This paper considers a decomposition framework as a mechanism for information hiding for secure communication via open network channels. Two varieties of this framework are provided: one is based on Gaussian arithmeti...This paper considers a decomposition framework as a mechanism for information hiding for secure communication via open network channels. Two varieties of this framework are provided: one is based on Gaussian arithmetic with complex modulus and another on an elliptic curve modular equation. The proposed algorithm is illustrated in a numerical example.展开更多
为了提高太阳电池阵多变量预测的精度,解决阳电池阵遥测参数存在周期波动与增长性互相耦合的问题,提出一种基于STL-Prophet-Informer模型的太阳电池阵多变量预测算法.该算法首先应用局部加权周期趋势分解算法(seasonal and trend decomp...为了提高太阳电池阵多变量预测的精度,解决阳电池阵遥测参数存在周期波动与增长性互相耦合的问题,提出一种基于STL-Prophet-Informer模型的太阳电池阵多变量预测算法.该算法首先应用局部加权周期趋势分解算法(seasonal and trend decomposition procedure based on loess,STL)对太阳电池阵的多个参数分解为趋势分量、周期分量和残差分量,然后采用对趋势性数据预测效果较好的Prophet预测趋势分量,Informer模型预测周期分量和残差分量,最后将各分量预测结果相加后得到总的太阳电池阵参数预测值.以某卫星太阳电池阵实际遥测数据做算例分析,提出算法的各项误差评价指标和单一的Informer模型、LSTM模型等相比有明显减小,将该组合预测模型用于太阳电池阵多变量参数预测中,可以提高参数预测精度,提升卫星自主运行性能.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
The novel information criterion (NIC) algorithm can find the principal subspace quickly, but it is not an actual principal component analysis (PCA) algorithm and hence it cannot find the orthonormal eigen-space wh...The novel information criterion (NIC) algorithm can find the principal subspace quickly, but it is not an actual principal component analysis (PCA) algorithm and hence it cannot find the orthonormal eigen-space which corresponds to the principal component of input vector. This defect limits its application in practice. By weighting the neural network's output of NIC, a modified novel information criterion (MNIC) algorithm is presented. MNIC extractes the principal components and corresponding eigenvectors in a parallel online learning program, and overcomes the NIC's defect. It is proved to have a single global optimum and nonquadratic convergence rate, which is superior to the conventional PCA online algorithms such as Oja and LMSER. The relationship among Oja, LMSER and MNIC is exhibited. Simulations show that MNIC could converge to the optimum fast. The validity of MNIC is proved.展开更多
由于光伏出力的波动性和随机性给电网的规划和运行带来了挑战,因此提高光伏功率预测的精度对提升新能源系统的稳定性具有重要意义。为此提出了一种结合模态分解、多维特征建模、Informer、双向长短期神经网络(bidirectional long short-...由于光伏出力的波动性和随机性给电网的规划和运行带来了挑战,因此提高光伏功率预测的精度对提升新能源系统的稳定性具有重要意义。为此提出了一种结合模态分解、多维特征建模、Informer、双向长短期神经网络(bidirectional long short-term memory network,BiLSTM)的超短期光伏组合预测模型。首先通过变分模态分解将光伏功率序列分解成不同频率的本征模态函数(intrinsic mode function,IMF),降低光伏功率信号的非平稳性与复杂度;随后使用离散小波变换提取天气因素中的细节分量,实现不同分解算法的优势互补,并用随机森林算法为每个IMF筛选冗余特征,然后将特征矩阵送入Informer进行建模,提取不同时间步中关键时刻的信息,提高对长时间序列的预测效率;最后为进一步提高模型预测精度,分析误差序列特性,利用BiLSTM进行误差校正。采用实际光伏数据进行算例分析,结果表明所提方法提高了超短期光伏功率预测精度。展开更多
Recommender system is an effective tool to solve the problems of information overload.The traditional recommender systems,especially the collaborative filtering ones,only consider the two factors of users and items.Wh...Recommender system is an effective tool to solve the problems of information overload.The traditional recommender systems,especially the collaborative filtering ones,only consider the two factors of users and items.While social networks contain abundant social information,such as tags,places and times.Researches show that the social information has a great impact on recommendation results.Tags not only describe the characteristics of items,but also reflect the interests and characteristics of users.Since the traditional recommender systems cannot parse multi-dimensional information,in this paper,a tensor decomposition model based on tag regularization is proposed which incorporates social information to benefit recommender systems.The original Singular Value Decomposition(SVD)model is optimized by mining the co-occurrence and mutual exclusion of tags,and their features are constrained by the relationship between tags.Experiments on real dataset show that the proposed algorithm achieves superior performance to existing algorithms.展开更多
Due to the large and frequent static data interaction between the Electric Information Acquisition System and the external business systems,researching on using limited server sources to do an efficient task schedulin...Due to the large and frequent static data interaction between the Electric Information Acquisition System and the external business systems,researching on using limited server sources to do an efficient task scheduling is becoming one of the key technologies of the unified interface platform.The information interaction structure of the unified interface platform is introduced.Task scheduling has been decomposed into two stages,task decomposition and task combination,based on the features(various types and dispersed)of large static data.The principle of the minimum variance of the subtasks data quantity is used to do the target task resolving in the decomposition stage.The thought of the Greedy Algorithm is used in the task combination.Breaking the target task with large static data into serval composed tasks with roughly same data quantity is effectively realized.Meanwhile,to avoid the situation of the GA falling into the local optimal solution,an improved combination method has been put forward.Moreover,the new method creates more average composed tasks and making the task scheduling more effective.Ultimately,the effectiveness of the proposed method is verified by the experimental data.展开更多
文摘This paper considers a decomposition framework as a mechanism for information hiding for secure communication via open network channels. Two varieties of this framework are provided: one is based on Gaussian arithmetic with complex modulus and another on an elliptic curve modular equation. The proposed algorithm is illustrated in a numerical example.
文摘为了提高太阳电池阵多变量预测的精度,解决阳电池阵遥测参数存在周期波动与增长性互相耦合的问题,提出一种基于STL-Prophet-Informer模型的太阳电池阵多变量预测算法.该算法首先应用局部加权周期趋势分解算法(seasonal and trend decomposition procedure based on loess,STL)对太阳电池阵的多个参数分解为趋势分量、周期分量和残差分量,然后采用对趋势性数据预测效果较好的Prophet预测趋势分量,Informer模型预测周期分量和残差分量,最后将各分量预测结果相加后得到总的太阳电池阵参数预测值.以某卫星太阳电池阵实际遥测数据做算例分析,提出算法的各项误差评价指标和单一的Informer模型、LSTM模型等相比有明显减小,将该组合预测模型用于太阳电池阵多变量参数预测中,可以提高参数预测精度,提升卫星自主运行性能.
文摘The novel information criterion (NIC) algorithm can find the principal subspace quickly, but it is not an actual principal component analysis (PCA) algorithm and hence it cannot find the orthonormal eigen-space which corresponds to the principal component of input vector. This defect limits its application in practice. By weighting the neural network's output of NIC, a modified novel information criterion (MNIC) algorithm is presented. MNIC extractes the principal components and corresponding eigenvectors in a parallel online learning program, and overcomes the NIC's defect. It is proved to have a single global optimum and nonquadratic convergence rate, which is superior to the conventional PCA online algorithms such as Oja and LMSER. The relationship among Oja, LMSER and MNIC is exhibited. Simulations show that MNIC could converge to the optimum fast. The validity of MNIC is proved.
基金the following grants:The National Key Research andDevelopment Program of China(No.2019YFB1404602,X.D.Zhang)The Natural Science Foundationof the Jiangsu Higher Education Institutions of China(No.17KJB520017,Z.B.Sun)+2 种基金The YoungTeachers Training Project of Nanjing Audit University(No.19QNPY017,Z.B.Sun)The OpeningProject of Jiangsu Key Laboratory of Data Science and Smart Software(No.2018DS301,H.F.Guo,Jinling Institute of Technology)Funded by Government Audit Research Foundation of Nanjing Audit University.
文摘Recommender system is an effective tool to solve the problems of information overload.The traditional recommender systems,especially the collaborative filtering ones,only consider the two factors of users and items.While social networks contain abundant social information,such as tags,places and times.Researches show that the social information has a great impact on recommendation results.Tags not only describe the characteristics of items,but also reflect the interests and characteristics of users.Since the traditional recommender systems cannot parse multi-dimensional information,in this paper,a tensor decomposition model based on tag regularization is proposed which incorporates social information to benefit recommender systems.The original Singular Value Decomposition(SVD)model is optimized by mining the co-occurrence and mutual exclusion of tags,and their features are constrained by the relationship between tags.Experiments on real dataset show that the proposed algorithm achieves superior performance to existing algorithms.
文摘Due to the large and frequent static data interaction between the Electric Information Acquisition System and the external business systems,researching on using limited server sources to do an efficient task scheduling is becoming one of the key technologies of the unified interface platform.The information interaction structure of the unified interface platform is introduced.Task scheduling has been decomposed into two stages,task decomposition and task combination,based on the features(various types and dispersed)of large static data.The principle of the minimum variance of the subtasks data quantity is used to do the target task resolving in the decomposition stage.The thought of the Greedy Algorithm is used in the task combination.Breaking the target task with large static data into serval composed tasks with roughly same data quantity is effectively realized.Meanwhile,to avoid the situation of the GA falling into the local optimal solution,an improved combination method has been put forward.Moreover,the new method creates more average composed tasks and making the task scheduling more effective.Ultimately,the effectiveness of the proposed method is verified by the experimental data.