On-line energy forecasting system and method based on product ARIMA model

Abstract

An on-line energy forecast system based on a product ARIMA module and a method thereof belong to the field of steel industry energy forecast technology. The system comprises a local PLC, a PCS layer consisting of DCSs, a MES layer, an ERP management layer and a network system. The network system comprises an SCADA system arranged on a spot, a real time database server, a database server, an application server, a client workstation, an anti-virus database and a network which is connected with a computer, a controller and a sensor. The invention has the advantages that an applicable module grade is configured by a prediction algorithm parameter configuration module, which can realize that real time on-line forecast can be carried out on multiple data types comprising steady, non-stationary,seasonal fluctuation data.

Description

technical field [0001] The invention belongs to the technical field of energy forecasting for iron and steel enterprises, and provides an online energy forecasting system and method based on the product ARIMA model, which can model and predict various data types including stationary, non-stationary, and seasonal fluctuations, and is mainly used for short-term and mid-term forecast. Background technique [0002] The flow and fluctuation of energy in iron and steel enterprises are affected by many factors, complex and changeable, and difficult to grasp. To a large extent, it is a random and unstable state, and the factors that affect its fluctuation occur from time to time. It is impossible to use a single If a fixed model can achieve accurate prediction, if the latest information cannot be used to correct the model parameters, large prediction deviations will occur. Therefore, this paper proposes an online energy forecasting method based on the product ARIMA model. [0003]...

AI Technical Summary

Problems solved by technology

The GM(1,1) model is commonly used in gray forecasting technology, which has the advantages of simple modeling and less modeling data, but it also has its own shortcomings, such as: the modeling data requires non-negative, and the data trend is exponentially growing, etc. This limits its wide application in practice

Although there are many methods such as data preprocessing to make the load exponentially increase; changing the modeling method and so on to broaden the scope of application, but only for the specific change trends of some energy media, the prediction effect is better. However, it is not suitable for the complex and changeable environment of the steel plant.

Neural network technology is also a widely used method in the field of energy forecasting. However, due to the long modeling and training time of neural network technology, there are defects such as local extremum, and it is not suitable for online forecasting.

Although the regression prediction technology is a relatively mature prediction technology, it is difficult to use a causal regression model to describe it because there are many factors affecting energy fluctuations in the iron and steel industry. Even if such a relatively satisfactory regression equation can be fitted, The results are also difficult to predict

Because generally in the causal relationship, the dependent variable and the independent variable are synchronized in time, if the future state of the dependent variable cannot be obtained, this regression model will not be used for prediction

Images