煤炭价格的准确预测对化解能源价格风险有着重要意义,针对煤炭价格预测的问题,开展了基于集成模型的煤炭价格多步预测研究。本研究分析了影响煤炭价格的主控因素,并建立了数据集;将粒子群优化算法(Particleswarmoptimization,PSO)和长短期记忆模型(LongShort-TermMemory,LSTM)有效集成,建立了一种基于PSO-LSTM的多参量多步预测模型。利用多参量多步预测模型调用数据集进行了曹妃甸港煤炭价格预测,结果表明:基于PSO-LSTM的多参量多步预测模型预测效果优于基于BP、LSTM的预测模型;其预测价格与实际价格的MAPE、R2值分别为0.025、0.908,能够为煤炭市场的科学管控提供帮助。

Accurate prediction of coal prices is of great significance to defuse energy price risks. Aiming at the problem of coal price forecasting, a multi-step forecasting study of coal price based on ensemble model was carried out. The main controlling factors affecting coal prices were analyzed, and a data set was established; Particle swarm optimization (PSO) and Long Short-Term Memory (LSTM) were effectively integrated, and a multi-parameter multi-step prediction model based on PSO-LSTM was established. Using the multi-parameter and multi-step forecasting model, the data set was called to forecast the coal price of Caofeidian Port, the results show that the forecasting effect of the multi-parameter and multi-step forecasting model based on PSO-LSTM is better than the forecasting model based on BP and LSTM. Its MAPE and R2 values of predicted price and actual price are 0. 025 and 0. 908, respectively, indicating that, the model can provide help for scientific control of coal market.

10.11799/ce202308034

郝 伟, 边萌春. 基于集成模型的煤炭价格多步预测研究 [J]. 煤炭工程, 2023, 55(8): 187-192.