改进FA优化LSTM的时序预测模型

doi:10.3778/j.issn.1002-8331.2108-0314

摘要/Abstract

摘要： 为了提高时序预测精度，提出了一种改进萤火虫算法（firefly algorithm，FA）优化LSTM的时序预测模型（GAFA-LSTM）。针对FA因种群多样性弥散陷入局部最优，影响寻优效果的问题，提出了种群多样性增加机制。FA在完成初始化后加入种群多样性的计算；在满足多样性增加机制的条件下，引入自适应多样性增加机制，有效平衡进化过程中对种群多样性的需求；在迭代后期加入自适应游动参数来避免局部震荡。将改进后的FA用于LSTM模型输入参数的优化，以提高LSTM模型输入参数的准确性。实验部分对改进FA进行了改进效果测试，对GAFA-LSTM模型进行了模型验证。结果表明改进FA具有较好的寻优效果，GAFA-LSTM预测模型较其他预测模型拟合程度与预测精度都有不同程度的提高。

关键词: 萤火虫算法, 时间序列预测, 种群多样性, 长短期记忆神经网络（LSTM）, 多样性增加机制

Abstract: In order to improve the accuracy of time series prediction, a time series prediction model（GAFA-LSTM）, which is improved by firefly algorithm（FA） and optimized LSTM, is proposed. Aiming at the problem that FA falls into a local optimum due to the dispersion of population diversity, which affects the optimization effect, a mechanism for increasing population diversity is proposed. First, FA adds the calculation of population diversity after initialization; secondly, it introduces an adaptive diversity increase mechanism under the condition of satisfying the diversity increase mechanism to effectively balance the demand for population diversity in the evolutionary process; finally, in the later iteration, swimming parameters are added to avoid local oscillations. The improved FA is used to optimize the input parameters of the LSTM model to improve the accuracy of the input parameters of the LSTM model. In the experimental part, the improvement effect of the improved FA is tested, and the GAFA-LSTM model is verified. The results show that the improved FA has a better optimization effect, and the GAFA-LSTM prediction model has improved the degree of fit and prediction accuracy to varying degrees compared with other prediction models.

Key words: firefly algorithm, time series forecast, population diversity, long-term and short-term memory network（LSTM）, mechanism of diversity increase

张忠林, 张艳. 改进FA优化LSTM的时序预测模型[J]. 计算机工程与应用, 2022, 58(11): 125-132.

ZHANG Zhonglin, ZHANG Yan. Improved FA Optimizing LSTM Time Series Prediction Model[J]. Computer Engineering and Applications, 2022, 58(11): 125-132.

参考文献

[1] CAO W，HU L，CAO L B.Deep modeling complex couplings within financial markets[C]//Proceedings of AAAI，2015：2518-2524.
[2] SHAO H X，SOONG B H.Traffic flow prediction with long short-term memory networks（LSTMs）[C]//Proceedings of 2016 IEEE Region 10 Conference.Piscataway：IEEE，2016：2986-2989.
[3] DU Y，WANG W，WANG L.Hierarchical recurrent neural network for skeleton based action recognition[C]//Proceedings of CVPR，2015：1110-1118.
[4] AMINI M H，KARGARIAN A，KARABASOGLU O.ARIMA-based decoupled time series forecasting of electric vehicle charging demand for stochastic power system operation[J].Electric Power Systems Research，2016，140：378-390.
[5] KRISTINA D，WOLFRAM-MANFRED L.Time series prediction with parallel evolutionary artificial neural networks[C]//Proceedings of ICDM，2007：10-15.
[6] JIE L，ENRICO Z.SVM hyperparameters tuning for recursive multi-step-ahead prediction[J].Neural Computing and Applications，2017，28（12）：3749-3763.
[7] LI X，BAI R B.Freight vehicle travel time prediction using gradient boosting regression tree[C]//Proceedings of ICMLA，2016：1010-1015.
[8] HOCHREITER S，SCHMIDHUBER J.Long short-term memory[J].Neural Computation，1997，9（8）：1735-1780.
[9] 宋刚，张云峰，包芳勋，等.基于粒子群优化LSTM的股票预测模型[J].北京航空航天大学学报，2019，45（12）：2533-2542.
SONG G，ZHANG Y F，BAO F X，et al.Stock prediction model based on particle swarm optimization LSTM[J].Journal of Beijing University of Aeronautics and Astronautics，2019，45（12）：2533-2542.
[10] 凌晓，徐鲁帅，高甲程，等.基于IFA-BPNN的长输管道外腐蚀速率预测[J].表面技术，2021，50（4）：285-293.
LING X，XU L S，GAO J C，et al.Prediction of external corrosion rate of long-distance pipeline based on IFA-BPNN[J].Surface Technology，2021，50（4）：285-293.
[11] KHAJEHZADEH M，TAHA M R，ESLAMI M.A new hybrid firefly algorithm for foundation optimization[J].National Academy Science Letters，2013，36（3）：279-288.
[12] 李春祥，丁晓达，叶继红.基于混合蚁群和粒子群优化LSSVM的脉动风速预测[J].振动与冲击，2016，35（21）：131-136.
LI C X，DING X D，YE J H.Pulsating wind speed prediction based on hybrid ant colony and particle swarm optimization LSSVM[J].Journal of Vibration and Shock，2016，35（21）：131-136.
[13] 马莹，王怀晓，刘贺，等.一种新的自适应量子遗传算法研究[J].计算机工程与应用，2018，54（20）：99-103.
MA Y，WANG H X，LIU H，et al.Research on self-adaptive quantum genetic algorithm[J].Computer Engineering and Applications，2018，54（20）：99-103.
[14] FISTER J I，FISTER I，YANG X S，et al.A comprehensive review of firefly algorithms[J].Swarm and Evolutionary Computation，2013，13：34-46.
[15] XIA X W，LING G，GUO L，et al.A hybrid optimizer based on firefly algorithm and particle swarm optimization algorithm[J].Journal of Computational Science，2018，26：488-500.
[16] 李红亚，彭昱忠，邓楚燕，等.GA与PSO的混合研究综述[J].计算机工程与应用，2018，54（2）：20-28.
LI H Y，PENG Y Z，DENG C Y，et al.Review of hybrids of GA and PSO[J].Computer Engineering and Applications，2018，54（2）：20-28.
[17] 张松灿，普杰信，司彦娜，等.蚁群算法在移动机器人路径规划中的应用综述[J].计算机工程与应用，2020，56（8）：10-19.
ZHANG S C，PU J X，SI Y N，et al.Survey on application of ant colony algorithm in path planning of mobile robot[J].Computer Engineering and Applications，2020，56（8）：10-19.
[18] 张静，高尚.基于轮盘赌反向选择机制的果蝇优化算法[J].计算机与数字工程，2020，48（7）：1595-1600.
ZHANG J，GAO S.Fruit fly optimization algorithm based on roulette reverse selection mechanism[J].Computer and Digital Engineering，2020，48（7）：1595-1600.
[19]　张峰峰，张欣，陈龙，等.采用改进遗传算法优化神经网络的双目相机标定[J].中国机械工程，2021，32（12）：1423-1431.
ZHANG F F，ZANG X，CHEN L，et al.Binocular camera calibration based on BP neural network optimized by improved genetic algorithm[J].China Mechanical Engineering，2021，32（12）：1423-1431.
[20]　FANG Q C.Modeling of rock fragmentation by firefly optimization algorithm and boosted generalized additive model[J].Neural Computing and Applications，2021，33（8）：3503-3519.
[21]　张忠林，费珊珊，任晓岚，等.基于CNN-LSTM的气象因素与高血压门诊人数关系[J].中华疾病控制杂志，2019，23（9）：1126-1131.
ZHANG Z L，FEI S S，REN X L，et al.Study on the relationship between meteorological factors and the number of hypertension outpatients based on CNN-LSTM[J].Chinese Journal of Disease Control & Prevention，2019，23（9）：1126-1131.
[22]　GNANASEKAR T S，SAMIAPPAN D.Impact of hybridized rider optimization with cuckoo search algorithm on optimal VANET routing[J].International Journal of Communication Systems，2021，34（16）.
[23] HAFEEZ G，KHAN I，JAN S，et al.A novel hybrid load forecasting framework with intelligent feature engineering and optimization algorithm in smart grid[J].Applied Energy，2021，299：117178.