CN116700011A - Fractional calculus energy reduction guiding method for enhanced depth transducer-attribute integrated prediction - Google Patents
Fractional calculus energy reduction guiding method for enhanced depth transducer-attribute integrated prediction Download PDFInfo
- Publication number
- CN116700011A CN116700011A CN202310867687.8A CN202310867687A CN116700011A CN 116700011 A CN116700011 A CN 116700011A CN 202310867687 A CN202310867687 A CN 202310867687A CN 116700011 A CN116700011 A CN 116700011A
- Authority
- CN
- China
- Prior art keywords
- refers
- attention
- energy consumption
- energy
- function
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 94
- 230000009467 reduction Effects 0.000 title claims abstract description 29
- 238000005265 energy consumption Methods 0.000 claims abstract description 137
- 238000004519 manufacturing process Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 100
- 239000013598 vector Substances 0.000 claims description 35
- 230000007246 mechanism Effects 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 25
- 239000011159 matrix material Substances 0.000 claims description 16
- 230000007774 longterm Effects 0.000 claims description 15
- 230000004069 differentiation Effects 0.000 claims description 14
- 238000009826 distribution Methods 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 10
- 238000004821 distillation Methods 0.000 claims description 9
- 230000001932 seasonal effect Effects 0.000 claims description 8
- 230000005653 Brownian motion process Effects 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 230000003068 static effect Effects 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 239000006185 dispersion Substances 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000009827 uniform distribution Methods 0.000 claims description 6
- 239000000446 fuel Substances 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000011176 pooling Methods 0.000 claims description 3
- 230000010339 dilation Effects 0.000 claims description 2
- 238000005315 distribution function Methods 0.000 claims description 2
- 230000005611 electricity Effects 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 claims description 2
- 239000002803 fossil fuel Substances 0.000 claims description 2
- 238000000465 moulding Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 230000001737 promoting effect Effects 0.000 claims description 2
- 230000000306 recurrent effect Effects 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a fractional order calculus energy reduction guiding method for enhanced depth transducer-Attention integrated prediction. The method considers the energy consumption of the comprehensive energy system, takes the energy consumption influencing factors and the energy production as inputs, and outputs the optimal energy reduction guiding signals. The transform-Attention network and the high-efficiency time sequence prediction network combined with the time sequence Attention unit in the method can solve the problem of prediction of the reference energy consumption and are used for outputting the optimal prediction result; the fractional order random dynamic calculus controller in the method can obtain the optimal energy-reducing guide signal through the predicted energy consumption and energy production. The method can reduce the overall energy consumption of the comprehensive energy system and improve the stability of the comprehensive energy system.
Description
Technical Field
The invention belongs to the field of energy control technology of an electric power system, the field of artificial intelligence and the field of calculus application in mathematical application, and relates to a control method of an artificial intelligence and comprehensive energy system, which is suitable for long-term energy reduction guidance of the comprehensive energy system.
Background
The patent name of 2020108660490 of 2020.08.25 is a long-term dynamic game strategy under the condition of incomplete information, only long-term dynamic games among research objects are considered, and influence factors of the research objects are not added into a control strategy. The patent application 2022.01.18 with the application number 2021111974623 is named as a dynamic differentiation method of a long-term price guiding method of dynamic differentiation control of a flexible energy hybrid network, which only considers the situation that random dynamic differentiation is differentiated in integer order, but the energy consumption and the time are in a nonlinear relation and have non-Markov properties, and the integer order random dynamic differentiation has limitations in describing the relation of the non-Markov properties. The patent with the application number 2022112767254 of 2022.10.18 is named as a fractional order long-term price guiding method for enhancing deep attention bidirectional prediction, which uses fractional order random dynamic differentiation for guiding the energy consumption of the electric automobile, but the method is only limited to a single object of the electric automobile, the whole energy system is not considered, the influence of the energy consumption of the single electric automobile on the whole energy system is very small, and the energy consumption management of the whole energy system is lacking.
Therefore, a fractional calculus energy reduction guiding method for enhancing depth conversion-Attention integrated prediction is provided, and the method can consider the influence of energy consumption states, energy consumption coefficients, seasons, air temperatures and admission rules on energy consumption; the method can play the regulating function of energy consumption in the comprehensive energy system, and solves the problem of unbalanced energy supply and energy consumption in the comprehensive energy system; the method utilizes a transducer-Attention network and a high-efficiency time sequence prediction network combined with a time sequence Attention unit to predict the reference energy consumption of the user, so that the problem of predicting the energy consumption of the user can be solved; the method introduces fractional order integration of the wiener process into the controller, so that random fluctuation of noise signals and random disturbance of the system can be better described; the method is characterized in that from the perspective of a comprehensive energy system, the energy of the system is guided through the energy reduction guiding signal, and the energy consumption is reduced under the condition of meeting the energy consumption side experience; the method reduces the energy consumption of the comprehensive energy system in the long term and can improve the stability of the comprehensive energy system.
Disclosure of Invention
The invention provides a fractional calculus energy reduction guiding method for enhanced depth conversion-Attention integrated prediction, which combines a conversion-Attention network, a high-efficiency time sequence prediction network combined with a time sequence Attention unit and a fractional random dynamic calculus controller, is used for long-term energy reduction guiding of a comprehensive energy system, and has the functions of improving the energy utilization rate, improving the stability of the comprehensive energy system, promoting renewable energy to be integrated into the comprehensive energy system and reducing energy consumption; the method comprises the following steps in the using process:
step (1): establishing an operation frame for energy reduction guidance of the comprehensive energy system; the comprehensive energy system obtains energy production from power plants, boilers and fossil fuels, collects expected required energy consumption from an energy consumption side, compares the energy production with the expected required energy consumption, finds an optimal energy-reducing guide signal through an energy-reducing guide method, and then sends the energy-reducing guide signal to the energy consumption side to guide energy consumption of industries, businesses and residences and reduce the energy consumption;
step (2): providing fractional calculus control for enhancing depth transducer-Attention integrated prediction, and predicting the reference energy consumption of the comprehensive energy system through a transducer-Attention network and a high-efficiency time sequence prediction network combined with a time sequence Attention unit;
firstly, preprocessing data, and extracting features of the processed data; then, respectively predicting the processed characteristic data by using a transducer-Attention network method and a high-efficiency time sequence prediction network combined with a time sequence Attention unit, and selecting a prediction result to obtain a predicted reference energy consumption;
the transform-Attention network is a deep network architecture taking multi-head Attention as a basic operation unit, and can acquire balance between long-term dependence acquisition and low time complexity acquisition; the prediction precision is improved by proposing a ProbSparse self-attention mechanism, a self-attention distillation mechanism and a generative decoder;
the transducer-attribute network consists of an input layer, an encoder, a decoder, a full-connection layer and an output layer;
first, history of electric energy, heat energy and fuelAll consumption is input into an encoder to be encoded to obtain a mapping sequence, then target values to be predicted in a long sequence are filled into zero, the target values and the mapping sequence obtained by the encoder are input into a decoder together, and prediction output elements to be obtained are directly generated; the encoder inputs the t-th input sequence χ t Molding into a matrix:
in the method, in the process of the invention,refers to a coding matrix; t is the time t; />Refers to the size L x X d set of real matrices;refers to real numbers; l (L) x Refers to the length of the sequence; d is the input dimension;
the probspark self-Attention mechanism employed by the transform-Attention network differs from the standard self-Attention mechanism, which employs scaled dot product pairs of:
wherein A (Q, K, V) is a self-attention mechanism value indicative of the index; q is a query vector; k refers to the vector being queried; v is the content vector; KT is the transpose of the queried vector; softmax () is a normalized exponential function; l (L) Q Is the length of Q; l (L) K Is the length of K;refers to the size L Q X d set of real matrices; />Refers to the size L K X d set of real matrices;
the probspark self-attention mechanism defines the scaled dot product pair of the standard attention mechanism as a kernel smoother in a probabilistic form as
Wherein A is i (q i K, V) refers to the self-attention mechanism value in the form of probability; i. j and l refer to the number of rows; q i Refers to row i of Q; k (k) j Refers to row j of K; k (k) l Refers to the first row of K; v j Refers to row j of V; k () refers to a probability function; p (k) j |q i ) Refers to k j At q i The following conditional probability distribution;refers to the sum of conditional probabilities;
probability function k (q in kernel smoother i ，k j ) The asymmetric index kernel used is:
in the method, in the process of the invention,is k j Is a transpose of (2);
the probability distribution of the query vector satisfies the uniform distribution:
wherein q (k) j |q i ) Refers to the uniform distribution of query vectors;
if p (k) j |q i ) Near uniform distribution q (k) j |q i ) The self-attention becomes the value V, which is redundant for the prediction output, so the similarity between the distributions p and q is used to distinguish important parts of the sequence, as measured by Kullback-Leibler divergence:
wherein KL (q||p) refers to the Kullback-Leibler divergence between the distributions p and q;refers to k l Is a transpose of (2); 1n () is a logarithmic function based on e;
removal of lnL in the Kullback-Leibler divergence K This constant, the sparsity measure for the ith query vector is defined as:
wherein M (q i K) refers to the sparsity measure of the ith query vector;
the sparsity measure in the standard self-attention mechanism yields the attention value of the probspark self-attention mechanism as:
wherein A is s (Q, K, V) refers to the attention value of the ProbSparse self-attention mechanism;refers to a sparse matrix of the same size as Q, comprising only sparsity metrics M (Q i ，K)；
By calculating the ProbSparse self-attention value of each element in each coding matrix, the distillation process of the attention value is to extract the attention value of the ProbSparse self-attention mechanism, and the attention is paidThe force value gives the preferred feature privileges with dominant features and generates a focused self-attention feature map at the next layer;the forward entry into the (n+1) layer from the n-th layer by distillation is:
in the method, in the process of the invention,refers to->A layer n self-care feature map; />Refers to->A self-care feature map of layer (n+1);
MaxPool () refers to the max pooling function; ELU () refers to an activation function; conv1d () refers to performing a 1-dimensional convolution filter in the time dimension using an activation function; [] AB Refers to the basic operations in the self-attention and attention block that contain multiple heads probspark;
the generating type decoder is formed by stacking 2 identical multi-head attention layers, and the generating type prediction can effectively relieve the problem of speed reduction in long-time prediction; the vector input to the decoder is:
in the method, in the process of the invention,is a vector pointing to the decoder input; />The initial word segmentation vector is referred to;refers to a placeholder vector for the target sequence, each element being 0; ltoken refers to the length of the initial segmentation vector; l (L) y Refers to the length of the placeholder vector of the target sequence; concat () refers to a splice operation function;
by combiningAnd->Finally, the vector is passed through the full connection layer after decoding operation to obtain the final energy consumption to be predicted, which is:
in the method, in the process of the invention,the energy consumption is predicted by a transducer-attribute network; />The real number matrix set with the dy output value is formed; dy refers to the dimension of the output data; />Refers to the o-th vector constituting the target output;
the efficient timing prediction network in combination with the timing attention unit does not use a recurrent neural network, but rather uses an attention mechanism to parallelize the processing of the time evolution; an efficient timing prediction network in combination with a timing attention unit breaks the timing attention down into two parts: static attention and dynamic attention; static attention uses small core depth convolution and dilation convolution to achieve a large receptive field, capturing long-term dependencies of sequences; the dynamic attention learns the time sequence weight by utilizing the difference of the time sequence attention, thereby capturing the variation trend among the sequences; the high-efficiency time sequence prediction network combined with the time sequence attention unit utilizes a differential divergence regularization method for optimizing a loss function of time sequence prediction learning; the differential divergence regularization method converts the difference between the predicted value and the true value into probability distribution, calculates the Kullback-Leibler divergence between the predicted value and the true value, and enables an efficient time sequence prediction network combined with a time sequence attention unit to learn the inherent change rule in the time sequence; the input matrix of the high-efficiency time sequence prediction network combined with the time sequence attention unit is that the historical consumption of electric energy, heat energy and fuel is input as follows:
wherein T is the length of the input time series;refers to a real matrix set of size T;
the predicted values for the neural network map are:
in the method, in the process of the invention,the predicted value of the neural network model mapping is referred to; />Is a neural network model;
the predicted value and the true value mapped by the neural network model are subjected to forward difference as follows:
in the method, in the process of the invention,is the forward difference of the predicted values of the neural network map; />The (i+1) th predicted value mapped by the neural network model is referred to; />Refers to the ith predicted value mapped by the neural network model; />Refers to the forward difference of the true values;refers to the true value +.>Data i+1th; />Refers to the true value +.>Ith data;
the forward difference is converted into probability by Softmax () function as follows:
wherein σ () refers to a probability distribution function;refers to dynamic attention; />Refers to static attention; τ is the temperature coefficient; exp () is an exponential function based on e;
by calculating probability distributionAnd->The obtained micro-dispersion regularization function of the Kullback-Leibler dispersion is as follows:
in the method, in the process of the invention,refers to a micro-dispersion regularization function; t' is the length of the time series that needs to be predicted;
the efficient time sequence prediction network combined with the time sequence attention unit performs end-to-end training in a completely unsupervised manner, and the loss function of the evaluation difference consisting of the mean square error loss and the constant lambda weighted differential divergence regularization is as follows:
in the method, in the process of the invention,is a loss function that evaluates the difference; lambda is a constant;
the weight parameters of the high-efficiency time sequence prediction network combined with the time sequence attention unit can be solved through the loss function, and the weight parameters are as follows:
in the formula Θ * Is the value of the solved weight parameter; argmin is a solution corresponding to the minimum value of the solving objective function; Θ is a weight parameter;
the efficient time sequence prediction network combined with the time sequence attention unit predicts the following T' from the time t+1, and the efficient time sequence prediction network combined with the time sequence attention unit can learn the slaveThe energy consumption obtained by the high-efficiency time sequence prediction network combined with the time sequence attention unit is as follows:
in the method, in the process of the invention,refers to the energy consumption predicted by the network through the efficient time sequence prediction combined with the time sequence attention unit; />Refers to a real matrix set of size T';
step (3): fractional order calculus control of enhanced depth transducer-attribute integrated prediction is used for energy reduction guidance of a comprehensive energy system; inputting the predicted reference energy consumption into a fractional order random dynamic calculus controller, and outputting an energy reduction guide signal by the fractional order random dynamic calculus controller;
the energy consumption of the comprehensive energy system comprises electric power consumption, heat energy consumption and fuel consumption, and the reference energy consumption obtained by using the energy consumption predicted by the converter-Attention network and the high-efficiency time sequence prediction network combined with the time sequence Attention unit through the reference energy consumption prediction function is as follows:
wherein D is t Refers to a predicted reference energy consumption; forecast () refers to a reference energy consumption amount prediction function;
the energy consumption state differentiation output by the fractional order random dynamic calculus controller is as follows:
wherein, alpha refers to the order of fractional calculus; s is S t Refers to the energy consumption state; d, d α S t Refers to fractional differentiation of the energy consumption state;refers to the energy obtained by the comprehensive energy system; pt refers to the energy consumption predicted by the fractional order random dynamic calculus controller; d, d α t refers to fractional differentiation over time; n (N) noise Refers to noise intensity; />Refers to fractional order integration of the wiener process; w (W) t Refers to the wiener process;
the comprehensive energy system comprises an energy generation side and an energy consumption side, wherein the energy consumption is output by the utilization fractional order random dynamic calculus controller, and the change of the energy consumption is as follows:
in the method, in the process of the invention,refers to the amount of change in energy consumption; gamma () refers to a logical function; l (L) 1 、l 2 、l 3 、l 4 And l 5 The energy consumption state function, the energy consumption coefficient function, the seasonal function, the air temperature function and the admission rule function in the logic function gamma (); sta (State of America)() Refers to an energy consumption state function; delta is a parameter of the energy consumption state function Sta (); coe () refers to an energy consumption coefficient function; c t Refers to the energy consumption coefficient; beta refers to a parameter of an energy consumption coefficient function Coe (); wea () refers to a seasonal function; w (w) t Refers to the seasonal situation; tem () refers to an air temperature function; h is a t Refers to air temperature; rul () refers to an admission rule function; u (u) t Refers to an admission rule; θ refers to a parameter of energy consumption;
the predicted electricity load is obtained through a fractional order random dynamic differential controller as follows:
wherein p is energy Refers to the proportion of renewable energy sources;refers to a sign function;
the sign function S () is:
the logical function γ () is:
where l is a argument of a logical function γ ();
step (4): taking into account dynamic energy consumption changes caused by energy consumption states, energy consumption coefficients, seasons, air temperatures and admission rules, generating a descending energy guiding signal by a fractional order random dynamic calculus controller;
the influence factors of energy consumption, the predicted reference energy consumption and the energy provided by the comprehensive energy system are used as input variables of the fractional order random dynamic calculus controller, and the energy reduction guide signal is used as output variable;
the energy consumption state function Sta () is:
Sta(S t ，δ 1 ，δ 2 ，δ 3 ，δ 4 )＝(1-2S t +δ 1 ×[1-(2S t -1) 2 ]}×[δ 2 +δ 3 ×(2S t -1) 2 +δ 4 ×(2S t -1) 6 ] (26)
in delta 1 、δ 2 、δ 3 And delta 4 The energy consumption state function Sta () is a coefficient for controlling the deflection degree, the variable constant term, the variable quadratic term and the variable sixth term of the energy consumption state;
the energy consumption coefficient function Coe () is:
wherein TNz is the total number of splines; z refers to the z-th spline; iz () refers to an I spline function;
the seasonal function Wea () is:
where sin () refers to a sine function;
the air temperature function Tem () is:
Tem(h t )＝0.6 exp(h t )+8h t (29)
the admission rule function Rul () is:
the predicted reference energy consumption and the energy supply are used as input variables of a fractional order random dynamic calculus controller, the predicted energy consumption is output through a fractional order random dynamic derivative equation, and then an optimal energy reduction guide signal is solved by utilizing an objective function; the function of solving the energy-reducing guide signal by using the fractional order random dynamic calculus controller is as follows:
wherein period refers to a prediction period; pre (D) t ，c t ) Is expressed by the energy consumption coefficient c t A predicted energy consumption function for the variable;
step (5): the energy-reducing guide signal is applied to the comprehensive energy system, the energy consumption side is guided to use energy, the energy utilization rate is improved, the stability of the comprehensive energy system is enhanced, the integration of renewable energy sources is promoted, and the energy consumption of the comprehensive energy system is reduced.
Compared with the prior art, the invention has the following advantages and effects:
(1) The invention predicts the reference energy consumption of the user by utilizing the data preprocessing function, the transducer-Attention network and the high-efficiency time sequence prediction network combined with the time sequence Attention unit, and simultaneously introduces the fractional integral of the wiener process into the fractional random dynamic calculus controller, thereby improving the accuracy of the energy-reducing guide signal.
(2) The invention considers the influence of energy consumption state, energy consumption coefficient, season, air temperature and admittance rule on energy consumption from the angle of the comprehensive energy system, and guides the energy consumption side to consume energy through the energy reduction guiding signal, thereby reducing the energy consumption of the comprehensive energy system.
(3) Compared with the patent name 2020108660490 of 2020.08.25 application, the method disclosed by the invention is a multi-group distributed flexible energy service provider long-term price guiding method, not only considers dynamic games between energy production and energy consumption, but also considers influencing factors of energy consumption in energy reduction guiding of a comprehensive energy system.
(4) Compared with a patent with 2021111974623 of 2022.01.18 application, the method disclosed by the invention is a dynamic differentiation method of a long-term price guiding method of dynamic differentiation control of a flexible energy hybrid network, and the method can better describe the nonlinear relation and the non-Markov property between the energy consumption and the time by adding the fractional order random dynamic differentiation into a controller.
(5) Compared with the 2022112767254 patent name of 2022.10.18 application, the method for guiding the fractional order long-term price for enhancing the deep attention bi-directional prediction expands a study object from a single electric automobile to a comprehensive energy system, and meanwhile, fractional order integration of a wiener process is added into a controller, so that random fluctuation of noise signals and random disturbance of the system can be better described, and the accuracy of energy consumption guiding signals is improved.
Drawings
FIG. 1 is a control framework diagram of a fractional calculus energy reduction guidance method for enhanced depth transform-Attention integrated prediction of the method of the present invention.
FIG. 2 is a transducer-Attention network of the method of the present invention.
FIG. 3 is a high efficiency timing prediction network incorporating a timing attention unit of the method of the present invention.
Detailed Description
The invention provides a fractional calculus energy reduction guiding method for enhanced depth transducer-attribute integrated prediction, which is described in detail below with reference to the accompanying drawings:
FIG. 1 is a control framework diagram of a fractional calculus energy reduction guidance method for enhanced depth transform-Attention integrated prediction of the method of the present invention. First, raw energy consumption data is obtained from industry, business, and house and data preprocessing is performed. And then, respectively predicting the preprocessed data through a transducer-Attention network and a high-efficiency time sequence prediction network combined with a time sequence Attention unit, and determining the predicted reference energy consumption. And finally, inputting the predicted reference energy consumption into a fractional order random dynamic calculus controller, and outputting an optimal energy reduction guiding signal to guide the consumption of energy sources of industry, business and residence by combining the energy consumption influencing factors and the energy production.
FIG. 2 is a transducer-Attention network of the method of the present invention. First the encoder receives a large number of long sequence inputs. The transform-Attention network replaces standard self-Attention with probespark self-Attention. Then, distillation operation is carried out on the multi-head attention, the attention subjected to the distillation operation is a pyramid dependency relationship, and the dominant attention is extracted to a decoder through layer-by-layer distillation, so that the network size is greatly reduced. Finally, the decoder receives the long sequence input, fills the target element to zero, calculates the weighted attention composition of the feature map, and immediately predicts the output element in a generative style.
FIG. 3 is a high efficiency timing prediction network incorporating a timing attention unit of the method of the present invention. The overall structure of the efficient timing prediction network in combination with the timing attention unit is the data input, encoder, timing attention unit, decoder and data output. In the time sequential attention unit, first, the static attention generated by the actual value is converted by small kernel depth convolution, expandable depth convolution, and 1*1 convolution to obtain a first output vector. The dynamic attention of the neural network map is then passed through the average pooling layer and the full connection layer to obtain a second output vector. Finally, the two output vectors are combined and sent to the decoder, which generates the final data output.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes using the descriptions and drawings of the present invention or directly or indirectly applied to other related technical fields are included in the scope of the invention.
Claims (1)
1. The fractional calculus energy reduction guiding method for enhancing depth conversion-Attention integrated prediction is characterized by combining a conversion-Attention network, a high-efficiency time sequence prediction network combined with a time sequence Attention unit and a fractional random dynamic calculus controller, is used for long-term energy reduction guiding of a comprehensive energy system, and has the functions of improving the energy utilization rate, improving the stability of the comprehensive energy system, promoting renewable energy to be integrated into the comprehensive energy system and reducing energy consumption; the method comprises the following steps in the using process:
step (1): establishing an operation frame for energy reduction guidance of the comprehensive energy system; the comprehensive energy system obtains energy production from power plants, boilers and fossil fuels, collects expected required energy consumption from an energy consumption side, compares the energy production with the expected required energy consumption, finds an optimal energy-reducing guide signal through an energy-reducing guide method, and then sends the energy-reducing guide signal to the energy consumption side to guide energy consumption of industries, businesses and residences and reduce the energy consumption;
step (2): providing fractional calculus control for enhancing depth transducer-Attention integrated prediction, and predicting the reference energy consumption of the comprehensive energy system through a transducer-Attention network and a high-efficiency time sequence prediction network combined with a time sequence Attention unit;
firstly, preprocessing data, and extracting features of the processed data; then, respectively predicting the processed characteristic data by using a transducer-Attention network method and a high-efficiency time sequence prediction network combined with a time sequence Attention unit, and selecting a prediction result to obtain a predicted reference energy consumption;
the transform-Attention network is a deep network architecture taking multi-head Attention as a basic operation unit, and can acquire balance between long-term dependence acquisition and low time complexity acquisition; the prediction precision is improved by proposing a ProbSparse self-attention mechanism, a self-attention distillation mechanism and a generative decoder;
the transducer-attribute network consists of an input layer, an encoder, a decoder, a full-connection layer and an output layer;
firstly, all the historical consumption of electric energy, heat energy and fuel are input into an encoder to be encoded to obtain a mapping sequence, then target values to be predicted in a long sequence are filled to be zero, the target values and the mapping sequence obtained by the encoder are input into a decoder together, and prediction output elements to be obtained are directly generated; the encoder inputs the t-th input sequence χ t Molding into a matrix:
in the method, in the process of the invention,refers to a coding matrix; t is the time t; />Refers to the size L x X d set of real matrices; />Refers to real numbers; l (L) x Refers to the length of the sequence; d is the input dimension;
the probspark self-Attention mechanism employed by the transform-Attention network differs from the standard self-Attention mechanism, which employs scaled dot product pairs of:
wherein A (Q, K, V) is a self-attention mechanism value indicative of the index; q is a query vector; k refers to the vector being queried; v is the content vector; k (K) T Is a transpose of the queried vector; softmax () is a normalized exponential function; l (L) Q Is the length of Q; l (L) K Is the length of K;refers to the size L Q X d set of real matrices; />Refers to the size L K X d set of real matrices;
the probspark self-attention mechanism defines the scaled dot product pair of the standard attention mechanism as a kernel smoother in probabilistic form as:
wherein A is i (q i K, V) refers to the self-attention mechanism value in the form of probability; i. j and l refer to the number of rows; q i Refers to row i of Q; k (k) j Refers to row j of K; k (k) l Refers to the first row of K; v j Refers to row j of V; k () refers to a probability function; p (k) j |q i ) Refers to k j At q i The following conditional probability distribution;refers to the sum of conditional probabilities;
probability function k (q in kernel smoother i ,k j ) The asymmetric index kernel used is:
in the method, in the process of the invention,is k j Is a transpose of (2);
the probability distribution of the query vector satisfies the uniform distribution:
wherein q (k) j |q i ) Refers to the uniform distribution of query vectors;
if p (k) j |q i ) Near uniform distribution q (k) j |q i ) The self-attention becomes the value V, which is redundant for the prediction output, so the similarity between the distributions p and q is used to distinguish important parts of the sequence, as measured by Kullback-Leibler divergence:
wherein KL (q||p) refers to the Kullback-Leibler divergence between the distributions p and q;refers to k l Is a transpose of (2); ln () is a logarithmic function based on e;
removal of lnL in the Kullback-Leibler divergence K This constant, the sparsity measure for the ith query vector is defined as:
wherein M (q i K) refers to the sparsity measure of the ith query vector;
the sparsity measure in the standard self-attention mechanism yields the attention value of the probspark self-attention mechanism as:
wherein A is s (Q, K, V) refers to the attention value of the ProbSparse self-attention mechanism;refers to a sparse matrix of the same size as Q, comprising only sparsity metrics M (Q i ,K)；
By calculating the ProbSparse self-attention value of each element in each coding matrix, the distillation process of the attention value is to extract the attention value of the ProbSparse self-attention mechanism, endow the attention value with better feature privileges with dominant features, and generate a focused self-attention feature map at the next layer;the forward entry into the (n+1) layer from the n-th layer by distillation is:
in the method, in the process of the invention,refers to->A layer n self-care feature map; />Refers to->A self-care feature map of layer (n+1); maxPool () refers to the max pooling function; ELU () refers to an activation function; conv1d () refers to performing a 1-dimensional convolution filter in the time dimension using an activation function; [] AB Refers to the basic operations in the self-attention and attention block that contain multiple heads probspark;
the generating type decoder is formed by stacking 2 identical multi-head attention layers, and the generating type prediction can effectively relieve the problem of speed reduction in long-time prediction; the vector input to the decoder is:
in the method, in the process of the invention,is a vector pointing to the decoder input; />The initial word segmentation vector is referred to; />Refers to a placeholder vector for the target sequence, each element being 0; l (L) token Refers to the length of the initial segmentation vector; l (L) y Refers to the length of the placeholder vector of the target sequence; concat () refers to a splice operation function;
by combiningAnd->Finally, the vector is passed through the full connection layer after decoding operation to obtain the final energy consumption to be predicted, which is:
in the method, in the process of the invention,the energy consumption is predicted by a transducer-attribute network; />Refers to the output value with the size d y A real number matrix set; d, d y Refers to the dimension of the output data; />Refers to the o-th vector constituting the target output;
the efficient timing prediction network in combination with the timing attention unit does not use a recurrent neural network, but rather uses an attention mechanism to parallelize the processing of the time evolution; an efficient timing prediction network in combination with a timing attention unit breaks the timing attention down into two parts: static attention and dynamic attention; static attention uses small core depth convolution and dilation convolution to achieve a large receptive field, capturing long-term dependencies of sequences; the dynamic attention learns the time sequence weight by utilizing the difference of the time sequence attention, thereby capturing the variation trend among the sequences; the high-efficiency time sequence prediction network combined with the time sequence attention unit utilizes a differential divergence regularization method for optimizing a loss function of time sequence prediction learning; the differential divergence regularization method converts the difference between the predicted value and the true value into probability distribution, calculates the Kullback-Leibler divergence between the predicted value and the true value, and enables an efficient time sequence prediction network combined with a time sequence attention unit to learn the inherent change rule in the time sequence; the input matrix of the high-efficiency time sequence prediction network combined with the time sequence attention unit is that the historical consumption of electric energy, heat energy and fuel is input as follows:
wherein T is the length of the input time series;refers to a real matrix set of size T;
the predicted values for the neural network map are:
in the method, in the process of the invention,the predicted value of the neural network model mapping is referred to; />Is a neural network model;
the predicted value and the true value mapped by the neural network model are subjected to forward difference as follows:
in the method, in the process of the invention,is the forward difference of the predicted values of the neural network map; />The (i+1) th predicted value mapped by the neural network model is referred to; />Refers to the ith predicted value mapped by the neural network model; />Refers to the forward difference of the true values; />Refers to the true value +.>Data i+1th; />Refers to the true value +.>Ith data;
the forward difference is converted into probability by Softmax () function as follows:
wherein σ () refers to a probability distribution function;refers to dynamic attention; />Refers to static attention; τ is the temperature coefficient; exp () is an exponential function based on e;
by calculating probability distributionAnd->The obtained micro-dispersion regularization function of the Kullback-Leibler dispersion is as follows:
in the method, in the process of the invention,refers to a micro-dispersion regularization function; t' is the length of the time series that needs to be predicted;
the efficient time sequence prediction network combined with the time sequence attention unit performs end-to-end training in a completely unsupervised manner, and the loss function of the evaluation difference consisting of the mean square error loss and the constant lambda weighted differential divergence regularization is as follows:
in the method, in the process of the invention,is a loss function that evaluates the difference; lambda is a constant;
the weight parameters of the high-efficiency time sequence prediction network combined with the time sequence attention unit can be solved through the loss function, and the weight parameters are as follows:
in the formula Θ * Is the value of the solved weight parameter; argmin is a solution corresponding to the minimum value of the solving objective function; Θ is a weight parameter;
the efficient time sequence prediction network combined with the time sequence attention unit predicts the following T' from the time t+1, and the efficient time sequence prediction network combined with the time sequence attention unit can learn the slaveThe energy consumption obtained by the high-efficiency time sequence prediction network combined with the time sequence attention unit is as follows:
in the method, in the process of the invention,refers to the energy consumption predicted by the network through the efficient time sequence prediction combined with the time sequence attention unit;refers to a real matrix set of size T';
step (3): fractional order calculus control of enhanced depth transducer-attribute integrated prediction is used for energy reduction guidance of a comprehensive energy system; inputting the predicted reference energy consumption into a fractional order random dynamic calculus controller, and outputting an energy reduction guide signal by the fractional order random dynamic calculus controller;
the energy consumption of the comprehensive energy system comprises electric power consumption, heat energy consumption and fuel consumption, and the reference energy consumption obtained by using the energy consumption predicted by the converter-Attention network and the high-efficiency time sequence prediction network combined with the time sequence Attention unit through the reference energy consumption prediction function is as follows:
wherein D is t Refers to a predicted reference energy consumption; forecast () refers to a reference energy consumption amount prediction function;
the energy consumption state differentiation output by the fractional order random dynamic calculus controller is as follows:
wherein, alpha refers to the order of fractional calculus; s is S t Refers to the energy consumption state; d, d α S t Refers to fractional differentiation of the energy consumption state;refers to the energy obtained by the comprehensive energy system; p (P) t The energy consumption predicted by the fractional order random dynamic calculus controller is referred to; d, d α t refers to fractional differentiation over time; n (N) noise Refers to noise intensity; />Refers to fractional order integration of the wiener process; w (W) t Refers to the wiener process;
the comprehensive energy system comprises an energy generation side and an energy consumption side, wherein the energy consumption is output by the utilization fractional order random dynamic calculus controller, and the change of the energy consumption is as follows:
in the method, in the process of the invention,refers to the amount of change in energy consumption; gamma () refers to a logical function; l (L) 1 、l 2 、l 3 、l 4 And l 5 The energy consumption state function, the energy consumption coefficient function, the seasonal function, the air temperature function and the admission rule function in the logic function gamma (); sta () refers to an energy consumption state function; delta is a parameter of the energy consumption state function Sta (); coe () refers to an energy consumption coefficient function; c t Refers to the energy consumption coefficient; beta refers to a parameter of an energy consumption coefficient function Coe (); wea () refers to a seasonal function; w (w) t Refers to the seasonal situation; tem () refers to an air temperature function; h is a t Refers to air temperature; rul () refers to an admission rule function; u (u) t Refers to an admission rule; θ refers to a parameter of energy consumption;
the predicted electricity load is obtained through a fractional order random dynamic differential controller as follows:
wherein p is energy Refers to the proportion of renewable energy sources;refers to a sign function;
the sign function S () is:
the logical function γ () is:
where l is a argument of a logical function γ ();
step (4): taking into account dynamic energy consumption changes caused by energy consumption states, energy consumption coefficients, seasons, air temperatures and admission rules, generating a descending energy guiding signal by a fractional order random dynamic calculus controller;
the influence factors of energy consumption, the predicted reference energy consumption and the energy provided by the comprehensive energy system are used as input variables of the fractional order random dynamic calculus controller, and the energy reduction guide signal is used as output variable;
the energy consumption state function Sta () is:
Sta(S t ,δ 1 ,δ 2 ，δ 3 ,δ 4 )＝{1-2S t +δ 1 ×[1-(2S t -1) z l}×[δ 2 +δ 3 ×(2S t -1) z +δ 4 ×(2S t -1) 6 ] (26)
in delta 1 、δ 2 、δ 3 And delta 4 The energy consumption state function Sta () is a coefficient for controlling the deflection degree, the variable constant term, the variable quadratic term and the variable sixth term of the energy consumption state;
the energy consumption coefficient function Coe () is:
in TN z Refers to the total number of splines; z refers to the z-th spline; i z () Refers to I spline functions;
the seasonal function Wea () is:
where sin () refers to a sine function;
the air temperature function Tem () is:
Tem(h t )＝0.6exp(h t )+8h t (29)
the admission rule function Rul () is:
the predicted reference energy consumption and the energy supply are used as input variables of a fractional order random dynamic calculus controller, the predicted energy consumption is output through a fractional order random dynamic derivative equation, and then an optimal energy reduction guide signal is solved by utilizing an objective function; the function of solving the energy-reducing guide signal by using the fractional order random dynamic calculus controller is as follows:
wherein period refers to a prediction period; pre (D) t ,c t ) Is expressed by the energy consumption coefficient c t A predicted energy consumption function for the variable;
step (5): the energy-reducing guide signal is applied to the comprehensive energy system, the energy consumption side is guided to use energy, the energy utilization rate is improved, the stability of the comprehensive energy system is enhanced, the integration of renewable energy sources is promoted, and the energy consumption of the comprehensive energy system is reduced.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310867687.8A CN116700011A (en) | 2023-07-15 | 2023-07-15 | Fractional calculus energy reduction guiding method for enhanced depth transducer-attribute integrated prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310867687.8A CN116700011A (en) | 2023-07-15 | 2023-07-15 | Fractional calculus energy reduction guiding method for enhanced depth transducer-attribute integrated prediction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116700011A true CN116700011A (en) | 2023-09-05 |
Family
ID=87825917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310867687.8A Pending CN116700011A (en) | 2023-07-15 | 2023-07-15 | Fractional calculus energy reduction guiding method for enhanced depth transducer-attribute integrated prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116700011A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113947427A (en) * | 2021-10-14 | 2022-01-18 | 广西大学 | Long-term price guiding method for dynamic differential control of flexible energy hybrid network |
-
2023
- 2023-07-15 CN CN202310867687.8A patent/CN116700011A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113947427A (en) * | 2021-10-14 | 2022-01-18 | 广西大学 | Long-term price guiding method for dynamic differential control of flexible energy hybrid network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109685252B (en) | Building energy consumption prediction method based on cyclic neural network and multi-task learning model | |
| Ke et al. | Short-term electrical load forecasting method based on stacked auto-encoding and GRU neural network | |
| CN112149879B (en) | New energy medium-and-long-term electric quantity prediction method considering macroscopic volatility classification | |
| CN108197751A (en) | Seq2seq network Short-Term Load Forecasting Methods based on multilayer Bi-GRU | |
| CN113988449B (en) | Wind power prediction method based on transducer model | |
| CN114022311B (en) | Comprehensive energy system data compensation method for generating countermeasure network based on time sequence condition | |
| CN116700011A (en) | Fractional calculus energy reduction guiding method for enhanced depth transducer-attribute integrated prediction | |
| CN115481788B (en) | Phase change energy storage system load prediction method and system | |
| Zhu et al. | Parallel interaction spatiotemporal constrained variational autoencoder for soft sensor modeling | |
| CN114781744A (en) | Deep learning multi-step long radiance prediction method based on codec | |
| CN116014722A (en) | Sub-solar photovoltaic power generation prediction method and system based on seasonal decomposition and convolution network | |
| CN115169742A (en) | Short-term wind power generation power prediction method | |
| CN110738363B (en) | Photovoltaic power generation power prediction method | |
| CN116843057A (en) | Wind power ultra-short-term prediction method based on LSTM-ViT | |
| CN117648469A (en) | Cross double-tower structure answer selection method based on contrast learning | |
| CN115640901A (en) | Small sample load prediction method based on hybrid neural network and generation countermeasure | |
| CN113393119B (en) | Stepped hydropower short-term scheduling decision method based on scene reduction-deep learning | |
| CN115409369A (en) | Comprehensive energy system reliability evaluation method based on mechanism and data hybrid driving | |
| CN112785056B (en) | Short-term load prediction method based on fusion of Catboost and LSTM models | |
| CN116483036B (en) | Transformer-based self-encoder soft measurement modeling method | |
| CN110674460B (en) | E-Seq2Seq technology-based data driving type unit combination intelligent decision method | |
| CN112667788A (en) | Novel BERTEXT-based multi-round dialogue natural language understanding model | |
| CN112232570A (en) | Forward active total electric quantity prediction method and device and readable storage medium | |
| CN115630987A (en) | Fractional order long-term price guiding method for enhancing depth attention bidirectional prediction | |
| Rohatgi et al. | Machine Learning-based Prediction of Departure from Nucleate Boiling Power for the PSBT Benchmark |
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 |