In this article, we are initiating the hypothesis that improvements in short term energy load forecasting may rely on inclusion of data from new information sources generated outside the power grid and weather related...In this article, we are initiating the hypothesis that improvements in short term energy load forecasting may rely on inclusion of data from new information sources generated outside the power grid and weather related systems. Other relevant domains of data include scheduled activities on a grid, large events and conventions in the area, equipment duty cycle schedule, data from call centers, real-time traffic, Facebook, Twitter, and other social networks feeds, and variety of city or region websites. All these distributed data sources pose information collection, integration and analysis challenges. Our approach is concentrated on complex non-cyclic events detection where detected events have a human crowd magnitude that is influencing power requirements. The proposed methodology deals with computation, transformation, modeling, and patterns detection over large volumes of partially ordered, internet based streaming multimedia signals or text messages. We are claiming that traditional approaches can be complemented and enhanced by new streaming data inclusion and analyses, where complex event detection combined with Webbased technologies improves short term load forecasting. Some preliminary experimental results, using Gowalla social network dataset, confirmed our hypothesis as a proof-of-concept, and they paved the way for further improvements by giving new dimensions of short term load forecasting process in a smart grid.展开更多
The medium-short term forecast for a certain kinds of main earthquake events might be possible with the time-to-failure method presented by Varnes (1989), Bufe and Varnes (1993), which is to simulate an accelerative r...The medium-short term forecast for a certain kinds of main earthquake events might be possible with the time-to-failure method presented by Varnes (1989), Bufe and Varnes (1993), which is to simulate an accelerative releasing model of precursory earthquake energy. By fitting the observed data with the theoretical formula, a medium-short term forecast technique for the main shock events could be established, by which the location, time and magnitude of the main shock could be determined. The data used in the paper are obtained from the earthquake catalogue recorded by Yunnan Regional Seismological Network with a time coverage of 1965~2002. The statistical analyses for the past 37 years show that the data of M2.5 earthquakes were fairly complete. In the present paper, 30 main shocks occurred in Yunnan region were simulated. For 25 of them, the forecasting time and magnitude from the simulation of precursory sequence are very close to the actual values with the precision of about 0.57 (magnitude unit). Suppose that the last event of the precursory sequence is known, then the time error for the forecasting main shock is about 0.64 year. For the other 5 main shocks, the simulation cannot be made due to the insufficient precursory events for the full determination of energy accelerating curve or disturbance to the energy-release curve. The results in the paper indicate that there is no obviously linear relation in the optimal searching radius for the main shock and the precursory events because Yunnan is an active region with damage earthquakes and moderate and small earthquakes. However, there is a strong correlation between the main shock moment and the coefficient k/m. The optimal fitting range for the forecasting time and magnitude can be further reduced using the relation between the main shock moment lgM0 and the coefficient lgk/m and the value range of the restricting index m, by which the forecast precision of the simulated main shock can be improved. The time-to-failure method is used to fit 30 main shocks in the paper and more than 80% of them have acquired better results, indicating that the method is prospective for its ability to forecast the known main shock sequence. Therefore, the prospect is cheerful to make medium-short term forecast for the forthcoming main shocks by the precursory events.展开更多
In the electricity market,fluctuations in real-time prices are unstable,and changes in short-term load are determined by many factors.By studying the timing of charging and discharging,as well as the economic benefits...In the electricity market,fluctuations in real-time prices are unstable,and changes in short-term load are determined by many factors.By studying the timing of charging and discharging,as well as the economic benefits of energy storage in the process of participating in the power market,this paper takes energy storage scheduling as merely one factor affecting short-term power load,which affects short-term load time series along with time-of-use price,holidays,and temperature.A deep learning network is used to predict the short-term load,a convolutional neural network(CNN)is used to extract the features,and a long short-term memory(LSTM)network is used to learn the temporal characteristics of the load value,which can effectively improve prediction accuracy.Taking the load data of a certain region as an example,the CNN-LSTM prediction model is compared with the single LSTM prediction model.The experimental results show that the CNN-LSTM deep learning network with the participation of energy storage in dispatching can have high prediction accuracy for short-term power load forecasting.展开更多
储能集装箱是锂电池储能电站的核心设备,每个集装箱由数千只电芯串并联构成。因此,对集装箱电芯锂电池荷电状态(state of charge,SOC)的准确估计成为表征储能电站运行最核心最基础的参数,并且为辅助新能源高效并网,储能系统的工作状态...储能集装箱是锂电池储能电站的核心设备,每个集装箱由数千只电芯串并联构成。因此,对集装箱电芯锂电池荷电状态(state of charge,SOC)的准确估计成为表征储能电站运行最核心最基础的参数,并且为辅助新能源高效并网,储能系统的工作状态也会相应地呈现随机性、波动性和不确定性,这对电芯状态估计的准确度提出了更高的要求。为此,首先基于基尔霍夫定律建立Thevenin电池模型,根据安时积分法列出系统的状态和观测方程,并且将其状态和观测方程作为扩展卡尔曼滤波(extended Kalman filtering,EKF)算法的研究对象。然后利用EKF算法对估计值电池SOC更新迭代,再将EKF算法中得到的卡尔曼矩阵和状态变量更新误差值以及UDDS工况下的电池数据,作为长短期记忆(long short-term memory,LSTM)神经网络算法的训练数据集,由此完成LSTM-EKF联合算法,实现对储能集装箱电芯SOC的优化估计。该文所提LSTM-EKF算法可将电芯SOC的误差值降低到1%以下。最后对优化算法在储能电站安全运行与监控平台中的应用情况进行介绍。展开更多
As a complex and critical cyber-physical system(CPS),the hybrid electric powertrain is significant to mitigate air pollution and improve fuel economy.Energy management strategy(EMS)is playing a key role to improve the...As a complex and critical cyber-physical system(CPS),the hybrid electric powertrain is significant to mitigate air pollution and improve fuel economy.Energy management strategy(EMS)is playing a key role to improve the energy efficiency of this CPS.This paper presents a novel bidirectional long shortterm memory(LSTM)network based parallel reinforcement learning(PRL)approach to construct EMS for a hybrid tracked vehicle(HTV).This method contains two levels.The high-level establishes a parallel system first,which includes a real powertrain system and an artificial system.Then,the synthesized data from this parallel system is trained by a bidirectional LSTM network.The lower-level determines the optimal EMS using the trained action state function in the model-free reinforcement learning(RL)framework.PRL is a fully data-driven and learning-enabled approach that does not depend on any prediction and predefined rules.Finally,real vehicle testing is implemented and relevant experiment data is collected and calibrated.Experimental results validate that the proposed EMS can achieve considerable energy efficiency improvement by comparing with the conventional RL approach and deep RL.展开更多
随着电力现货市场的开展,短期电价预测对于各市场主体的决策有着重要意义,而高比例清洁能源与储能的不断接入给短期电价预测带来很大挑战。提出一种基于最大信息系数法(maximum information coefficient,MIC)、集成经验模态分解(ensembl...随着电力现货市场的开展,短期电价预测对于各市场主体的决策有着重要意义,而高比例清洁能源与储能的不断接入给短期电价预测带来很大挑战。提出一种基于最大信息系数法(maximum information coefficient,MIC)、集成经验模态分解(ensemble empirical mode decomposition,EEMD)和改进Informer的短期电价多步预测模型。首先,采用MIC分析出与电价相关性较高的几类因素作为模型原始输入序列;然后,将上述原始序列进行EEMD分解后得到多条本征模函数(intrinsic mode function,IMF)和一个残余项后输入改进Informer分别得到翌日24点多步预测结果,再对预测结果进行滤波;最后,将滤波后序列的预测结果叠加得到最终的预测值。以西班牙电力市场数据进行验证,实验结果证明该模型可以有效提高电力市场短期电价多步预测精度。展开更多
文摘In this article, we are initiating the hypothesis that improvements in short term energy load forecasting may rely on inclusion of data from new information sources generated outside the power grid and weather related systems. Other relevant domains of data include scheduled activities on a grid, large events and conventions in the area, equipment duty cycle schedule, data from call centers, real-time traffic, Facebook, Twitter, and other social networks feeds, and variety of city or region websites. All these distributed data sources pose information collection, integration and analysis challenges. Our approach is concentrated on complex non-cyclic events detection where detected events have a human crowd magnitude that is influencing power requirements. The proposed methodology deals with computation, transformation, modeling, and patterns detection over large volumes of partially ordered, internet based streaming multimedia signals or text messages. We are claiming that traditional approaches can be complemented and enhanced by new streaming data inclusion and analyses, where complex event detection combined with Webbased technologies improves short term load forecasting. Some preliminary experimental results, using Gowalla social network dataset, confirmed our hypothesis as a proof-of-concept, and they paved the way for further improvements by giving new dimensions of short term load forecasting process in a smart grid.
文摘The medium-short term forecast for a certain kinds of main earthquake events might be possible with the time-to-failure method presented by Varnes (1989), Bufe and Varnes (1993), which is to simulate an accelerative releasing model of precursory earthquake energy. By fitting the observed data with the theoretical formula, a medium-short term forecast technique for the main shock events could be established, by which the location, time and magnitude of the main shock could be determined. The data used in the paper are obtained from the earthquake catalogue recorded by Yunnan Regional Seismological Network with a time coverage of 1965~2002. The statistical analyses for the past 37 years show that the data of M2.5 earthquakes were fairly complete. In the present paper, 30 main shocks occurred in Yunnan region were simulated. For 25 of them, the forecasting time and magnitude from the simulation of precursory sequence are very close to the actual values with the precision of about 0.57 (magnitude unit). Suppose that the last event of the precursory sequence is known, then the time error for the forecasting main shock is about 0.64 year. For the other 5 main shocks, the simulation cannot be made due to the insufficient precursory events for the full determination of energy accelerating curve or disturbance to the energy-release curve. The results in the paper indicate that there is no obviously linear relation in the optimal searching radius for the main shock and the precursory events because Yunnan is an active region with damage earthquakes and moderate and small earthquakes. However, there is a strong correlation between the main shock moment and the coefficient k/m. The optimal fitting range for the forecasting time and magnitude can be further reduced using the relation between the main shock moment lgM0 and the coefficient lgk/m and the value range of the restricting index m, by which the forecast precision of the simulated main shock can be improved. The time-to-failure method is used to fit 30 main shocks in the paper and more than 80% of them have acquired better results, indicating that the method is prospective for its ability to forecast the known main shock sequence. Therefore, the prospect is cheerful to make medium-short term forecast for the forthcoming main shocks by the precursory events.
基金supported by a State Grid Zhejiang Electric Power Co.,Ltd.Economic and Technical Research Institute Project(Key Technologies and Empirical Research of Diversified Integrated Operation of User-Side Energy Storage in Power Market Environment,No.5211JY19000W)supported by the National Natural Science Foundation of China(Research on Power Market Management to Promote Large-Scale New Energy Consumption,No.71804045).
文摘In the electricity market,fluctuations in real-time prices are unstable,and changes in short-term load are determined by many factors.By studying the timing of charging and discharging,as well as the economic benefits of energy storage in the process of participating in the power market,this paper takes energy storage scheduling as merely one factor affecting short-term power load,which affects short-term load time series along with time-of-use price,holidays,and temperature.A deep learning network is used to predict the short-term load,a convolutional neural network(CNN)is used to extract the features,and a long short-term memory(LSTM)network is used to learn the temporal characteristics of the load value,which can effectively improve prediction accuracy.Taking the load data of a certain region as an example,the CNN-LSTM prediction model is compared with the single LSTM prediction model.The experimental results show that the CNN-LSTM deep learning network with the participation of energy storage in dispatching can have high prediction accuracy for short-term power load forecasting.
基金supported in part by the National Natural Science Foundation of China(61533019,91720000)Beijing Municipal Science and Technology Commission(Z181100008918007)the Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles(pICRI-IACVq)
文摘As a complex and critical cyber-physical system(CPS),the hybrid electric powertrain is significant to mitigate air pollution and improve fuel economy.Energy management strategy(EMS)is playing a key role to improve the energy efficiency of this CPS.This paper presents a novel bidirectional long shortterm memory(LSTM)network based parallel reinforcement learning(PRL)approach to construct EMS for a hybrid tracked vehicle(HTV).This method contains two levels.The high-level establishes a parallel system first,which includes a real powertrain system and an artificial system.Then,the synthesized data from this parallel system is trained by a bidirectional LSTM network.The lower-level determines the optimal EMS using the trained action state function in the model-free reinforcement learning(RL)framework.PRL is a fully data-driven and learning-enabled approach that does not depend on any prediction and predefined rules.Finally,real vehicle testing is implemented and relevant experiment data is collected and calibrated.Experimental results validate that the proposed EMS can achieve considerable energy efficiency improvement by comparing with the conventional RL approach and deep RL.
