Short-term Forecasting Based On Support Vector Machines, Ship Electric Load

The short-term load forecasting is an important routine for power dispatch departments. Its precision will influence the economic and secure operation of power systems and quality of power supply. The present short-term load forecasting is usually focus on the big district electric power on land. At present, with the development of bigger size and more function in ship, there are more and more demands on the larger-scale and super larger-scale ship in the ocean transportation, and then the complex and automation extent becomes much higher than before in the ship's electric power serve and transfer and control system. There are some traits in the ship's electric power, for example, the power station in ship is made of diesel generator and has lower power capacity, the electric power dynamic control system need work frequently because of many kinds of electrical equipment, The situation of dynamic change on ship's power load appear more often and the range of dynamic change is also bigger, which are straight to affect the stabilization of the power system, so we need predict the change of the electric power load in time and based on it we can control the change of power load with rational range by regulating the power distribution and ensure that ship power system will be on work well .Power load system is a multi-dimensional nonlinear system. It is easy to get the chaotic time series of practical load data in the real situation. So in this paper we study the forecast of the chaotic time series at first and present a new forecast method based on support vector machines regress theory and apply it to the chaotic time series. Support vector machine is a new generation machine learn algorithm and based on statistical study theory, the essence of the training support vector machines is equal to solving the quadratic formulation problem. The advantages of this method include: high forecasting accuracy, global optima property and small time complexity. In order to proof the performance in these sides, we have had done two works in this paper, the first is that we apply to chaotic time seriesby using the reconstruct theory and analyst result by comparing with artificial neural network in other literature. The second is that we add different level noise to chaotic time series and analyst result by comparing with back-perception and radial basis function network. The simulation shows the forecasting behavior of predicting chaotic time series by using support vector machines is better than others and the method has good generalization and solid character.Through the foundation work in chaotic time series, we are in combination with the character of ship power load and apply the prediction conception to ship power system in the first time, we also build the model of ship power load short time prediction based on support vector machines and do the simulation experiment by using the practical ship power load data .the simulation shows the method has apparently more advantages than other method such as artificial neuron network in the prediction precision and operating time.