基于马尔科夫残差修正-自回归滑动平均模型的负荷预测

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (1541 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract To improve the forcasting accuracy of short and medium term loads, this article proposes an autoregressive moving average model based on Markov residual correction. The autoregressive moving average model is used to predict the load and calculate the residual, and the Markov residual correction algorithm is used to correct the prediction results. The engineering case verification shows that the average absolute error of load forecasting obtained by the autoregressive moving average model is 13.67%. After Markov residual correction, the average absolute error of load forecasting is 6.912%, and the prediction accuracy is improved by 49.4%. It is concluded that the load forecasting model proposed in this article has certain significance for guiding industrial users in short and medium term loads forecasting.

Key words： load forecasting Markov correction autoregressive moving average short and medium term characteristics

Received: 06 November 2024

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	HUI Jie
	LIU Bojia
	ZHAO Shusheng
	HU Quandan
	ZENG Xianfeng

Cite this article:

HUI Jie,LIU Bojia,ZHAO Shusheng等. Load forecasting based on Markov residual correction-autoregressive moving average model[J]. Electrical Engineering, 2025, 26(4): 37-43.

URL:

https://dqjs.cesmedia.cn/EN/Y2025/V26/I4/37

[1] 康重庆, 夏清, 张伯明. 电力系统负荷预测研究综述与发展方向的探讨[J].电力系统自动化, 2004(17): 1-11.
[2] WILLIS H L.Spatial electric load forecasting[M].Second edition. New York: Marcel Dekker, 2002.
[3] 陆秋瑜, 马千里, 魏韡, 等. 基于置信容量的风场配套储能容量优化配置[J].电工技术学报, 2022, 37(23): 5901-5910.
[4] 张明泽, 栾文鹏, 艾欣, 等. 基于边缘计算的台区短期负荷预测方法[J].电测与仪表, 2024, 61(4): 93-99.
[5] 江晶晶, 窦真兰, 杨海涛, 等. 贫乏信息下基于深度迁移学习的智慧建筑负荷预测方法[J].电气技术, 2022, 23(5): 55-61, 72.
[6] 李延珍, 王海鑫, 杨子豪, 等. 基于非侵入式负荷分解的家庭负荷两阶段超短期负荷预测模型[J].电工技术学报, 2024, 39(11): 3379-3391.
[7] 彭显刚, 胡松峰, 吕大勇. 基于RBF神经网络的短期负荷预测方法综述[J].电力系统保护与控制, 2011, 39(17): 144-148.
[8] 赵渊, 张夏菲, 谢开贵. 非参数自回归方法在短期电力负荷预测中的应用[J].高电压技术, 2011, 37(2): 429-435.
[9] 牛东晓, 谷志红, 邢棉, 等. 基于数据挖掘的SVM短期负荷预测方法研究[J].中国电机工程学报, 2006, 26(18): 6-12.
[10] 张涛, 顾洁. 高比例可再生能源电力系统的马尔科夫短期负荷预测方法[J].电网技术, 2018, 42(4): 1071-1078.
[11] 张栋梁, 严健, 李晓波, 等. 基于马尔可夫链筛选组合预测模型的中长期负荷预测方法[J].电力系统保护与控制, 2016, 44(12): 63-67.
[12] DUDEK G.Pattern similarity-based methods for short- term load forecasting-part 2: models[J].Applied Soft Computing, 2015, 36: 422-441.
[13] PAPARODITIS E, SAPATINAS T.Short-term load forecasting: the similar shape functional time series predictor[J].IEEE Transactions on Power Systems, 2012, 28(4): 3818-3825.
[14] 林涵, 郝正航, 郭家鹏, 等. 基于TCA-CNN-LSTM的短期负荷预测研究[J].电测与仪表, 2023, 60(8): 73-80.
[15] 赵洋, 王瀚墨, 康丽, 等. 基于时间卷积网络的短期电力负荷预测[J].电工技术学报, 2022, 37(5): 1242-1251.
[16] 崔星, 李晋国, 张照贝, 等. 基于改进粒子群算法优化LSTM的短期电力负荷预测[J].电测与仪表, 2024, 61(1): 131-136.
[17] GERMI M B, MIRJAVADI M, NAMIN A S S, et al. A hybrid model for daily peak load power forecasting based on SAMBA and neural network[J].Journal of Intelligent & Fuzzy Systems: Application in Engin- eering and Technology, 2014, 27(2): 913-920.
[18] 李智轩, 李嘉丰, 叶晓华, 等. 基于Copula函数与多目标进化算法的负荷区间预测[J].电气技术, 2024, 25(6): 24-30.
[19] 陈轩伟. 基于BP-QR模型的负荷区间预测[J].电气技术, 2022, 23(4): 14-17, 24.
[20] 黄元生, 方伟. 基于灰色傅里叶变换残差修正的电力负荷预测模型[J].电力自动化设备, 2013, 33(9): 105-107, 112.
[21] 李滨, 覃芳璐, 吴茵, 等. 基于模糊信息粒化与多策略灵敏度的短期日负荷曲线预测[J].电工技术学报, 2017, 32(9): 149-159.
[22] 唐俊杰, 牛焕娜, 杨明皓. 基于线性相关分析的周期自回归短期负荷预测[J].电力系统保护与控制, 2010, 38(14): 128-133.
[23] 蒋敏, 顾东健, 孔军, 等. 基于在线序列极限支持向量回归的短期负荷预测模型[J].电网技术, 2018, 42(7): 2240-2247.
[24] 徐扬, 张紫涛. 基于遗传模拟退火算法改进BP神经网络的中长期电力负荷预测[J].电气技术, 2021, 22(9): 70-76.
[25] 张贲, 邵常宁, 赵燃. 基于误差修正的短期负荷预测方法[J].电力自动化设备, 2015, 35(11): 152-157.
[26] 阳曾, 丁施尹, 叶萌, 等. 基于变分模态分解和深度学习的短期电力负荷预测模型[J].电测与仪表, 2023, 60(2): 126-131, 146.