外文翻譯---人工神經(jīng)網(wǎng)絡(luò)在短期負(fù)荷預(yù)測(cè)中的應(yīng)用（英文）

1、Artificial Neural Networks in Short Term load Forecasting K.F. Reinschmidt, President B. Ling Stone h Webster Advanced Systems Development Services, Inc. 245 Summer Street Boston, U 0221 0 Phone: 617-589-1

2、 84 1 Abstract We discuss the use of artificial neural networks to the short term forecasting of loads. In this system, there are two types of neural networks: non-linear and linear neural networks. The non- linear

3、neural network is used to capture the highly non-linear relation between the load and various input parameters. A neural network- based ARMA model is mainly used to capture the load variation over a very short time p

4、eriod. Our system can achieve a good accuracy in short term load forecasting. 1. Introduction Short term (hourly) load forecasting is an essential hction in electric power operations. Accurate shoirt term load foreca

5、sts are essential for efficient generation dispatch, unit commitment, demand side management, short term maintenance scheduling and other purposes. Improvements in the accuracy of short term load forecasts can

6、result in si@cant financial savings for utilities and cogenerators. Various teclmiques for power system load forecasting have been reported in literature. Those include: multiple linear regression, time series, gene

7、ral exponential smoothing, Kalman filtering, expert system, and artificial neural networks. Due to the highly nonlinear relations between power load and various parameters (whether temperature, humidity, wind speed,

8、 etc.), non-linear techniques, both for modeling and forecasting, tend to play major roles in the power load forecasting. The artificial neural network (A“) represents one of those potential non-linear techniques. H

9、owever, the neural networks used in load forecasting tend to be large in size due to the complexity of the system. Therefore, training of such a large net becomes a major issue since the end user is expected to run

10、 this system at daily or even hourly basis. In this paper, we consider a hybrid neural network based load forecasting system. In this network, there are two types of neural networks: non-linear and linear neural netwo

11、rks. The non- linear neural network is used to capture the highly non-linear relation between the load and various input parameters such as historical load values, weather temperature, relative humidity, etc. We use

12、 the linear neural network to generate an ARMA model. This neural network based ARMA model will be mainly used to capture the load variation over a very short time period. The final load forecasting system is a com

13、bination of both neural networks. To train them, sigxuiicant amount of historical data are used to minimize MAPE (Mean Absolute Percentage Error). A modified back propagation learning algorithm is carried out to trai

14、n the non-linear neural network. We use Widrow-Hoff algorithm to train the linear neural network. Since our network structure is simple, the overall system training is very fast. To illustrate the performance of this

15、 neural network-based load forecasting system in real situations, we apply the system to actual demand d a t aprovided by one utility. Three years of hourly data (1989, 1990 and 1991) are used to train the neural ne

16、tworks. The hourly demand data for 1992 are used to test the overall system. This paper is organized as follows: Section I is the introduction of this paper; Section I1 0-7803-2550-8~/95$4.00@1995 IEEE 209 where:fl

17、.) is a nonlinear function determined by the artificial neural network. Layered, feed-forward neural networks are used, typically with one hidden layer (although in some cases with two). The layers are fully connect

18、ed, with one bias unit in each layer (except the output layer). The output of each unit is the slum of the weighted inputs (including the bias), passed through an exponential activation fiinction. Our modiked backpro

19、pagation method is applied. The errors are defined to be the sum of the squares of the deviations between the computed values at the output units and the actual or desired values; this definition makes the error fu

20、nction differentiable everywhere. Unlike the linear time series model, in which there is one fitted coefficient for each lagged variable, in the nonlinear neural network forecaster tlhe selection of lagged input varia

21、bles is independent of the number of fitted coefficients, the network weights, the number of which is determined by the number of layers and the number of hidden units. Also, in linear regression models, if an in

22、put variable is extraneous, then its regression coefficient is zero (or, more properly, is not significantly different from zero by a t-test). However, in nonlinear neural networks this is not necessarily true; an

23、input Variable may be unimportant but still have large weights; the effects of these weights cancel somewhere downstream. The same is true for the hidden units. Therefore, in conventional backpropagation for nonlinea

24、r neural networks, there is no automatic elimination of extraneous input nodes or hidden nodes. However, in practical forecasting it is necessary to achieve a parsimonious model, one which is neither too simple nor

25、too complex for the problem at hand. If the neural network is chosen to be too small (to have too few input or hidden u n i t s ) ,then it will not be flexible enough to capture ithe dynamics of the electrical deman

26、d system; this is known as underfitting. Conversely, if the neural network is too large, then it can fit not only the underlying signal but also the noise in the training set; this is known as overfitting. Overf

27、itted models may show low error rates on the training set but do not generalize; they may then have high error rates in actual prediction. The nonlinear model can yield greater accuracy than the linear formulation, bu

28、t takes much longer to train. Large nonlinear neural networks are also prone to overfitting. Forecasting requires parsimonious models capable of generalization. The size of the nonlinear neural network can be reduc

29、ed by examining the correlation coefficients, or by using the genetic algorithm to select the optimum set of input variables. The linear model is a satisfactory approximation to the nonlinear model for the purpose

30、of selecting the input terms. Large artificial neural networks trained using backpropagation are notoriously time-consuming, and a number of methods to reduce training time have been evaluated. One method that has

31、 been found to yield orders of magnitude reductions in training time replaces the steepest descent search by techniques that mod@ the network weights using a least-squares approach; the computations in each ste

32、p are greater but the number of iterations is greatly reduced. Reductions in training time are desirable not only to reduce computation costs, but to allow more alternative input variables to be investigated, and he

33、nce to optimize forecast accuracy. 4. Determination of Network Structure As we stated above, the neural network used in load forecasting tends to be large in size, which results in longer training time. By carefully

34、 choosing network structure (i.e., input nodes, output nodes), one will be able to build a relatively small network. In our system, we apply statistical analysis and genetic algorithm to find the network “optimal“ st