A Short-term Prediction of Air Traffic Flow Based on a Wavelet-optimized GRU-ARMA Model
-
摘要: 空中交通流量短时预测是空中交通管理的基础，是有效缓解交通拥堵问题的前提。为提高空中交通流量短时预测的精度，减小空中交通管制员的工作压力，提出了基于小波优化GRU-ARMA的空中交通流量短时预测方法。在传统预测方法的基础上，通过小波变换对原始流量数据进行多尺度分解，提取不同频率交通流量的细节特征，对原始流量数据进行预处理。同时，根据小波变换，在低频处将频率细分作为趋势项，高频处将时间细分作为噪声项。其中，趋势项反映了空中交通流量随时间演化的整体趋势性，噪声项反映了随机因素对空中交通流量的综合影响。使用门控循环单元（GRU）神经网络模型预测趋势项，自回归滑动平均模型（ARMA）模型预测噪声项；将趋势项和噪声项的预测值叠加，得到最终的短时流量预测值。误差分析表明，该方法在每个预测点上的误差保持在2%左右，预测效果稳定；而直接采用原始流量数据进行预测的GRU、BiLSTM、CNN-LSTM神经网络模型及单一的ARMA模型，每个点的预测误差在5%~37.14%之间。与GRU、BiLSTM、CNN-LSTM神经网络模型相比，该模型的预测精度分别提高了3.02%，5.39%，5.05%。Abstract: A short-term prediction of air traffic flow is important for air traffic management, and effectively reduce traffic congestion.To improve the accuracy of the short-term prediction and reduce the workload of air traffic controllers, a wavelet-optimized GRU-ARMA based model is proposed.Based on traditional prediction methods, the originaldata of air traffic flow is decomposed by multi-scale wavelet transform. The detailed features of traffic flow with different frequenciesare extracted. Moreover, by using wavelet transform, component at low frequencies is subdivided as trend term, and time at high frequencies as noise term.Among them, the trend term represents the overall evolution trends of air traffic flow over time, while the noise term describes the comprehensive influences of random factors on air traffic flow. The gated recurrent unit (GRU) neural network and the autoregressive moving average (ARMA) model are used to predict the trend and noise terms, respectively.The prediction values of trend and noise terms are superimposed to obtain the final value of short-termprediction. An error analysis shows that the method maintains a stable prediction of about 2% at each prediction point. In contrast, the models that directly use raw traffic data for prediction (i.e. GRU, BiLSTM, CNN-LSTM neural network models) and the single ARMA model have prediction errors ranging from 5% to 37.14%.Compared to the GRU, BiLSTM and CNN-LSTM neural network models, the prediction accuracy of the proposed model is increased by 3.02%, 5.39% and 5.05%, respectively.
-
图 2 基于小波优化GRU-ARMA模型的空中交通流量短时预测流程
Figure 2. Short term air traffic flow frediction process based on Wavelet-Optimized GRU-ARMA model
图 8 小波优化GRU-ARMA预测结果
Figure 8. Prediction results of the wavelet-optimized GRU-ARMA model
表 1 不同分解层数信噪比对比
Table 1. Comparison of different decomposition layers of signal-to-noise ratio
小波基函数 分解层数 信噪比 bior2.2 3 24.195 0 4 24.175 6 5 24.174 6 db3 3 21.701 3 4 21.663 6 5 21.639 2 sym4 3 22.383 5 4 22.336 5 5 22.332 5 
下载: 导出CSV
表 2 不同置信区间对应的临界ADF值
Table 2. Corresponding critical ADF value under different confidence intervals
置信区间 临界ADF值 99% -3.430 9 95% -2.861 8 90% -2.566 9
下载: 导出CSV
表 3 5种模型的评价指标
Table 3. Evaluation indexes of four models
预测模型 评价指标 RMSE MAE MAPE/% 小波优化GRU-ARMA 1.338 0.958 1.74 GRU 3.234 2.542 4.76 BiLSTM 4.996 3.958 7.13 CNN-LSTM 4.601 3.667 6.79 ARMA 5.208 3.33 6.04
下载: 导出CSV
-
[1] 王剑辉, 朱晓波, 夏正洪, 等. 基于知识图谱的国内空中交通管理研究可视化分析[J]. 交通信息与安全, 2019, 37(6): 11-19. doi: 10.3963/j.issn.1674-4861.2019.06.002WANG J H, ZHU X B, XIA Z H, et al. A visualization analysis of domestic air traffic management based on mapping knowledge domains[J]. Journal of Transport Information and Safety, 2019, 37(6): 11-19. (in Chinese) doi: 10.3963/j.issn.1674-4861.2019.06.002 [2] 陈恺, 曾培彬, 蔡浩. 改进型空中交通流量预测算法的验证与实现[J]. 计算机测量与控制, 2020, 28(12): 267-272. https://www.cnki.com.cn/Article/CJFDTOTAL-JZCK202012055.htmCHEN K, ZENG P L, CAI H. Verification and implementation of improved air traffic flow prediction method[J]. Computer Measurement and Control, 2020, 28(12): 267-272. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JZCK202012055.htm [3] 毛阿芳. 基于数据挖掘的四维航迹预测技术研究[D]. 唐山: 华北理工大学, 2021.MAO A F. Research on 4D track prediction technology based on data mining[D]. Tangshan: North China University of Science and Technology, 2021. (in Chinese) [4] PANG Y, LIU Y. Probabilistic aircraft trajectory prediction considering weather uncertainties using dropout as bayesian approximate variational inference[C]. AIAA Scitech 2020 Forum, Orlando, FL: AIAA, 2020. [5] LI S M, XU X H, MENG L H. Flight conflict fo recasting based on chaotic time series[J]. Transactions of Nanjing University of Aeronautics and Astronautics, 2012, 29 (4): 388-394. [6] CONG W, HU M H. Chaotic characteristic analysis of air traffic system[J]. Transactions of Nanjing University of Aeronautics and Astronautics: 2014, 31(6): 636-642. [7] 王超, 郑旭芳, 王蕾. 交汇航路空中交通流的非线性特征研究[J]. 西南交通大学学报, 2017, 52(1): 171-178. doi: 10.3969/j.issn.0258-2724.2017.01.024WANG C, ZHENG X F, WANG L. Research on nonlinear characteristics of air traffic flows on converging air routes[J]. Journal of Southwest Jiaotong University, 2017, 52(1): 171-178. (in Chinese) doi: 10.3969/j.issn.0258-2724.2017.01.024 [8] 王飞. 空中交通流非线性分形特征[J]. 西南交通大学学报, 2019, 54(6): 1147-1154. https://www.cnki.com.cn/Article/CJFDTOTAL-XNJT201906004.htmWANG F. Nonlinear fractal characteristics of air traffic flow[J]. Journal of Southwest Jiaotong University, 2019, 54 (6): 1147-1154. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XNJT201906004.htm [9] 王飞. 基于Hurst指数的空中交通流长相关性实证分析[J]. 中国民航大学学报, 2019, 37(2): 1-4. doi: 10.3969/j.issn.1674-5590.2019.02.001WANG F. Empirical analysis on air traffic flow long phase correlation based on Hurst exponent[J]. Journal of Civil Aviation University of China, 2019, 37(2): 1-4. (in Chinese) doi: 10.3969/j.issn.1674-5590.2019.02.001 [10] 杨阳. 空中交通流量短期预测方法研究[D]. 天津: 中国民航大学, 2017.YANG Y. Research on short term forecasting method of air traffic flow[D]. Tianjin: Civil Aviation University of China, 2017. in Chinese [11] 王飞, 韩翔宇. 基于分形插值的空中交通流量短期预测[J/OL]. (2021-07)[2022-07-15]. http://kns.cnki.net/kcms/detail/11.1929.v.20210720.1106.016.html.WANG F, HAN X Y. Short-term prediction of air traffic flow based on fractal interpolation[J/OL]. (2021-07)[2022-07-15]. http://kns.cnki.net/kcms/detail/11.1929.v.20210720.1106.016.html. (in Chinese) [12] 张兆宁, 张莹莹, 冀姗姗. 基于GA-BP神经网络的空中交通网络流系统拥堵预测[J]. 中国民航大学学报, 2021, 39(3): 1-5. doi: 10.3969/j.issn.1674-5590.2021.03.001ZHANG Z N, ZHANG Y Y, JI S S, Congestion prediction of flow system of air traffic network based on GA-BP neural network[J]. Journal of Civil Aviation University of China, 2021, 39(3): 1-5. (in Chinese) doi: 10.3969/j.issn.1674-5590.2021.03.001 [13] 赵元棣, 陈俊夫, 刘泽宇, 等. 基于K近邻模型的空中交通流量短期预测[J]. 中国民航大学学报, 2017, 35(5): 1-5+11. doi: 10.3969/j.issn.1674-5590.2017.05.001ZHAO Y L, CHEN J F, LIU Z Y, et al. Short-term air traffic flow forecast based on K-nearest neighbor algorithm[J], Journal of Civil Aviation University of China, 2017, 35(5): 1-5+11. (in Chinese) doi: 10.3969/j.issn.1674-5590.2017.05.001 [14] 闫少华, 崔海洋, 张兆宁. 一种基于支持向量机的飞行冲突探测方法[J]. 安全与环境学报, 2021, 21(3): 1211-1217. https://www.cnki.com.cn/Article/CJFDTOTAL-AQHJ202103042.htmYAN S H, CUI H Y, ZHANG Z N, A flight conflict detection method based on support vector machine[J]. Journal of Safety and Environment, 2021, 21(3): 1211-1217. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-AQHJ202103042.htm [15] 李桂毅, 胡明华. 考虑航段相关性的航路拥挤态势多模型融合动态预测方法[J]. 交通运输系统工程与信息, 2018, 18 (1): 215-222. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201801033.htmLI G Y, HU M H, Multi-model fusion dynamic prediction method of enroute congestion situation with considering the correlation of air route segment[J]. Journal of Transportation System Engineering and Information Technology, 2018, 18 (1): 215-222. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201801033.htm [16] PANG Y, XU N, LIU Y. Aircraft trajectory prediction using LSTM neural network with embedded convolutional layer[C]. The Annual Conference of the PHM Society. Scottsdale, AZ, USA: PHM Society, 2019. [17] GUAN G, ZHOU Z, WANG J, et al. Machine learning aided air traffic flow analysis based on aviation big data[J]. IEEE Transactions on Vehicular Technology, 2020, 69(5): 4817-4826. doi: 10.1109/TVT.2020.2981959 [18] 尚然然. 基于数据挖掘的终端区短期流量预测技术研究[D]. 唐山: 华北理工大学, 2021.SHANG R R. Research on short-term traffic flow prediction technology in terminal area based on data mining[D]. Tangshan: North China University of Science and Technology, 2021. (in Chinese) [19] 徐一帆. 基于小波降噪技术的OPAX方法改进研究及应用[D]. 沈阳: 沈阳理工大学, 2020.XU Y F. Study and application of OPAX method based on wavelet denoising technology[D]. Shenyang: Shenyang Ligong University, 2020. (in Chinese) [20] 夏飞, 李明特. 联合BIC准则和多重注意力机制的空调能耗预测[J]. 低温与超导, 2022, 50(4): 81-87. https://www.cnki.com.cn/Article/CJFDTOTAL-DWYC202204014.htmXIA F, LI M T, Air conditioning energy prediction using combined BIC criterion and multiple attention mechanism[J]. Cryogenics and Superconductivity, 2022, 50(4): 81-87. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DWYC202204014.htm [21] 刘明, 王永瑜. Durbin-Watson自相关检验应用问题探讨[J]. 数量经济技术经济研究, 2014, 31(6): 153-160. https://www.cnki.com.cn/Article/CJFDTOTAL-SLJY201406011.htmLIU M, WANG Y Y. Exploring in Durbin-Watson autocorrelation test[J]. The Journal of Quantitative and Technical Economics, 2014, 31(6): 153-160. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-SLJY201406011.htm -
点击查看大图
图(10) / 表(3)
计量
- 文章访问数: 1024
- HTML全文浏览量: 447
- PDF下载量: 48
- 被引次数: 0