Research on Short-term Load Forecasting Method of Power Grid Based on Deep Learning
-
摘要: 深度模型通过学习一种深层非线性网络结构以实现复杂函数逼近,具有很强的自适应感知能力。本文为了提高电力负荷预测精度,提出一种基于栈式自编码神经网络的深度学习预测方法。该方法结合自编码器和逻辑回归分类器构建一个多输入单输出预测模型,并将重构后的历史负荷、气象信息等数据输入到预测模型中,用栈式自编码器逐层学习并提取深层特征,最后在网络顶层连接逻辑回归模型进行短期负荷预测。实例分析表明,所提预测模型能够有效刻画日负荷变化规律,泛化能力较强,其预测精度达到96.2%,比支持向量回归和模糊神经网络两种浅层学习模型更高。Abstract: The depth model achieves complex function approximation by learning a deep nonlinear network structure,which has strong adaptive perception ability. In order to improve the prediction accuracy of power load, a deep learning prediction method based on stacked auto-encoder neural network is proposed in the paper. A multi-input single-output prediction model is built by combing the auto-encoder with the logic regression classifier, such data as the reconstructed historical load, meteorological elements and so on are all input into prediction model, and the load characteristics is extracted through the hierarchical learning of the stacked auto-encoder. Finally, the short-term load prediction is realized by using the logical regression model at the top of the network. Case analysis shows that the proposed model can effectively characterize the daily load change law with strong generalization performance, and its prediction accuracy can reach 96.2%, which is higher than that of two shallow learning models based on support vector regression and fuzzy neural network respectively.
-
Key words:
- load forecasting /
- deep learning /
- stacked auto-encoder /
- feature extraction /
- neural network
-
[1] Amjady N. Short-term hourly load forecasting using time series modeling with peak load estimation capability[J]. IEEE Transactions on Power Systems, 2001, 16(4): 798805.[2] 马坤隆. 基于大数据的分布式短期负荷预测方法[D]. 长沙: 湖南大学, 2014.[3] 廖旎焕, 胡智宏, 马莹莹, 等. 电力系统短期负荷预测方法综述[J]. 电力系统保护与控制, 2011, 39(1): 147152.[4] 徐培, 蔡小路, 何文伟, 等. 基于深度自编码网络的运动目标检测[J]. 计算机应用, 2015, 30(8): 29342937. [5] 李龙, 魏靖, 黎灿兵,等. 基于人工神经网络的负荷模型预测[J]. 电工技术学报, 2014, 31(3): 225230. [6] 杨再鹤,向铁元,郑 丹. 基于小波变换和SVM 算法的微电网短期负荷预测研究[J]. 现代电力, 2014, 31(3): 7479.[7] Jorjeta G J, Mostafa M, Chen Weipeng. Neural network model ensembles for building-level electricity load forecasts[J]. Energy and Buildings, 2014, 84: 214223.[8] 吴潇雨, 和敬涵, 张沛, 等. 基于灰色投影改进随机森林算法的电力系统短期负荷预测[J]. 电力系统自动化,2015, 39(12): 5055.[9] 吴倩红, 高军, 侯广松, 等. 实现影响因素多源异构融合的短期负荷预测支持向量机算法[J]. 电力系统自动化, 2016, 40(15): 6772.[10]Huang W, Song G, Hong H, et al.Deep architecture for traffic flow prediction: deep belief networks with multitask learning[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(5): 21912201.[11]罗向龙, 焦青青, 牛力瑶, 等. 基于深度学习的短时交通流预测[J]. 计算机应用研究, 2017, 34(1): 9193. [12]Qu X, Kang X, Zhang C, et al. ShortTerm Prediction of Wind Power Based on Deep Long ShortTerm Memory [C]//Power and Energy Engineering Conference (APPEEC). Xi’an: IEEE, 2016: 11481152. [13]寇茜茜, 何希平. 基于栈式自编码器模型的汇率时间序列预测[J]. 计算机应用与软件, 2017, 34(3): 218222.[14]Hinton G E,Osindero S Y W.The A fast learning algorithm for deep belief nets[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(5): 21912201.[15]严干贵, 王东, 杨茂, 等. 两种风电功率多步预测方式的分析及评价[J]. 东北电力大学学报, 2013, 33 (z1):126130. -
点击查看大图
计量
- 文章访问数: 2051
- HTML全文浏览量: 102
- PDF下载量: 72
- 被引次数: 0
下载:
