Academic Journal of Computing & Information Science, 2021, 4(2); doi: 10.25236/AJCIS.2021.040203.
Chaoju Hu1, *, Yunpeng Gao1
1North China Electric Power University, Baoding, China
*Corresponding author
In order to make the operation of optical fiber protection system more stable and improve the accuracy of time series prediction for a small amount of optical power data samples, this paper presents an ARIMA model prediction method based on improved wavelet decomposition. This method uses the improved wavelet decomposition is multistage discrete wavelet decomposition SWT and improved it. Different from the conventional method of decomposition and reconstruction of signals, this paper directly uses wavelet decomposition coefficient for modeling, which simplifies the process of input data construction and reduces the data loss caused by data reconstruction. ARIMA is autoregressive integrated moving Average model. Building a combination model and using the data to conduct simulation experiments. Experimental results verify that the prediction accuracy of this optimization model is higher than that of the ARIMA model alone and prove that this model is superior to a small amount of sample optical power data.
the time series, wavelet decomposition, ARIMA
Chaoju Hu, Yunpeng Gao. Prediction of Optical Power Data Based on Optimized ARIMA Model. Academic Journal of Computing & Information Science (2021), Vol. 4, Issue 2: 11-19. https://doi.org/10.25236/AJCIS.2021.040203.
[1] Hanchuan Fan. (2013)Application of Optical Fiber Line Protection System in Communication Network. Practical Electronics, 12, 146-146.
[2] Hua Qin, Gang Li, Jian Yang, et al. (2020) Application of uninterpolated Loss-type optical fiber protection system in electric Power Communication Network. Inner Mongolia Science Technology & Economy, 5, 97-99.
[3] Li Yumei. (2014)Security Protection of railway optical communication System by using intelligent optical fiber protection module. Technology Innovation and Application, 26, 72-72.
[4] Hua Qin, Gang Li, Jian Yang, et al. (2020) Application of uninterpolated Loss-type optical fiber protection system in electric Power Communication Network. Inner Mongolia Science Technology & Economy, 5, 97-99.
[5] Amin M A A, Hoque M A, et al. (2019) Comparison of ARIMA and SVM for Short-term Load Forecasting. 9th Annual Information Technology, Electromechanical Engineering and Microelectronics Conference (IEMECON). Jaipur, India, 1-6.
[6] W. Cheng, Y. Zhou, Y. Guo, et al. (2019) Research on prediction method based on ARIMA-BP combination model. Porc of the 3rd International Conference on Electronic Information Technology and Computer Engineering (EITCE). Xiamen, China, 663-666.
[7] CN Babu, BE Reddy. (2012)Prediction data mining at global mean temperature using variants of ARIMA model. International Conference on Progress in Engineering Science and Management, 256-260.
[8] Xiang Li, Ling Peng, Jing Shao, et al. (2016)Study on air pollution prediction based on wavelet decomposition and ARMA Model. Environmental Engineering, 8, 110-113.
[9] Mallat S G. (1989) A theory for multiresolution signal decomposition: The wavelet representation. Pattern Analysis and Machine Intelligence. IEEE Transactions on, 11, 674-693.
[10] Hao Fu, Shengda Wang, Shan Jiang, et al. (2019) Optical power prediction method based on ARMA-LSTM. Optical Communication Technology, 43, 20-23.
[11] Shiguang Peng, Xianhui Geng. (2020)Based on the ARIMA and GM (1, 1) model of China's soybean imports and imports of prediction. Soybean science, 8, 1-13.
[12] Chadsuthi S, Iamsirithaworn S, Triampo W, et al. (2015)Modeling seasonal influenza transmission and its association with climate factors in Thailand using time-series and ARIMAX anal yses. Comput Math Methods Med, 436495.
[13] Liu L, Luan RS, Yin F, et al. (2016) predicting the incidence of hand, foot and mouth disease in Sichuan Province, China using the ARIMA model. EPidemiol Infect, 144, 144-151.
[14] T Wang, J Liu, Y Zhou, et al. (2016)Prevalence of hemorrhagic fever with renal syndrome in Yi yuan County, China, 2005-2014. BMC Infect Dis, 16, 69.
[15] C Narendra Babu, B Eswara Reddy. (2012)Predictive data mining of global mean temperatures using variants of the ARIMA model. Porc of IEEE International Conference on Progress in Engineering, Science and Management (ICAESM-2012). Tamil Nadu, Nagapattinam, 256-260.
[16] Z Zou, X Wu, Z Zhao, et al. (2016) Short-term Power Load forecasting based on the combination of BP Neural Network and ARIMA. Porc of the IEEE 4th Congress on Information Technology and Electromechanical Engineering (ITOEC). Chongqing, China, 1671-1674.