No abstract

Power consumption prediction is the basis of implementing planned power consumption and preparing production plan. It is one of the main projects in the design of industrial and mining enterprises. It is also an important link to ensure the balance between national economic needs and power supply. Due to the influence of distributed energy and the change of power demand and load characteristics of the user side compared with the past, the power consumption prediction starts to face smallscale users and is more easily disturbed by various influencing factors, so the traditional prediction method is not fully suitable for today's power consumption prediction. Firstly, STL is used to decompose the power consumption sequence of corresponding month into trend component, season component and random component. Secondly, the BP neural network model is used to predict the seasonal component of the month when the seasonal mutation and major festivals are located. ARIMA model is used to predict the trend component. The average value is used to predict the random components. Then, the predicted values of the three components are reconstructed into the final predicted values. Finally, the algorithm is compiled by R language, and the validity of the proposed method is verified by the actual monthly electricity sales data of a University Park in the north. And further consider the prediction method of economic factors.

Short-term power load forecasting is essential in ensuring the safe operation of power systems and a prerequisite in building automated power systems. Short-term power load demonstrates substantial volatility because of the effect of various factors, such as temperature and weather conditions. However, the traditional short-term power load forecasting method ignores the influence of various factors on the load and presents problems of limited nonlinear mapping ability and weak generalization ability to unknown data. Therefore, a short-term power load forecasting method based on GRA and ABC-SVM is proposed in this study. First, the Pearson correlation coefficient method is used to select critical influencing factors. Second, the gray relational analysis (GRA) method is utilized to screen similar days in the history, construct a rough set of similar days, perform K-means clustering on the rough sets of similar days, and further construct the set of similar days. The artificial bee colony (ABC) algorithm is then utilized to optimize penalty coefficient and kernel function parameters of the support vector machine (SVM). Finally, the above method is applied on the basis of actual load data in Nanjing for simulation verification, and the results show the effectiveness of the proposed method.

No abstract