitness value of dragonfly and the optimal position of dragonfly obtained through iteration is considered as the optimal combination of parameters C and s of SVM. Findings DA-SVM algorithm was used to do short-term load forecast in the microgrid of an offshore oilfield group in the Bohai Sea, China and the forecasting results were compared with those of PSO-SVM, GA-SVM and BP neural network models. The experimental results indicate that the DA-SVM algorithm has better global searching ability. In the case of study, the root mean square errors of DA-SVA are about 1.5 per cent and its computation time is saved about 50 per cent. Originality/value The DA-SVM model presented in this paper provides an efficient and effective method of short-term load forecasting for a microgrid electric power system.

Short-Term Load Forecasting for Electric Power System Based on DB Wavelet and Regression BP Neural Networks

2013 ◽  
Vol 380-384 ◽  
pp. 3018-3021
Author(s):  
Kun Zhang ◽  
Yan Hui Wang
Keyword(s):  
Neural Networks ◽  
Electric Power ◽  
Dynamic Balance ◽  
Load Forecasting ◽  
Electric Power System ◽  
Wavelet Coefficients ◽  
Bp Neural Networks ◽  
Short Term ◽  
Power Load ◽  
Short Term Load Forecasting

In order to ensure the dynamic balance of power load and improve the accuracy of short-term load forecasting, this paper presents a method of short-term load forecasting for electric power based on DB wavelet and regression BP neural networks. In this method, we get the wavelet coefficients at different scales through series decomposing of wavelet decomposition to load sample, and each scale wavelet coefficients for threshold selection, and then trained adjusted wavelet coefficients by regression BP neural networks, reconstructed load sequence predicted date through inverse wavelet transform. Finally, the accuracy of this method is significantly higher than BP neural network by examples verification.

Sign in / Sign up

Export Citation Format

Share Document