CN112308402B - Power time series data abnormity detection method based on long and short term memory network - Google Patents
Power time series data abnormity detection method based on long and short term memory network Download PDFInfo
- Publication number
- CN112308402B CN112308402B CN202011182119.7A CN202011182119A CN112308402B CN 112308402 B CN112308402 B CN 112308402B CN 202011182119 A CN202011182119 A CN 202011182119A CN 112308402 B CN112308402 B CN 112308402B
- Authority
- CN
- China
- Prior art keywords
- model
- hidden state
- attention
- data
- encoder
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 22
- 230000006403 short-term memory Effects 0.000 title claims abstract description 11
- 230000007787 long-term memory Effects 0.000 title claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 27
- 230000002159 abnormal effect Effects 0.000 claims abstract description 17
- 238000003062 neural network model Methods 0.000 claims abstract description 12
- 230000005856 abnormality Effects 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 25
- 230000004913 activation Effects 0.000 claims description 11
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 10
- 230000015654 memory Effects 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 238000011176 pooling Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 230000005764 inhibitory process Effects 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims description 2
- 241000080795 Elaphoglossum affine Species 0.000 claims 1
- 238000013459 approach Methods 0.000 claims 1
- 238000010606 normalization Methods 0.000 claims 1
- 238000000844 transformation Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000008034 disappearance Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 239000002356 single layer Substances 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 239000010410 layer Substances 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an abnormality detection method for power time series data based on a long-term and short-term memory network. The method comprises the following steps: (1) preprocessing power time sequence data; (2) neural network model pre-training, using encoder-decoder structureCalculating the layer dynamic attention; (3) abnormal data detection in neural network modelsAfter training is completed, the model weight W is stored locally, the model is directly loaded when new power time sequence data x are detected, and calculation is carried outDistance from the representative point cAnd obtaining the abnormal score of the user to judge whether the user is abnormal or not. The method is used for abnormality detection of the power time series data, and is simple and high in detection accuracy.
Description
Technical Field
The invention belongs to the technical field of data analysis and anomaly detection, and particularly relates to an anomaly detection method of power time series data based on a long-term and short-term memory network.
Background
The real-time operation data of the power system has the potential capability of reflecting the current operation state and the future development trend of the power system. Along with the rapid development of the intellectualization of the power system, the scale of embedding various sensors in the power system is continuously enlarged, so that the types of data collected by a sensing layer are more refined, and the data to be processed is increased rapidly. According to incomplete statistics, the power grid service data collected every day in a single city can reach a PB level. In general, the real-time operation data of the power system has the characteristics of multiple data acquisition devices, high acquisition frequency, large data scale, complex data types and the like. And the collected data is typical time-series data (TSD). The method has the advantages that the power time sequence data are fully utilized, the appropriate technology is adopted to carry out abnormity detection and timely find faults existing in the power system, and decision and auxiliary support can be provided for efficient and safe operation of the power system.
Disclosure of Invention
In order to achieve the above object, the present invention provides a method for detecting abnormality of power timing data based on long and short term memory network; the invention uses the long and short term memory network model in deep learning to analyze the power time sequence data and detect the abnormal data in the power time sequence data so as to help the power system to find the existing faults in time.
An abnormality detection method for power time series data based on a long-short term memory network comprises the following steps:
s1: preprocessing power time sequence data, removing unimportant features in the data, cleaning partial noise data, and taking a data preprocessing result as input of next model training;
s2: pre-training a neural network model, and calculating the layered dynamic attention by adopting an encoder-decoder structure; the basic model uses a Long short-term memory network (LSTM), the ReLU is used as an activation function, the loss function uses a custom loss function, the optimizer uses Adam, and the model is trained until convergence; this step is based on a power time series data set { x }1,…,xNObtaining initial parameters of the neural network model parameters of the next step and representative point representation c of the whole time sequence data set;
s3: abnormal data detection in neural network modelsAfter training is completed, the model weight W is stored locally, the model is directly loaded when new power time sequence data x are detected, and calculation is carried outDistance from the representative point c And obtaining the abnormal score of the user to judge whether the user is abnormal or not.
Compared with the prior art, the invention has the beneficial effects that:
the method comprises the steps of firstly preprocessing the existing data to obtain a group of relatively regular data sets without redundancy; the invention adopts the long-term and short-term memory network, and is more suitable for the analysis of time sequence data compared with other networks; the Adam optimizer is adopted, the Adam algorithm is a method for calculating the self-adaptive learning rate of each parameter, the algorithm needs less memory and is efficient in calculation, and the method is suitable for solving the problems of large-scale data and parameters; the method uses the custom loss function, performs specific optimization aiming at the abnormal detection, and can improve the network training efficiency and the abnormal detection accuracy; according to the invention, a ReLU activation function is used, and the single-side inhibition of the function enables neurons in a neural network to have sparse activation, so that a model after sparse realization through the ReLU can better mine relevant characteristics and fit training data; the invention uses the network pre-training technology, thereby greatly reducing the training time of the model.
Drawings
FIG. 1 is a flow chart of an anomaly detection method based on power time series data of a long-term and short-term memory network according to the present invention.
FIG. 2 is a block diagram of an encoder-decoder neural network architecture for pre-training a hierarchical attention mechanism in accordance with the present invention.
Fig. 3 shows the principle and structure of the method for detecting the abnormality of the power time series data based on the long-short term memory network according to the present invention.
Detailed Description
The following description of the embodiments of the present invention is provided in order to better understand the present invention for those skilled in the art with reference to the accompanying drawings. It is to be expressly noted that in the following description, a detailed description of known functions and designs will be omitted when it may obscure the subject matter of the present invention.
Example 1
Although illustrative embodiments of the present invention have been described above to facilitate the understanding of the present invention by those skilled in the art, it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all changes that come within the meaning and range of equivalency of the claims are to be embraced therein.
As shown in fig. 1 and fig. 3, a method for detecting an abnormality of power time series data based on a long-short term memory network, the method comprising two parts of off-line training a model and detecting an abnormality based on the model by a power time series data analysis method based on a long-short term memory network model, comprises the following steps:
s1: and (3) preprocessing power time sequence data, removing unimportant features in the data, and cleaning part of noise data. The result of the data preprocessing is used as the input of the next model training;
s2: the method comprises the following steps of pre-training a neural network model, training the model until convergence, based on a hierarchical attention mechanism encoder-decoder neural network structure (figure 2), using a long-short-term memory network (LSTM) for a basic model, using Adam for an optimizer, using a custom loss function for a loss function, using a ReLU as an activation function, and training the model. In the training process, a back propagation algorithm is adopted, the algorithm is based on a chain rule of a complex function, a gradient descending mode is adopted, the gradient is intuitively understood to be first-order approximation, so the gradient can be understood to be a coefficient of the sensitivity of a certain variable or a certain intermediate variable to the output influence, and the understanding is more intuitive when the chain method is changed from multiplication to Jacobian matrix multiplication. To reduce training time, pre-training (pre-training) can be used to find a near-optimal solution for weights in the neural network.
The pre-trained model adopts a coder-decoder structure based on a hierarchical attention mechanism, and comprises the following modules:
2.1 encoder
Input orderColumn(s) ofFor k variable sequence with length of l, the hidden state sequence of n encoder units is obtained by passing the k variable sequence through LSTM unitWherein XiCorresponding encoder hidden state
2.2 decoder
Combining the previous decoder unit hidden state with the k-dimensional prediction result of the previous decoder unitThe current decoder hidden state is obtained by the LSTM unit. Thereby obtaining a sequence of hidden states of the decoder unitWherein
2.3 computing hierarchical dynamic attention
(1) Calculating attention weights
For each decoder unit, all encoder hidden states E obtained from step 2.1 and decoder hidden states obtained from step 2.2Calculating attention alphai*The method used is a bilinear mapping method (i.e.,) Or location-based methods (i.e. using a location-based method)). Then to alphai*Use ofThe softmax is normalized to obtain the attention weight
(2) Computing dynamic attention context vectors
Using the attention weight obtained in the previous stepSet H of hidden states for all encoders and hidden states for decodersiThe weighted sum is taken E ═ D, resulting in a dynamic attention context vector, i.e.,
(3) computing hierarchical attention hiding states
Obtained in the last stepAfter being connected with the hidden state of the decoder, the corresponding dynamic attention hidden state is obtained through a ReLU activation functionThen, a Max-Pooling or averaging method is used for calculating and obtaining the context vector of the encoder according to all the hidden states E of the encoder obtained in the step 2.1Finally, the encoder context vector ceAnd dynamic attention hidden stateBy blending functions (serial affine transformation of two vectors, or pooling operations on both), we get a hierarchical attention hidden state
Specifically, the number of hidden units in the model is 128, a single-layer LSTM is used, and parameter estimation is performed by using an Adam optimization algorithm. The size of the model training batch is set to 512, the number of iterations is 500, the learning rate is set to 0.001, overfitting is prevented by using early stopping, and the time point of early stopping is judged by the error reduction trend of the model on the cross validation set.
S3: abnormal data detection in neural network modelsAfter training is completed, the model weight W is stored locally, the model is directly loaded when new power time sequence data x are detected, and calculation is carried outDistance from the representative point cAnd obtaining the abnormal score of the user to judge whether the user is abnormal or not.
Further, in step S3, a Long short-term memory (LSTM) is used, which is an excellent variant model of RNN, inherits most characteristics of RNN model, and solves the problem of gradient disappearance caused by gradual reduction in the gradient back propagation process, and the LSTM is very suitable for processing the highly time-related problems, such as the power time-series data concerned in this patent.
Specifically, the number of hidden units in the model is 96, single-layer LSTM is used, and parameter estimation is performed by using an Adam optimization algorithm. The model training batch size is set to 512, the number of iterations is 200, the learning rate is set to 0.001, and overfitting is prevented by using the advance stop
The beneficial effect of adopting the further scheme is as follows: the LSTM is more suitable for time sequence data than other networks, so that the addition of the LSTM effectively improves the effect of anomaly detection.
Further, in step S3, Adam is used as an optimization function, which is essentially RMSprop with momentum term, and it dynamically adjusts the learning rate of each parameter using the first moment estimate and the second moment estimate of the gradient. The formula is as follows:
(1)mt=μ*mt-1+(1-μ)*gt
(2)nt=v*nt-1+(1-v)*gt 2
where equations (1) (2) are the first and second order moment estimates, respectively, for the gradient, which can be considered as Egt|,E|gt 2The estimate of | equation (3) (4) is a correction to the first order second moment estimate, which can be approximated as an unbiased estimate of the expectation. It can be seen that the moment estimation directly on the gradient has no additional requirements on the memory and can be dynamically adjusted according to the gradient. The last term is preceded by a dynamic constraint formed on the learning rate n and having a well-defined range.
The beneficial effect of adopting the further scheme is as follows: after offset correction, the learning rate of each iteration has a certain range, so that the parameters are relatively stable.
Further, step S3 uses a custom loss function, which is defined as follows:
herein, theFor the LSTM model, the parameters of the network are W, and a time sequence x is formediMapping into a hypersphere. The objective function described above requires that the raw data be mapped into a hypersphere, in order to contain as much data as possible within the hypersphere. Wherein the first term minimizes the volume of the hypersphere; the second term is a penalty term for those located outside the hypersphere,the hyper-parameter α is used to control a trade-off of hyper-sphere volume and over-boundary; the third term is a regularization term that controls the norm of the network parameter W to avoid model overfitting.
After the Adam completes the training of the model, the model is directly loaded and calculated when new power time sequence data x are detectedDistance from the representative point cAnd obtaining the abnormal score of the user to judge whether the user is abnormal or not.
The beneficial effect of adopting the further scheme is as follows: the loss function is specifically optimized for anomaly detection, network training efficiency is effectively improved, and anomaly detection accuracy and recall rate are improved.
Further, step S3 uses ReLU as the activation function, whose formula is defined as follows:
ReLU(x)=max{0,x}
the function changes all negative values into 0, and the positive values are unchanged, namely, unilateral inhibition is carried out, so that neurons in the neural network also have sparse activation.
The beneficial effect of adopting the further scheme is as follows: for a linear function, the expression capacity of the ReLU is stronger, and the ReLU is particularly embodied in a deep network; for the nonlinear function, because the Gradient of the non-negative interval is constant, the ReLU has no Problem of Gradient disappearance (cancellation Gradient distribution), so that the convergence rate of the model is maintained in a stable state.
Further, the step S3 initializes parameters of the LSTM model using the S2 pre-trained network parameters, the pre-trained model being a model trained on a large reference data set for solving a similar problem. Because the calculation cost for training the model is high, it is common practice to import published results and use the corresponding model, and slight adjustment of model parameters is performed on the basis of the model, so that the training process of the model is completed.
The beneficial effect of adopting the further scheme is as follows: the training speed of the model can be increased, the generated model can be stored in a weight mode and can be migrated to the solution of other problems, and the idea is adopted in the process of migration learning.
Claims (3)
1. An abnormality detection method for power time series data based on a long-term and short-term memory network is characterized by comprising the following steps:
s1: preprocessing power time sequence data, removing unimportant features in the data, cleaning partial noise data, and taking a data preprocessing result as input of next model training;
s2: pre-training a neural network model, and calculating the layered dynamic attention by adopting an encoder-decoder structure; the basic model uses a long-short term memory network LSTM and a ReLU as an activation function, the loss function uses a custom loss function, the optimizer uses Adam, and the model is trained until convergence; this step is based on the power time series data set { x }1,…,xNObtaining initial parameters of the neural network model parameters of the next step and representative point representation c of the whole time sequence data set;
s3: abnormal data detection in neural network modelsAfter training is completed, the model weight W and the model are stored locally, the model is directly loaded when new power time sequence data x are detected, and calculation is carried outDistance from the representative point c Obtaining the abnormal score of the user to judge whether the user is abnormal; wherein:
in step S2, the method for calculating the hierarchical dynamic attention using the encoder-decoder structure is as follows:
(1) input sequenceObtaining hidden state sequences of n encoder units by a k-dimensional variable sequence with the length of l through an LSTM unitWherein XiCorresponding encoder hidden state
(2) Combining the previous decoder unit hidden state with the k-dimensional prediction result of the previous decoder unitObtaining the hidden state of the current decoder through the LSTM unit, and further obtaining the hidden state sequence of the decoder unitWherein
(3) Computing hierarchical dynamic attention
Calculating attention weight
For each decoder unit, according to the hidden state sequence E of all the encoder units obtained in the step (1) and the hidden state of the decoder obtained in the step (2)Calculating attention alphai*The method used is a bilinear mapping method, i.e.Or a location-based approach, the location of the user,namely, it isThen to alphai*Normalization using softmax to obtain attention weight
② calculating dynamic attention context vector
Using the attention weight obtained in the previous stepSet H of hidden states for all encoders and hidden states for decodersiThe weighted sum is taken E ═ D, resulting in a dynamic attention context vector, i.e.,
computing layered attention hidden state
Obtained in the last stepAfter being connected with the hidden state of the decoder, the corresponding dynamic attention hidden state is obtained through a ReLU activation functionAnd then calculating to obtain a context vector of the encoder according to the hidden state sequence E of the encoder unit obtained in the step (1) by using a Max-Pooling or averaging methodFinally, the encoder context vector ceAnd dynamic attention hidden stateBy mixed functions, i.e. affine transformations of two vectors in series, or pooling operations of bothTo do, get a layered attention hidden state
In step S2, the custom loss function is defined as follows:
2. The abnormality detection method according to claim 1, characterized in that in step S2, ReLU is selected based on the activation function of the neural network model, all negative values become 0, and positive values are unchanged, i.e., unilateral inhibition, so that neurons in the neural network also have sparse activation, and the formula is as follows:
ReLU(x)=max{0,x}。
3. the abnormality detection method according to claim 1, characterized in that in step S2, Adam is selected as an optimization algorithm for training a neural network model, and the learning rate of each parameter is dynamically adjusted using first order moment estimation and second order moment estimation of the gradient; the formula is as follows:
mt=μ*mt-1+(1-μ)*gt (1)
wherein the formulas (1) and (2) are respectively for the gradient gtThe first order moment estimate and the second order moment estimate of (d) are regarded as the expected value E | gt|,E|gt 2Estimate of | equation (3) (4) is a correction to the first order second moment estimate, approximated as an unbiased estimate of the expectation; the front part of equation (5) is a dynamic constraint formed on the learning rate η.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011182119.7A CN112308402B (en) | 2020-10-29 | 2020-10-29 | Power time series data abnormity detection method based on long and short term memory network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011182119.7A CN112308402B (en) | 2020-10-29 | 2020-10-29 | Power time series data abnormity detection method based on long and short term memory network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112308402A CN112308402A (en) | 2021-02-02 |
CN112308402B true CN112308402B (en) | 2022-04-12 |
Family
ID=74331560
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011182119.7A Active CN112308402B (en) | 2020-10-29 | 2020-10-29 | Power time series data abnormity detection method based on long and short term memory network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112308402B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113779879B (en) * | 2021-09-06 | 2024-06-18 | 安徽大学 | Middle-long-term electricity utilization abnormality detection method based on LSTM-seq2seq-attention model |
CN115497006B (en) * | 2022-09-19 | 2023-08-01 | 杭州电子科技大学 | Urban remote sensing image change depth monitoring method and system based on dynamic mixing strategy |
CN115309736B (en) * | 2022-10-10 | 2023-03-24 | 北京航空航天大学 | Time sequence data anomaly detection method based on self-supervision learning multi-head attention network |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102750416A (en) * | 2012-06-19 | 2012-10-24 | 中国电力科学研究院 | Topological subnetting method of electromagnetic transient simulation containing switching characteristic circuit |
CN109214003A (en) * | 2018-08-29 | 2019-01-15 | 陕西师范大学 | The method that Recognition with Recurrent Neural Network based on multilayer attention mechanism generates title |
CN109816008A (en) * | 2019-01-20 | 2019-05-28 | 北京工业大学 | A kind of astronomical big data light curve predicting abnormality method based on shot and long term memory network |
CN110413729A (en) * | 2019-06-25 | 2019-11-05 | 江南大学 | Talk with generation method based on the more wheels of tail sentence-dual attention model of context |
CN110717345A (en) * | 2019-10-15 | 2020-01-21 | 内蒙古工业大学 | Translation realignment recurrent neural network cross-language machine translation method |
CN110929092A (en) * | 2019-11-19 | 2020-03-27 | 国网江苏省电力工程咨询有限公司 | Multi-event video description method based on dynamic attention mechanism |
CN111078866A (en) * | 2019-12-30 | 2020-04-28 | 华南理工大学 | Chinese text abstract generation method based on sequence-to-sequence model |
CN111833583A (en) * | 2020-07-14 | 2020-10-27 | 南方电网科学研究院有限责任公司 | Training method, device, equipment and medium for power data anomaly detection model |
-
2020
- 2020-10-29 CN CN202011182119.7A patent/CN112308402B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102750416A (en) * | 2012-06-19 | 2012-10-24 | 中国电力科学研究院 | Topological subnetting method of electromagnetic transient simulation containing switching characteristic circuit |
CN109214003A (en) * | 2018-08-29 | 2019-01-15 | 陕西师范大学 | The method that Recognition with Recurrent Neural Network based on multilayer attention mechanism generates title |
CN109816008A (en) * | 2019-01-20 | 2019-05-28 | 北京工业大学 | A kind of astronomical big data light curve predicting abnormality method based on shot and long term memory network |
CN110413729A (en) * | 2019-06-25 | 2019-11-05 | 江南大学 | Talk with generation method based on the more wheels of tail sentence-dual attention model of context |
CN110717345A (en) * | 2019-10-15 | 2020-01-21 | 内蒙古工业大学 | Translation realignment recurrent neural network cross-language machine translation method |
CN110929092A (en) * | 2019-11-19 | 2020-03-27 | 国网江苏省电力工程咨询有限公司 | Multi-event video description method based on dynamic attention mechanism |
CN111078866A (en) * | 2019-12-30 | 2020-04-28 | 华南理工大学 | Chinese text abstract generation method based on sequence-to-sequence model |
CN111833583A (en) * | 2020-07-14 | 2020-10-27 | 南方电网科学研究院有限责任公司 | Training method, device, equipment and medium for power data anomaly detection model |
Non-Patent Citations (10)
Title |
---|
ACCF:Learning Attentional Conformity for Collaborative Filtering;Liang Bin;《IEEE Access》;20190101;全文 * |
An Ensemble Model Based on Adaptive Noise Reducer and Over-Fitting Prevention LSTM for Multivariate Time Series Forecasting;Fagui Liu;《IEEE Access》;20190221;全文 * |
Memory-Augmented attention Network for Sequential Recommendation;Cheng Hu;《Springer Link》;20191029;全文 * |
What to do next:Modeling user behaviors by time-LSTM;Yu Zhu;《Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence》;20170801;全文 * |
基于CCA和数据引力场模型的社交媒体信息置信度评估方法;张萌;《微型电脑应用》;20140920;全文 * |
基于个性化推荐的图像浏览与检索相关方法研究;岑磊;《中国优秀硕士学位论文全文数据库 信息科技辑》;20120115;全文 * |
基于密度的聚类和异常检测;沙朝锋;《万方数据》;20110818;全文 * |
基于深度学习的方面级情感分析关键技术研究;申梦绮;《中国优秀硕士学位论文全文数据库 信息科技辑》;20200715;全文 * |
基于长短时记忆网络的电力负荷异常检测;马一杰;《云南大学学报(自然科学版)》;20200930;全文 * |
面向微电网时序多态不确定性的选择性数据驱动;宋晓通;《高电压技术》;20200311;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN112308402A (en) | 2021-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112308402B (en) | Power time series data abnormity detection method based on long and short term memory network | |
Ye et al. | Predicting electricity consumption in a building using an optimized back-propagation and Levenberg–Marquardt back-propagation neural network: Case study of a shopping mall in China | |
CN109685252B (en) | Building energy consumption prediction method based on cyclic neural network and multi-task learning model | |
CN112488415A (en) | Power load prediction method based on empirical mode decomposition and long-and-short-term memory network | |
CN110826791A (en) | Hybrid wind power prediction method based on long-time and short-time memory neural network | |
CN111832825B (en) | Wind power prediction method and system integrating long-term memory network and extreme learning machine | |
CN101118610A (en) | Sparseness data process modeling approach | |
CN113159389A (en) | Financial time sequence prediction method based on deep forest generation countermeasure network | |
Liu et al. | Heating load forecasting for combined heat and power plants via strand-based LSTM | |
CN116451873B (en) | Wind power generation power prediction method and system based on multi-scale double space-time network area | |
Wang et al. | A pseudo-inverse decomposition-based self-organizing modular echo state network for time series prediction | |
CN114648147A (en) | IPSO-LSTM-based wind power prediction method | |
CN113705922A (en) | Improved ultra-short-term wind power prediction algorithm and model establishment method | |
CN114240687A (en) | Energy hosting efficiency analysis method suitable for comprehensive energy system | |
CN113393119B (en) | Stepped hydropower short-term scheduling decision method based on scene reduction-deep learning | |
CN114596726A (en) | Parking position prediction method based on interpretable space-time attention mechanism | |
CN109447843B (en) | Photovoltaic output prediction method and device | |
CN116306803A (en) | Method for predicting BOD concentration of outlet water of ILSTM (biological information collection flow) neural network based on WSFA-AFE | |
CN111177881A (en) | Random production simulation method for power system containing photo-thermal-photovoltaic power generation | |
CN117877587A (en) | Deep learning algorithm of whole genome prediction model | |
CN113779861B (en) | Photovoltaic Power Prediction Method and Terminal Equipment | |
CN115660038A (en) | Multi-stage integrated short-term load prediction based on error factors and improved MOEA/D-SAS | |
CN115860232A (en) | Steam load prediction method, system, electronic device and medium | |
Liu et al. | Dynamic multi-objective optimization control for wastewater treatment process based on modal decomposition and hybrid neural network | |
CN114741952A (en) | Short-term load prediction method based on long-term and short-term memory network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |