Autoregressive Integrated Moving Average (ARIMA) and seasonal ARIMA (SARIMA) models are common techniques that are widely used in analysing and forecasting stationary and seasonal time series data. The three essential steps involved to construct ARIMA are identification, estimation, and checking the validity of the model. The most critical step followed in constructing the ARIMA model is model identification. However, overcoming the difficult local optima problem for both ARIMA and SARIMA is still challenging as there is no appropriate method to solve it. In this paper, the proposed parallel GA-SARIMA model is used to solve the problem of local optima, where the genetic algorithm (GA) is used at the initial stage to identify the order and estimation of the parameters for SARIMA. The National Climate Data Centre (NCDC) time series dataset is used for testing the efficiency of the final parallel GA-SARIMA model to forecast the mean temperature of India from 2000 to 2017. The GA algorithm is successfully implemented to solve the optimization problems by introducing better solutions suitable for SARIMA models. The results of the study showed that the implementation of the combined approach of parallel GA and SARIMA enhances the prediction accuracy of the model. The parallel GA-SARIMA method is particularly robust, faster and performs better than sequential SARIMA models in terms of running time and cost function values.

自回归综合移动平均（ARIMA）模型和季节性ARIMA（SARIMA）模型是广泛用于分析和预测固定和季节性时间序列数据的常用技术。构造ARIMA涉及的三个基本步骤是识别，估计和检查模型的有效性。构建ARIMA模型的最关键步骤是模型识别。但是，克服ARIMA和SARIMA的局部最优难题仍然很困难，因为没有合适的方法可以解决。本文提出的并行GA-SARIMA模型用于解决局部最优问题，在初始阶段使用遗传算法（GA）来识别SARIMA的参数顺序和估计。国家气候数据中心（NCDC）时间序列数据集用于测试最终并行GA-SARIMA模型的效率，以预测2000年至2017年印度的平均气温。通过引入遗传算法成功解决了优化问题适用于SARIMA模型的更好的解决方案。研究结果表明，并行GA和SARIMA组合方法的实施提高了模型的预测准确性。在运行时间和成本函数值方面，并行GA-SARIMA方法特别健壮，速度更快，并且性能优于顺序SARIMA模型。通过引入适用于SARIMA模型的更好解决方案，成功实现了GA算法来解决优化问题。研究结果表明，并行GA和SARIMA组合方法的实施提高了模型的预测准确性。在运行时间和成本函数值方面，并行GA-SARIMA方法特别健壮，速度更快，并且性能优于顺序SARIMA模型。通过引入适用于SARIMA模型的更好解决方案，成功实现了GA算法来解决优化问题。研究结果表明，并行GA和SARIMA组合方法的实施提高了模型的预测准确性。在运行时间和成本函数值方面，并行GA-SARIMA方法特别健壮，速度更快，并且性能优于顺序SARIMA模型。