山东大学学报 (工学版) ›› 2024, Vol. 54 ›› Issue (4): 86-94.doi: 10.6040/j.issn.1672-3961.0.2023.287
王凤娟1,王语睿2,卫兰3,4*,范存群3,4,徐晓斌2
WANG Fengjuan1, WANG Yurui2, WEI Lan3,4*, FAN Cunqun3,4, XU Xiaobin2
摘要： 针对环境大数据在智慧城市应用中的实时性和准确性问题,提出一种基于自适应线性模型的环境数据预测算法。根据气象数据的实时变化情况对模型进行训练,自适应调整训练窗口大小,并在训练态与预测态之间动态实时切换,使模型具有较强的适应环境的能力。该算法具有较低的时延和较小的计算开销,可以在传感器节点上直接部署,满足数据预测的实时性需求。在真实环境数据集的基础上构建仿真试验,相比固定窗口模型,该算法数据预测误差降低17.4%以上,环境数据采集能耗降低80%以上,平均时延降低超过50%;相比已有的机器学习算法,训练及预测时间降低37%以上。
中图分类号:
| [1] EI M O, RACHID S, ABDELLAH C, et al. 6G enabled smart environments and sustainable cities: an intelligent big data architecture[C] //Proceedings of the 2022 IEEE 95th Vehicular Technology Conference(VTC2022-Spring). Helsinki, Finland: IEEE, 2022: 1-5. [2] SHIDROKH G, MOHAMMAD H A, SEYED A S, et al. An IoT-based prediction technique for efficient energy consumption in buildings[J]. IEEE Transactions on Green Communications and Networking, 2021, 5(4): 2076-2088. [3] LI J Z, LI G H, GAO H. Novel ε -approximation to data streams in sensor networks[J]. IEEE Transactions on Parallel and Distributed Systems, 2015, 26(6): 1654-1667. [4] HUNG V, JEUNG. H, ABERER K. Anevaluation of model-based approaches to sensor data compression[J]. IEEE Transactions on Knowledge and Data Engineering, 2013, 25(11): 2434-2447. [5] ZISIS I P, TIAN Y L. Prediction ofsea ice motion with convolutional long short-term memory networks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(9): 6865-6876. [6] WANG W N, LIU W Q, CHEN H. Information granules-based BP neural network for long-term prediction of time series[J]. IEEE Transactions on Fuzzy Systems, 2021, 29(10): 2975-2987. [7] DYLAN P, WANG N, SHEN S H. Energy demand prediction with optimized clustering-based federated learning[C] //Proceedings of the 2021 IEEE Global Communications Conference(GLOBECOM). Madrid, Spain: IEEE, 2021: 1-6. [8] JIANG Y S, NIU S T, ZHANG K, et al. Spatial-temporal graph data mining for IoT-enabled air mobility prediction[J]. IEEE Internet of Things Journal, 2022, 9(12): 9232-9240. [9] YAN B W, WANG G J, YU J G, et al. Spatial-temporal Chebyshev graph neural network for traffic flow prediction in IoT-based ITS[J]. IEEE Internet of Things Journal, 2022, 9(12): 9266-9279. [10] VINIT K, MOHAMMADREZA B, NICHOLE M, et al. DeepTrack: lightweight deep learning for vehicle trajectory prediction in highways[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(10): 18927-18936. [11] ZENG Y Y, ZHOU S J, XIANG K. Online-offline interactive urban crowd flow prediction toward IoT-based smart city[J]. IEEE Transactions on Services Computing, 2022, 15(6): 3417-3428. [12] 万晨, 李文中, 丁望祥, 等. 一种基于自演化预训练的多变量时间序列预测算法[J]. 计算机学报, 2022, 45(3): 513-525. WAN Chen, LI Wenzhong, DING Wangxiang, et al. A multivariate time series forecasting algorithm based on self-evolution and pretraining[J]. Chinese Journal of Computers, 2022, 45(3): 513-525. [13] LI Z, KOVACHKI N, AZIZZADENSHELI K, et al.Fourier neural operator for parametric partial differential equations[C] //Proceedings of the 9th International Conference on Learning Representations(ICLR). [S.l.] : ICLR, 2021: 1-6. [14] XU X B, ZHAO H, YAO H P, et al. A blockchain-enabled energy-efficient data collection system for UAV-assisted IoT[J]. IEEE Internet of Things Journal, 2021, 8(4): 2431-2443. [15] AROOSA H, JOHN V, ARIS L, et al. Toward QoS prediction based on temporal transformers for IoT applications[J]. IEEE Transactions on Network and Service Management, 2022, 19(4): 4010-4027. [16] 杨鹏史, 丁卉, 陈同, 等. 基于局部加权线性回归的城市公交车排放能耗预测[J]. 中山大学学报(自然科学版), 2019, 58(6): 111-118. YANG Pengshi, DING Hui, CHEN Tong, et al. Estimation of emissions or electricity consumptions of urban buses based on locally weighted linear regression[J]. Acta Scientiarum Naturalium Universitatis SunYatseni, 2019, 58(6): 111-118. [17] 郭松亮, 闫鹏君, 鄂浩坤. 基于ARIMA模型的北京市全社会用电量短期预测[J]. 北京信息科技大学学报(自然科学版), 2020, 35(5): 93-96. GUO Songliang, YAN Pengjun, E Haokun. Short-term forecast of the total electricity consumption in Beijing based on ARIMA model[J]. Journal of Beijing Information Science & Technology University(Natural Science Edition), 2020, 35(5): 93-96. [18] 唐继强, 钟鑫伟, 刘健, 等. 基于时间序列季节分类模型的轨道交通客流短期预测[J]. 重庆交通大学学报(自然科学版), 2021, 40(7): 31-38. TANG Jiqiang, ZHONG Xinwei, LIU Jian, et al. Short term forecast of rail transit passenger flow based on time series seasonal classification model[J]. Journal of Chongqing Jiaotong University(Natural Science Edition), 2021, 40(7): 31-38. [19] 马乐乐, 刘向杰. 非线性快速批次过程高效迭代学习预测函数控制[J]. 自动化学报, 2022, 48(2): 515-530. MA Lele, LIU Xiangjie. A high efficiency iterative learning predictive functional control for nonlinear fast batch processes[J]. Acta Automatica Sinica, 2022, 48(2): 515-530. |
|
