類神經網路於電力訊號預測之研究
研究生：陳俊榮* 指導教授：黃瑞初**
義守大學電機工程研究所
摘要
本論文主要探討利用類神經網路之倒傳遞法(Back Propagation Network 簡稱BPN)，預測未來一年每日電力總負載量，並針對其每日總負載量(Total Daily Load)、最高溫度、平均溫度、最低溫度，以訊號特性，作一詳細分析。該多項訊號當神經網路訓練值的參考輸入，提供人工神經網路(Artificial Neural Network 簡稱ANN)學習，並藉由其預測未來每日之相對應負載值，即未來每日之總負載量，再與實際值相對照，並對預測值做一評估與分析，經模擬實驗結果發現其準確性與容錯的能力遠超過傳統的預測方法。
本論文除詳述倒傳遞神經網路外，並將對每月日期、星期、工作日、溫度、時間、季節等數據與每日的總負載量及尖峰負載量之間的關係做詳細分析與討論，同時，將預測結果與實際總負載做一詳細比較與介紹。
本文中每日電力總負載量取自1992年1月1日至1996年12月31日，前三年資料當做神經網路訓練之用，提供網路學習，詳細理論後敘；1995~1996年當做實際數據，以與網路預測輸出做比較，藉此判斷其準確性，取此期間數據值是因本人所得資料中，此期間的數據較其他時間完整，其對分析與預測亦較符合實際，對本研究更能彰顯其實用性。

The Prediction of Power Signal by Neural Networks
Student: Chun-Jung Chen* Advisor: Rey-Chue Hwang**
Department of Electrical Engineering
I-Shou University
Taiwan, R.O.C.
Abstract
In this study, the prediction of total load for each day by using neural network technique is investigated and developed. The data of daily total load, daily maximum temperature, daily average temperature and daily minimum temperature is studied and analyzed. Such analyzed data can be used as the input data for neural network training. Through a proper training, the network can predict the load value for next day. Compare with the real load value, we can find that the accuracy of prediction by using neural network is quite good.
The structure of neural network and its learning algorithm will be clearly described in this thesis. The relationships between daily total load and weather information will also be analyzed and reported. Then, the prediction results will be discussed.
The data of daily total load and its relevant weather information from year 1992 to year 1996 is studied and simulated. The first three years data is used as the input information for neural network training. The last two years data will be used as the real experimental values, i.e., for neural network testing. All of the predicted values will be computed and compared with the actual load values.

目錄
中文摘要………………………………………………………………………………i
英文摘要………………………………………………………………………………iii
誌謝………………………………………………………………………………………iv
目錄………………………………………………………………………………………v
圖目錄……………………………………………………………………………………vi
表目錄…………………………………………………………………………viii
第一章 緒論…………………………………………………………………1
第二章 日期與溫度………………………………………………………4
2-1 日期與總負載的關係…………………………………………4
2-2 溫度與總負載的關係…………..………………………6
2-3 每日總負載與尖峰負載……………………………………8
第三章 類神經網路基本原理
3-1 緒論………………………………………………………………………18
3-2 倒傳遞網路(BPN)…………………………………………19
第四章 負載訊號特性分析
4-1 緒論………………………………………………………………32
4-2 與 關係…………………… ………………………32
4-3 L(k)與 關係圖…………………………………………35
4-4 L(k)與 關係圖…………………………………………35
4-5 L(k)與 關係圖…………………………………………36
第五章 模擬結果分析
5-1 模擬結果……………………….………………………………50
第六章 結論………………………………………………………………63
參考文獻……………………………………………………………………64
授權書…………………………………………………………………………67
List of Figures
圖2-1 81年1月至6月總負載曲線 ----------------------------- 9
圖2-2 81年全年每日總負載量走勢圖 --------------------------------- 10
圖2-3 81年至83年每日平均溫度走勢圖 ----------------------------- 11
圖2-4 81年1月至6月總負載與溫度關係走勢圖 --------------------- 12
圖2-5 民國81年全年每日溫度與總負載量走勢圖 ---------------------- 13
圖2-6 82年每日總負載量與每日平均溫度 ----------------------------- 14
圖2-7 83年全年每日平均溫度與總負載曲線 --------------------------- 15
圖2-8 81-84四年間每日總負載與每日溫度 ---------------------------- 16
圖2-9 每日總負載與尖峰負載比較圖 ---------------------------------- 17
圖3-1 回歸型類神經網路 -------------------------------------------- 29
圖3-2 前授型類神經網路結構圖 -------------------------------------- 30
圖3-3 倒傳遞類神經網路架構圖 -------------------------------------- 31
圖4-1 與 之關係走勢圖(1992年全年) --------------------- 38
圖4-2 每日總負載Vs每日平均溫度 ---------------------------------- 39
圖4-3 每日總負載Vs每日最低溫 ------------------------------------ 40
圖4-4 每日總負載Vs每日最高溫 ------------------------------------ 41
圖4-5 每日負載與每日平均溫度比較圖 -------------------------------- 42
圖4-6 兩月份每日負載與每日平均溫度比較圖 -------------------------- 43
圖4-7 1992年全年每日負載與前日負載差異量對應圖 ------------------- 44
圖4-8 1992年全年每日負載與前兩日負載差異量對應圖 -------------- 45
圖4-9 1992年全年每日負載與上週同一日負載對應圖 ------------------ 46
圖4-10 1991-1993 三年每日負載與前日負載差異量對應圖 --------- 47
圖4-11 1991-1993 三年每日負載與前兩日負載差異量對應圖 ----------- 48
圖4-12 1991-1993 三年每日負載與上週同日負載差異量對應圖 -------- 49
圖5-1 94年非遞歸的與遞歸的測試誤差 ------------------------------ 53
圖5-2 95年非遞歸的與遞歸的測試誤差 ----------------------------- 54
圖5-3 94與95年非遞歸測試誤差比較圖 ---------------------------- 55
圖5-4 94與95非遞歸的測試誤差百分比 ---------------------------- 56

參 考 文 獻
[1] Christiaanse W. R., “Short term load forecasting using general exponential smoothing,” IEEE Trans. on Power Applications and Systems, Vol. PAS-90, No. 2, pp. 900-910, 1972.
[2] Gunst R. F. and Mason R. L., Regression analysis and its applications: A data-oriented approach, Dekker, New York, 1980.
[3] Papalexopoulos A. D. and Hesterberg T. C., “A regression-based approach to short-term system load forecasting,” IEEE Trans. on Power Systems, PWRS, Vol. 5, No. 4, pp. 1535-1544, 1990.
[4] Ho K. L., Hsu Y. Y., Chen C. F., Lee T. E., Liang C. C., Lai T. S., and Chen K. K., “Short term load forecasting of Taiwan power system using a knowledge-based expert system,” IEEE Trans. on Power Systems, Vol. 5, pp. 1214-1221, 1990.
[5] Hagan M. and Klein R., “Off-line and adaptive Box and Jenkins models for load forecasting,” Proceedings of Lawrence Systems and Decision Science, Berkeley, 1977.
[6] Hagan M. and R. Klein, “On-line maximum likelihood estimation for load forecasting,” IEEE Trans. on Systems, Man, and Cybernetics, Vol. SMC-8, No. 9, pp. 711-715, 1978.
[7] Huang S. R., “Short-term load forecasting using threshold autoregressive models,” IEE Proc. Electric Power Application, Vol. 144, No. 5, pp. 477-481, 1997.
[8] Hagan M. and Behr S. M., “The time series approaches to short-term load forecasting,” IEEE Trans. on Power Systems, PWRS, Vol. 2, pp. 785-791, 1987.
[9] Heydt G., Khotanzad A. and Farahbakhshian N., “A method for the forecasting of the probability density function of power system loads,” IEEE Trans. on Power Applications and Systems, Vol. PAS-100, No. 2, pp. 5002-5010, 1981.
[10] Lu Q. C., Grady W. M., Crawford M. M. and Anderson G. M., “An adaptive nonlinear predictor with orthogonal escalator structure for short-term load forecasting,” IEEE Trans. on Power Systems, Vol. PWRS-4, No. 1, pp. 158-165, 1989.
[11] Bakirtzis A. G., Peprldls V., Klartzis S. J., Alezladls M. C. and Malssls A. H., “A neural network short term load forecasting model for the Greek power systems,” IEEE Trans. on Power Systems, Vol. 11, No. 2, pp. 858-863, 1996.
[12] Connor J., Atlas L. E. and Martin D., “Recurrent neural networks and load forecasting,” Proc. of First International Forum on Applications of Neural Networks to Power System, pp. 211-215, 1991.
[13] Dillon T. S., Sestito S. and Leuang S., “Short term load forecasting using an adaptive neural network,” International Journal of Electrical Power & Energy Systems, Vol. 13, No. 4, pp. 186-192, 1991.
[14] Chen S. T., Yu D. C. and Moghaddamjo A. M., “Weather sensitive short term load forecasting using non-fully connected artificial neural networks,” IEEE Trans. on Power Systems, Vol. 7, No. 3, pp. 1098-1105, 1992.
[15] Khotanzad A., Hwang R. C., Abaye A. and Maratukulam D., “An adaptive modular artificial neural network hourly load forecaster and its application at electric utilities,” IEEE Trans. on Power Systems, Vol. 10, No. 3, pp. 1716-1722, 1995.
[16] Chow M. Y., Zhu J. and Tram H., “Application of fuzzy multi-objective decision making in spatial load forecasting,” IEEE Trans. on Power Systems, Vol. 13, No. 3, pp. 1185-1190, 1998.
[17] Daneshdoost M., Lotfalian M., Bumroonggit G. and Ngoy J. P., “Neural network with fuzzy set-based classification for short-term load forecasting,” IEEE Trans. on Power Systems, Vol. 13, No. 4, pp. 1386-1391, 1998.
[18] Dash P. K., Satpathy H. P. and Liew A. C., “A real-time short-term peak and average load forecasting system using a self-organizing fuzzy neural network,” Engineering Applications of Artificial Intelligence, Vol. 11, pp. 307-316, 1998.
[19] Hwang R. C., Huang H. C. and Hsieh J. G., “Short-term power load forecasting by neural network with modified back-propagation learning algorithm,” IEEE Winter Power Meeting, Singapore, 2000.
[20] 王進德. 蕭大全 , “類神經網路與模糊控制理論入門”,全華科技圖書股份有限公司,1999.