2018 Vol.1 Aug No.4

• Title: Short-term power load forecasting model analysis of neural network based on big data technology
• Name: Louisa Margaret
• Company: Chartered Institute of Technology,Singapore
• Abstract:

  Conventional short-term power load forecasting model can forecast a small range of short-term electricity, the analysis of a wide range of short-term electricity, it exists the shortage of the prediction deviation sex is bigger, therefore puts forward neural network based on the technology of large data short-term power load forecasting model analysis. Determine the data collection path of power short-term load influencing factors, and process the data of power grid load and influencing factors, so as to complete the analysis of the change rule of power short-term load based on big data. Modeling based on BP neural network and PSO algorithm, optimization of PSO neural network algorithm, and complete power short-term load forecasting based on the large data analysis, the implementation technology based on large data analysis of the neural network short-term power load forecasting model. Experimental data show that the proposed load forecasting model of big data neural network is 23.48% lower than the conventional model, which is suitable for short-term power consumption analysis in different areas.

• Keyword: Big data technology; Short neural network; Periodic power load; Prediction model;
• DOI: 10.12250/jpciams2018040115
• Citation form: Louisa Margaret.Short-term power load forecasting model analysis of neural network based on big data technology[J]. Computer Informatization and Mechanical System, 2018, vol. 1, pp. 22-27.

[1] Zhang Shaoping, Xu Xiaozhong, Dai Junwei. Research on short-term gas load optimization prediction of natural gas pipeline network[J]. Computer Simulation, 2016, 33(3): 305-309.
[2] LI Li, YANG Shengfeng, QIU Jinpeng, et al. Simulation study of short-term load forecasting method for power system power supply[J]. Computer Simulation, 2017, 34(1): 104-108.
[3] Wang Jiquan, Wang Fulin, Dong Zhigui, et al. Power Load Forecasting Based on Improved BP Neural Network[J]. Mathematics in Practice and Theory, 2017, 47(9): 276-284.
[4] Su Xueneng, Liu Tianqi, Cao Hongqian, et al. Short-term load forecasting method based on Hadoop architecture for multiple distributed BP neural networks[J]. Proceedings of the CSEE, 2017, 37(17): 4966-4973.
[5] Wu Runze, Bao Zhengrui, Wang Wenbiao, et al. Short-term power load forecasting method based on pattern matching under Hadoop architecture[J]. Transactions of China Electrotechnical Society, 2018, 33(7): 1542-1551.
[6] Huang Yuanyu, Mao Wei, Yan Ningna. Short-term electric load forecasting based on Kohonen clustering wavelet packet decomposition and ELM[J]. Journal of Natural Science of Hunan Normal University, 2016, 39(4): 53-58.
[7] Zhu Jixing, Wang Chongbin, Wang Tianzhi, et al. Adaptive power load forecasting method based on multi-source data[J]. Hydropower Science, 2017(12): 200-203.
[8] Meng Anbo, Hu Jiwu, Liu Xiangdong. Load forecasting model based on vertical and horizontal crossover algorithm for optimization neural network[J]. Power System Protection and Control, 2016, 44(7): 102-106.
[9] Dong Hao, Li Mingxing, Zhang Shuqing, et al. Short-term electric load forecasting based on kernel principal component analysis and extreme learning machine[J]. Journal of Electronic Measurement and Instrument, 2018(1).
[10] Xiao Bai, Liu Qingyong, Niu Qiang, et al. Spatial Load Forecasting Method for RBF Neural Networks Based on Analysis of Cell Load Characteristics[J]. Power System Technology, 2018, 42(1):301-307.