基于灰色预测模型的参数寻优方法及能源预测应用

A method and application study of optimizing key parameters of gray prediction model based on emperor butterfly algorithm

能源电力是中国实现双碳目标的关键领域,精确预测未来能源供需及碳排放量,有利于制定低碳转型的可行路径。灰色预测模型GM(1,1)是在能源预测领域应用最为广泛的一种动态预测模型,但其对原始数据要求较高,且GM(1,1)发展系数α较大时,模型可能失效,另一方面,GM(1,1)的另一关键参数灰作用量u直接决定模型预测精度,如果能够找到更优的u值代入模型进行预测,则模型的精度将会显著提高,考虑到这些问题,本文将一种在实际优化问题中表现优良的新颖群体智能算法帝王蝶优化算法(Monarch Butterfly Optimization,MBO)引入到灰色预测模型关键参数α和u的寻优过程,提出了一种全新的灰色-帝王蝶优化预测模型,实现对天津能源供需及碳排放的准确预测,并依据预测结果制定天津2030年碳达峰的低碳转型路径,通过与已有经典文献方法与预测数据的对比,证实了本文所提出的灰色-帝王蝶优化预测模型的有效性和优越性。

Energy and electricity are the key area for China to achieve its dual-carbon goals.Precisely predicting future energy supply and demand and carbon emissions are beneficial for formulate a feasible path for low-carbon transition.The gray prediction model GM(1,1)is the most widely used dynamic prediction model in the field of energy forecasting,but it has higher requirements for original data and the model may fail when the development coefficient of GM(1,1)is large.On the other hand,another key parameter of GM(1,1),the gray effect u,directly determines the prediction accuracy of the model.If a better value of u can be found to be substituted into the model for prediction,the accuracy of the model will be significantly improved.Taking these into account problem,this paper introduced into the optimization process of the gray prediction model a novel swarm intelligence algorithm,namely the Monarch Butterfly Optimization(MBO)that performs well in actual optimization problems.The newly proposed gray-monarch butterfly prediction model can achieve accurate predictions of Tianjin’s energy supply and demand and carbon emissions.Based on the prediction results,a low-carbon transition path for Tianjin’s carbon peak in 2030 was formulated.Compared with existing classic literature methods and prediction data,the effectiveness and superiority of the grey-monarch butterfly optimized forecasting model proposed in this paper were discussed.