Electric Power Load Forecasting Based On Grey Theory

The power load forecasting is one of the most important tasks to the planning department of the power enterprise, and the level of the load forecasting work has already become one of the most outstanding marks to judge whether the management of an enterprise is modernized. The accuracy of load forecasting is a key requirement for the planning, economy and security of modern power systems.Because the load forecasting is affected by many uncertain factors, up to now, no method can obtain the satisfying forecasting results at all circumstances. Therefore, appropriate model should be selected out according to the corresponding facts in the practical forecasting.In this thesis, the significance of load forecasting and its development at home and abroad is introduced briefly at first, and the load forecasting methods are also summarized. Then a deeply research on grey theory is carried through. Through researching on modeling mechanism of grey forecasting method, the limitations of grey model are found out and some improved measures are adopted. Firstly, through the pretreatment and optimization to historical load data, the ability of grey forecasting dealing with fluctuant load data is strengthened, besides, the application range and forecasting precision are enhanced. Secondly, by selecting initial condition, the curve is made to match the rule of the future development better. Thirdly, through correcting the grey model according to the partial residual error, the precision of the model is improved. Finally, by using equally dimensional new information model, new information is used in the forecasting, which not only overcomes the shortcoming that the math model is changeless in simple grey forecasting method, but also makes use of the advantage of the high precision in short term load forecasting. After the improvement, the applicable range of the common grey model is widened. Compared with the common grey model by calculation examples, the improved model can be used in short term and mid-long term load forecasting of power systems. The simulation results show that the improved model has the advantages of small error and high precision.