CN114648178A - Operation and maintenance strategy optimization method of electric energy metering device based on DDPG algorithm - Google Patents
Operation and maintenance strategy optimization method of electric energy metering device based on DDPG algorithm Download PDFInfo
- Publication number
- CN114648178A CN114648178A CN202210515703.2A CN202210515703A CN114648178A CN 114648178 A CN114648178 A CN 114648178A CN 202210515703 A CN202210515703 A CN 202210515703A CN 114648178 A CN114648178 A CN 114648178A
- Authority
- CN
- China
- Prior art keywords
- electric energy
- metering device
- error
- energy metering
- maintenance
- 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.)
- Granted
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 152
- 238000005457 optimization Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 33
- 230000009471 action Effects 0.000 claims abstract description 50
- 238000012549 training Methods 0.000 claims abstract description 6
- 230000007774 longterm Effects 0.000 claims description 22
- 238000011156 evaluation Methods 0.000 claims description 17
- 239000000126 substance Substances 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 12
- 238000013077 scoring method Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 238000013499 data model Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000005315 distribution function Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 3
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims 1
- 230000006870 function Effects 0.000 abstract description 29
- 230000002787 reinforcement Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 7
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000000737 periodic effect Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 3
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000005303 weighing Methods 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- 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
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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
Abstract
The invention relates to an operation and maintenance strategy optimization method of an electric energy metering device based on a DDPG algorithm, which comprises the following steps: evaluating the error state of the electric energy metering device based on the error state score and the set threshold range; establishing an operation and maintenance model based on a DDFG algorithm, wherein an Actor network of the operation and maintenance model generates operation and maintenance actions for the electric energy metering device; the Critic network of the operation and maintenance model evaluates the performance of the operation and maintenance action and guides the strategy function to generate the operation and maintenance action of the next stage; performing iterative update training on the operation and maintenance model; performing iterative optimization on a threshold range corresponding to the electric energy metering device to be evaluated based on the operation and maintenance model, and determining an operation and maintenance strategy of the electric energy metering device to be evaluated according to the optimized threshold range and the operation and maintenance model; the idea of reinforcement learning is used for solving the optimization problem of the operation and maintenance strategy of the electric energy metering device, so that the constraint of human experience in the traditional operation and maintenance mode is eliminated, the operation and maintenance cost is reduced, and the operation and maintenance efficiency is improved.
Description
Technical Field
The invention relates to the field of operation and maintenance management of electric energy metering devices, in particular to an operation and maintenance strategy optimization method of an electric energy metering device based on a DDPG algorithm.
Background
The electric energy metering device comprises a voltage transformer, a current transformer, a secondary circuit and an electric energy meter, is an important tool for carrying out fair and fair transaction and accurate trade settlement among a power generation group, a power grid company, a power selling company and power utilization customers, is also an important basis for carrying out line loss assessment and bus balance calculation inside a power grid enterprise, and the accuracy and the stability of the operation of the electric energy metering device are related to the economic benefits of both sides of a trade and the economic benefits inside the enterprise. The periodic maintenance is the field verification of the electric energy metering device according to the management rule of the electric energy metering device and the periodic time required by the classification of the electric energy metering device. Along with the quantity and the scale of the electric energy metering devices are gradually increased, a large amount of manpower and material resources are wasted by the period verification required by regulations, and the enterprise benefits are damaged.
Aiming at the problems of 'insufficient maintenance' and 'excessive operation and maintenance' caused by periodic maintenance of the electric energy metering device, the invention provides an operation and maintenance strategy optimization method of the electric energy metering device based on a DDPG (Deep Deterministic Policy Gradient) algorithm, wherein the idea of reinforcement learning is used for solving the optimization problem of the operation and maintenance strategy of the electric energy metering device, the artificial experience constraint in the traditional operation and maintenance mode is eliminated, the operation and maintenance cost is reduced, and the operation and maintenance efficiency is improved.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides the DDPG algorithm-based electric energy metering device operation and maintenance strategy optimization method, which uses the idea of reinforcement learning to solve the optimization problem of the electric energy metering device operation and maintenance strategy, breaks away from the constraint of artificial experience in the traditional operation and maintenance mode, reduces the operation and maintenance cost and improves the operation and maintenance efficiency.
According to a first aspect of the invention, an electric energy metering device operation and maintenance strategy optimization method based on a DDPG algorithm is provided, and comprises the following steps: step 1, selecting each error state parameter of an electric energy metering device in historical data to establish a decision characteristic vector representing the error state of the electric energy metering device, calculating the error state score of the electric energy metering device according to the decision characteristic vector, and evaluating whether the error state of the electric energy metering device is stable, good or early-warning based on the error state score and a set threshold range;
step 2, establishing an operation and maintenance model based on a DDFG algorithm, wherein an Actor network of the operation and maintenance model generates operation and maintenance actions for the electric energy metering device; the Critic network of the operation and maintenance model evaluates the performance of the operation and maintenance action and guides a strategy function to generate the operation and maintenance action of the next stage; performing iterative update training on the operation and maintenance model according to the error state and the corresponding operation and maintenance action obtained in the step 1;
and 3, performing iterative optimization on the threshold range corresponding to the electric energy metering device to be evaluated based on the operation and maintenance model, and determining the operation and maintenance strategy of the electric energy metering device to be evaluated according to the optimized threshold range and the operation and maintenance model.
On the basis of the technical scheme, the invention can be improved as follows.
Optionally, in step 1, the decision feature vector is
Wherein, in the step (A),
for the purpose of real-time error estimation,
for a short-term prediction error estimate sequence,
for the long-term prediction error estimate sequence, W is the stability state.
Optionally, in step 1, the method for obtaining the error state parameter of the electric energy metering device includes:
calculating to obtain the real-time error estimated value by adopting an algorithm based on data driving
；
Preprocessing error data of the electric energy metering device, stripping the error data into self error and additional error, constructing a trend prediction model by utilizing an ARIMA algorithm, inputting the self error into the trend prediction model to obtain a self error short-term prediction value of the electric energy metering device, calculating the additional error short-term prediction value of the electric energy metering device to be measured according to temperature information and frequency information, and adding the self error prediction value and the additional error prediction value to obtain a short-term prediction error estimation value sequence
；
Processing the plurality of self errors into a time sequence, and inputting the time sequence into a trained LSTM model to obtain a self error long-term predicted value of the electric energy metering device; calculating an additional error long-term predicted value of the electric energy metering device according to the temperature information and the frequency information; fusing the self error long-term predicted value and the additional error long-term predicted value to obtain the long-term prediction error estimated value sequence
；
The method comprises the following steps of constructing and obtaining a stability state evaluation index of the electric energy metering device, and establishing a stability state index data model of the electric energy metering device, wherein the stability state evaluation index comprises the following steps: a sudden change error stable frequency function model, a sudden change error unstable frequency function model, a gradual change error monotonous significance function model and a gradual change error standard deviation function model; comparing the importance of each state evaluation index by adopting a hierarchical analysis theory, determining the weight of the state evaluation index, calculating the stability state score of the electric energy metering device according to the result of each state evaluation index of the stability state index data model of the electric energy metering device and the corresponding weight, and evaluating whether the stability state W of the electric energy metering device is stable, slightly stable, moderately stable or severely stable according to the stability state score of the electric energy metering device;
in the step 1, after each error state parameter of the decision feature vector is calculated by a weighted comprehensive scoring method, the error state score is obtained.
Optionally, the step 1 of calculating the error state score of the electric energy metering device according to the decision feature vector includes:
101, estimating the error value based on the electric energy metering device
Standard deviation of error estimate
Establishing an error state scoring model of the electric energy metering device according to the precision k;
102, respectively calculating real-time error estimation values based on the error state scoring model
Short-term prediction error estimation sequence
And long-term prediction error estimate sequence
Respectively is
、
And
；
103, setting corresponding weights for the stability W of the electric energy metering device to be stable, slightly stable, moderately stable and heavily stable according to the stability degree respectively
、
、
And
to obtain
；
104, calculating the error state scores of the error state parameters by adopting a weighted comprehensive scoring method to obtain the error state scores of the electric energy metering device
；
105, setting each threshold value range of corresponding error state scores representing that the error state of the electric energy metering device is stable, good or early-warning, and scoring according to the error states
The threshold value range is used for evaluating the error of the electric energy metering deviceA bad state.
Optionally, a scoring threshold parameter is used in the step 1 and the step 3
、
And
represents the threshold range:
error state of the electric energy metering device
；
Wherein the content of the first and second substances,
、
and
respectively showing stability, good and early warning;
scoring an error state of an electric energy metering device, a scoring threshold parameter
、
And
satisfy the requirement of
。
Optionally, step 101 is implementedThe error state scoring model is:
;
wherein the content of the first and second substances,
based on error estimation
Error truth value of electric energy metering device obtained by calculation
Out of range [ -k, k]Probability of (c):
optionally, the error state score in step 102
、
And
the calculation formulas of (A) and (B) are respectively as follows:
where i and j are constants.
OptionallyCalculating an error state score of the electric energy metering device in step 104
Comprises the following steps:
optionally, the calculating process of the target Q value of the operation and maintenance model in step 2 includes:
step 201, setting the error state of the electric energy metering device at time t as
Operation and maintenance actions as
：
Wherein the content of the first and second substances,
、
and
respectively representing forward extending of a verification period, and performing and arranging field verification according to a specified period;
step 202, define the function
Representing a deterministic operation and maintenance action strategy, and the operation and maintenance of the electric energy metering device at any time tMovement of
The calculation formula of (2) is as follows:
；
step 203, define parameters
And a function J, the parameter
For the function
The parameters of the strategy network for simulation are measured by the function J
A function of the performance of the represented operation and maintenance action policy;
wherein the content of the first and second substances,
is a distribution function;
indicating different error states as a function
Q value which can be generated when the represented operation and maintenance action strategy is adopted;
is an error state
According to
When distributed
The expected value of (d);
step 204, the error state of the electric energy metering device is
Take operation and maintenance actions
Thereafter, and continuously executing the function
Calculating the target under the represented operation and maintenance action strategy
The values are:
wherein the content of the first and second substances,
r is the return value for the discount factor.
Optionally, step 3 includes:
step 301, defining an error state of an electric energy metering device
The operation and maintenance actions
A function of relationship of
Satisfies the following conditions: as electric energy metering devicesError states are respectively
、
And
the operation and maintenance actions executed are respectively corresponding to
、
And
；
step 302, based on the target in the operation and maintenance model in the step 2
Value and function of
Corresponding deterministic action strategy to set the initial scoring threshold parameter
、
And
performing iterative optimization to obtain the optimized grading threshold parameter
、
And
，
indicating the number of optimization iterations.
According to the operation and maintenance strategy optimization method of the electric energy metering device based on the DDPG algorithm, the accuracy of error state evaluation of the electric energy metering device is ensured by adopting a weighted comprehensive scoring method and setting of a dynamic threshold; an operation and maintenance model based on a DDPG algorithm is established, the operation and maintenance strategy of the electric energy metering device is optimized, the operation and maintenance cost is reduced, and the operation and maintenance efficiency is improved; the idea of reinforcement learning is used for solving the optimization problem of the operation and maintenance strategy of the electric energy metering device, the constraint of artificial experience in the traditional operation and maintenance mode is eliminated, the operation and maintenance cost is reduced, and the operation and maintenance efficiency is improved.
Drawings
FIG. 1 is a flow chart of an operation and maintenance strategy optimization method of an electric energy metering device based on DDPG algorithm provided by the invention;
FIG. 2 is a schematic diagram of a network structure of DDPG;
fig. 3 is a schematic diagram of a scoring threshold parameter optimization method according to an embodiment of the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
Fig. 1 is a flowchart of an operation and maintenance strategy optimization method for an electric energy metering device based on a DDPG algorithm, as shown in fig. 1, the operation and maintenance strategy optimization method includes:
step 1, selecting each error state parameter of the electric energy metering device from historical data to establish a decision characteristic vector representing the error state of the electric energy metering device, calculating the error state score of the electric energy metering device according to the decision characteristic vector, and evaluating whether the error state of the electric energy metering device is stable, good or early-warning based on the error state score and a set threshold range.
Step 2, establishing an operation and maintenance model based on a DDFG algorithm, wherein an Actor network of the operation and maintenance model generates operation and maintenance actions for the electric energy metering device; the Critic network of the operation and maintenance model evaluates the performance of the operation and maintenance action and guides the strategy function to generate the operation and maintenance action of the next stage; and (4) performing iterative update training on the operation and maintenance model according to the error state and the corresponding operation and maintenance action obtained in the step (1).
The DDPG algorithm inherits a deterministic strategy of a DPG (deterministic policy gradient) algorithm, an agent outputs deterministic actions according to state decisions, and the DDPG adopts a deep neural network to enhance the fitting capacity of a decision function. Compared with a random strategy, the DDPG greatly reduces the sampling data volume, improves the algorithm efficiency and is more beneficial to the learning of an intelligent agent in a continuous action space.
The network structure of the DDPG is shown in fig. 2, and as can be seen from fig. 2, the DDPG algorithm takes the form of an Actor-Critic framework, and mainly includes an Actor (Actor) network and a Critic (Critic) network. The Actor network is responsible for generating actions and environment interaction for the electric energy metering device, and the criticic network is responsible for evaluating states and performance of the actions and guiding the strategy function to generate the action of the next stage. Both the Actor and Critic adopt a dual-network structure, and have respective Target (Target) network and estimation (Eval) network. The Actor-eval network is mainly responsible for policy network parameters
The action a is selected according to the current state s, and the state of the next moment is generated in the process of interacting with the environment
And a reward value r resulting from executing the current action. The Actor-target network is responsible for sampling the next state according to the experience pool
Selecting an optimal next moment action
. Network parameters
Periodically from Actor-eval network
And (6) copying. Critic-eval network mainly aims at network parameters
Is updated by iteration, the current Q value is calculated
And target Q value
Wherein
Representing a discount factor that affects how important the future reward is relative to the current reward during the training process. Critic-target network main parameter
From periodic copying of the critical-eval network
Derived from parameters primarily responsible for calculating the target Q value
。
And 3, performing iterative optimization on the threshold range corresponding to the electric energy metering device to be evaluated based on the operation and maintenance model, and determining the operation and maintenance strategy of the electric energy metering device to be evaluated according to the optimized threshold range and the operation and maintenance model.
The invention provides an operation and maintenance strategy optimization method of an electric energy metering device based on a DDPG algorithm, which uses the idea of reinforcement learning to solve the optimization problem of the operation and maintenance strategy of the electric energy metering device, gets rid of the constraint of artificial experience in the traditional operation and maintenance mode, reduces the operation and maintenance cost and improves the operation and maintenance efficiency.
Example 1
Embodiment 1 provided by the present invention is an embodiment of an operation and maintenance policy optimization method for an electric energy metering device based on a DDPG algorithm, and as can be seen from fig. 1, the embodiment of the operation and maintenance policy optimization method includes:
step 1, selecting each error state parameter of the electric energy metering device from historical data to establish a decision characteristic vector representing the error state of the electric energy metering device, calculating the error state score of the electric energy metering device according to the decision characteristic vector, and evaluating whether the error state of the electric energy metering device is stable, good or early-warning based on the error state score and a set threshold range.
In a possible embodiment, the decision feature vector established in step 1 is
Wherein, in the step (A),
for the purpose of real-time error estimation,
for a short-term prediction error estimate sequence,
for the long-term prediction error estimate sequence, W is the stability state. Namely, the error state parameters of the electric energy metering device comprise: real-time error estimates, short-term prediction error estimate sequences, long-term prediction error estimate sequences, and stability states.
In a possible embodiment mode, in step 1, the method for acquiring the error state parameter of the electric energy metering device includes:
1) real-time error estimation value calculated by data-driven algorithm
。
2) Preprocessing error data of the electric energy metering device, stripping the error data into self error and additional error, constructing a trend prediction model by utilizing an Auto Regression Integration Moving Average (ARIMA) algorithm, inputting the self error into the trend prediction model to obtain a self error short-term prediction value of the electric energy metering device, calculating the additional error short-term prediction value of the electric energy metering device to be measured according to temperature information and frequency information, and adding the self error short-term prediction value and the additional error short-term prediction value to obtain a short-term prediction error estimation value sequence
As shown in equation (1).
m is a constant.
3) Processing the plurality of self errors into a time sequence, and inputting the time sequence into a trained LSTM model to obtain a self error long-term predicted value of the electric energy metering device; calculating an additional error long-term predicted value of the electric energy metering device according to the temperature information and the frequency information; fusing the self error long-term predicted value and the additional error long-term predicted value to obtain a long-term prediction error estimated value sequence
As shown in equation (2).
n is a constant.
4) The method comprises the following steps of constructing and obtaining a stability state evaluation index of the electric energy metering device, and establishing a stability state index data model of the electric energy metering device, wherein the stability state evaluation index comprises the following steps: a sudden change error stable frequency function model, a sudden change error unstable frequency function model, a gradual change error monotonous significance function model and a gradual change error standard deviation function model; and comparing the importance of each state evaluation index by adopting a hierarchical analysis theory, determining the weight of the state evaluation index, calculating the stability state score of the electric energy metering device according to the result of each state evaluation index of the stability state index data model of the electric energy metering device and the corresponding weight, and evaluating whether the stability state W of the electric energy metering device is stable, slightly stable, moderately stable or severely stable according to the stability state score of the electric energy metering device.
Wherein the content of the first and second substances,
、
and
respectively represent each time, an
。
In a possible embodiment, in step 1, after each error state parameter of the decision feature vector is calculated by a weighted comprehensive scoring method, an error state score is obtained.
In a possible embodiment, the step 1 of calculating the error state score of the electric energy metering device according to the decision feature vector includes:
101, estimating error value based on electric energy metering device
Standard deviation of error estimate
（
Is constant) and precision k (k isConstant) to establish an error state grading model of the electric energy metering device.
It can be understood that, for a power metering device to be evaluated, the true error value and the estimated error value obtained by the algorithm are respectively recorded as
And
obeying the following distribution:
based on the error estimate
Error truth value of electric energy metering device is calculated
Out of range [ -k, k]Probability of (2)
As shown in equation (3):
the specific calculation is as follows:
based on probability
Calculating error state scores for an electric energy metering device
：
102, respectively calculating real-time error estimation values based on the error state scoring model
Short-term prediction error estimation sequence
And long-term prediction error estimate sequence
Respectively is
、
And
。
it will be appreciated that error state scoring in step 102
、
And
the calculation formulas of (A) and (B) are respectively as follows:
where i and j are constants.
103, setting corresponding weights for the stability W of the electric energy metering device to be stable, slightly stable, moderately stable and heavily stable according to the stability degree respectively
、
、
And
to obtain
。
In specific implementation, the weight value can be determined by a method of expert judgment.
104, calculating the error state scores of the error state parameters by adopting a weighted comprehensive scoring method to obtain the error state scores of the electric energy metering device
。
Calculating an error state score for the electric energy metering device in step 104
Comprises the following steps:
step 105, setting the representation powerThe error state of the metering device is stable, good or early-warning and corresponding to each threshold range of the error state score according to the error state score
And evaluating the error state of the electric energy metering device within the threshold range.
In specific implementation, each threshold range corresponding to each error state score can be determined by an expert judgment method.
In a possible embodiment, the scoring threshold parameter is used in step 1 and step 3
、
And
represents a threshold range:
error state of the electric energy metering device:
wherein the content of the first and second substances,
、
and
respectively showing stability, good and early warning;
scoring an error state of an electric energy metering device, a scoring threshold parameter
、
And
satisfy the requirement of
。
Step 2, establishing an operation and maintenance model based on a DDFG algorithm, wherein an Actor network of the operation and maintenance model generates operation and maintenance actions for the electric energy metering device; the Critic network of the operation and maintenance model evaluates the performance of the operation and maintenance action and guides the strategy function to generate the operation and maintenance action of the next stage; and (4) performing iterative update training on the operation and maintenance model according to the error state and the corresponding operation and maintenance action obtained in the step (1).
In a possible embodiment, the calculation process of the target Q value of the operation and maintenance model in step 2 includes:
step 201, setting the error state of the electric energy metering device at time t as
Operation and maintenance actions as
：
Wherein the content of the first and second substances,
、
and
respectively showing that the field verification is carried out and arranged according to a specified period along a verification period.
Step 202, define the function
Representing a deterministic operation and maintenance action strategy, and the operation and maintenance actions of the electric energy metering device at any time t
The calculation formula of (2) is as follows:
。
step 203, define parameters
And function J, parameter
Is a function of pair
The parameters of the strategy network for simulation, function J is a weighing function
A function of the performance of the represented operation and maintenance action policy.
Wherein the content of the first and second substances,
is a distribution function;
indicating different error states as a function
Q value which can be generated when the represented operation and maintenance action strategy is adopted;
is an error state
According to
When distributed
Is calculated from the expected value of (c).
Step 204, the error state of the electric energy metering device is
Take operation and maintenance actions
Then, and continuously executing the function
Calculating the target under the represented operation and maintenance action strategy
The values are:
wherein the content of the first and second substances,
r is the return value for the discount factor.
And 3, performing iterative optimization on the threshold range corresponding to the electric energy metering device to be evaluated based on the operation and maintenance model, and determining the operation and maintenance strategy of the electric energy metering device to be evaluated according to the optimized threshold range and the operation and maintenance model.
As shown in fig. 3, a schematic diagram of a scoring threshold parameter optimization method provided in the embodiment of the present invention is shown, and as can be seen from fig. 3, in a possible embodiment, step 3 includes:
step 301, defining an error state of an electric energy metering device
The operation and maintenance actions
A function of relationship of
Satisfies the following conditions: when the error states of the electric energy metering device are respectively
、
And
the operation and maintenance actions executed are respectively corresponding to
、
And
。
step 302, based on the target in the operation and maintenance model in step 2
Value and function of
Corresponding deterministic action strategy, setting initial grading threshold parameter
、
And
performing iterative optimization to obtain optimized scoring threshold value parameters
、
And
，
the number of optimization iterations is indicated.
Specifically, the error state of the electric energy metering device when the time t is executed is
Downward operation and maintenance action
Rear end
If the error state score is smaller, the initial score threshold parameter of the set error state score of the electric energy metering device is indicated
、
And
if the setting is too small, the scoring threshold parameter needs to be increased.
And guiding the operation and the maintenance of the electric energy metering device according to the optimized error state grading threshold of the electric energy metering device and an operation and maintenance model based on a DDFG algorithm.
According to the operation and maintenance strategy optimization method of the electric energy metering device based on the DDPG algorithm, provided by the embodiment of the invention, the accuracy of error state evaluation of the electric energy metering device is ensured by adopting a weighted comprehensive scoring method and setting of a dynamic threshold; an operation and maintenance model based on a DDPG algorithm is established, the operation and maintenance strategy of the electric energy metering device is optimized, the operation and maintenance cost is reduced, and the operation and maintenance efficiency is improved; the idea of reinforcement learning is used for solving the optimization problem of the operation and maintenance strategy of the electric energy metering device, so that the constraint of human experience in the traditional operation and maintenance mode is eliminated, the operation and maintenance cost is reduced, and the operation and maintenance efficiency is improved.
It should be noted that, in the foregoing embodiments, the description of each embodiment has an emphasis, and reference may be made to the related description of other embodiments for a part that is not described in detail in a certain embodiment.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. An operation and maintenance strategy optimization method of an electric energy metering device based on a DDPG algorithm is characterized by comprising the following steps:
step 1, selecting each error state parameter of an electric energy metering device in historical data to establish a decision characteristic vector representing the error state of the electric energy metering device, calculating the error state score of the electric energy metering device according to the decision characteristic vector, and evaluating whether the error state of the electric energy metering device is stable, good or early-warning based on the error state score and a set threshold range;
step 2, establishing an operation and maintenance model based on a DDFG algorithm, wherein an Actor network of the operation and maintenance model generates operation and maintenance actions for the electric energy metering device; the Critic network of the operation and maintenance model evaluates the performance of the operation and maintenance action and guides a strategy function to generate the operation and maintenance action of the next stage; performing iterative update training on the operation and maintenance model according to the error state and the corresponding operation and maintenance action obtained in the step 1;
and 3, performing iterative optimization on the threshold range corresponding to the electric energy metering device to be evaluated based on the operation and maintenance model, and determining the operation and maintenance strategy of the electric energy metering device to be evaluated according to the optimized threshold range and the operation and maintenance model.
2. The operation and maintenance strategy optimization method according to claim 1, wherein in the step 1, the decision feature vector is
Wherein, in the step (A),
for the purpose of real-time error estimation,
for a short-term prediction error estimate sequence,
for the long-term prediction error estimate sequence, W is the stability state.
3. The operation and maintenance strategy optimization method according to claim 2, wherein in the step 1, the method for obtaining the error state parameter of the electric energy metering device comprises:
calculating to obtain the real-time error estimated value by adopting an algorithm based on data driving
；
Preprocessing error data of the electric energy metering device, stripping the error data into self error and additional error, constructing a trend prediction model by utilizing an ARIMA algorithm, inputting the self error into the trend prediction model to obtain a self error short-term prediction value of the electric energy metering device, calculating the additional error short-term prediction value of the electric energy metering device to be measured according to temperature information and frequency information, and adding the self error prediction value and the additional error prediction value to obtain a short-term prediction error estimation value sequence
；
Processing the plurality of self errors into a time sequence, and inputting the time sequence into a trained LSTM model to obtain a self error long-term predicted value of the electric energy metering device; calculating an additional error long-term predicted value of the electric energy metering device according to the temperature information and the frequency information; fusing the self error long-term predicted value and the additional error long-term predicted value to obtain the long-term prediction error estimated value sequence
；
The method comprises the following steps of constructing and obtaining a stability state evaluation index of the electric energy metering device, and establishing a stability state index data model of the electric energy metering device, wherein the stability state evaluation index comprises the following steps: a sudden change error stable frequency function model, a sudden change error unstable frequency function model, a gradual change error monotonous significance function model and a gradual change error standard deviation function model; comparing the importance of each state evaluation index by adopting a hierarchical analysis theory, determining the weight of the state evaluation index, calculating the stability state score of the electric energy metering device according to the result of each state evaluation index of the stability state index data model of the electric energy metering device and the corresponding weight, and evaluating whether the stability state W of the electric energy metering device is stable, slightly stable, moderately stable or severely stable according to the stability state score of the electric energy metering device;
in the step 1, after each error state parameter of the decision feature vector is calculated by a weighted comprehensive scoring method, the error state score is obtained.
4. The operation and maintenance strategy optimization method according to claim 2, wherein the step 1 of calculating the error state score of the electric energy metering device according to the decision feature vector comprises:
101, estimating the error value based on the electric energy metering device
Standard deviation of error estimate
Establishing an error state scoring model of the electric energy metering device according to the precision k;
102, respectively calculating real-time error estimation values based on the error state scoring model
Short-term prediction error estimation sequence
And long-term prediction error estimate sequence
Respectively is
、
And
；
103, setting the corresponding weights of the stability W of the electric energy metering device to be stable, slightly stable, moderately stable and severely stable according to the stability degree respectively
、
、
And
to obtain
；
104, calculating the error state scores of the error state parameters by adopting a weighted comprehensive scoring method to obtain the error state scores of the electric energy metering device
；
105, setting each threshold value range of corresponding error state scores representing that the error state of the electric energy metering device is stable, good or early-warning, and scoring according to the error states
The threshold range is used for evaluating the error state of the electric energy metering device.
5. The operation and maintenance strategy optimization method according to claim 4, wherein a scoring threshold parameter is used in the step 1 and the step 3
、
And
represents the threshold range:
error state of the electric energy metering device
；
Wherein the content of the first and second substances,
、
and
respectively showing stability, good and early warning;
scoring an error state of an electric energy metering device, a scoring threshold parameter
、
And
satisfy the requirement of
。
6. The operation and maintenance strategy optimization method according to claim 4, wherein the error state score model established in the step 101 is:
;
wherein the content of the first and second substances,
based on error estimation
Error truth value of electric energy metering device obtained by calculation
Out of range [ -k, k]Probability of (c):
7. the operation and maintenance strategy optimization method according to claim 4, wherein the error state score in the step 102 is obtained
、
And
the calculation formulas of (A) and (B) are respectively as follows:
where i and j are constants.
8. The operation and maintenance strategy optimization method according to claim 4, wherein the error state score of the electric energy metering device is calculated in the step 104
Comprises the following steps:
9. the operation and maintenance strategy optimization method according to claim 5, wherein the calculation process of the target Q value of the operation and maintenance model in the step 2 comprises:
step 201, setting the error state of the electric energy metering device at time t as
Operation and maintenance actions as
：
Wherein the content of the first and second substances,
、
and
respectively representing forward extending of a verification period, and performing and arranging field verification according to a specified period;
step 202, define the function
Representing a deterministic operation and maintenance action strategy, and the operation and maintenance actions of the electric energy metering device at any time t
The calculation formula of (2) is as follows:
；
step 203, define parameters
And a function J, the parameter
For the function
The parameters of the strategy network for simulation are measured by the function J
A function of the performance of the represented operation and maintenance action policy;
wherein the content of the first and second substances,
is a distribution function;
indicating different error states as a function
Q value which can be generated when the represented operation and maintenance action strategy is adopted;
is an error state
According to
When distributed
The expected value of (d);
step 204, in the error state of the electric energy metering device, the error state is
Take operation and maintenance actions
Thereafter, and continuously executing the function
Calculating the target under the represented operation and maintenance action strategy
The values are:
wherein the content of the first and second substances,
r is the return value for the discount factor.
10. The operation and maintenance strategy optimization method according to claim 9, wherein the step 3 comprises:
step 301, defining an error state of an electric energy metering device
The operation and maintenance actions
A function of relationship of
Satisfies the following conditions: when the error states of the electric energy metering device are respectively
、
And
the operation and maintenance actions executed are respectively corresponding to
、
And
；
step 302, based on the target in the operation and maintenance model in the step 2
Value and function of
Corresponding deterministic action strategy to set the initial scoring threshold parameter
、
And
performing iterative optimization to obtain the optimized grading threshold parameter
、
And
，
indicating the number of optimization iterations.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210515703.2A CN114648178B (en) | 2022-05-12 | 2022-05-12 | Operation and maintenance strategy optimization method of electric energy metering device based on DDPG algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210515703.2A CN114648178B (en) | 2022-05-12 | 2022-05-12 | Operation and maintenance strategy optimization method of electric energy metering device based on DDPG algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114648178A true CN114648178A (en) | 2022-06-21 |
| CN114648178B CN114648178B (en) | 2022-08-26 |
Family
ID=81997106
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210515703.2A Active CN114648178B (en) | 2022-05-12 | 2022-05-12 | Operation and maintenance strategy optimization method of electric energy metering device based on DDPG algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114648178B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115018209A (en) * | 2022-08-08 | 2022-09-06 | 国网湖北省电力有限公司营销服务中心(计量中心) | Long-term prediction method and equipment for operation error of digital electric energy metering system |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030023466A1 (en) * | 2001-07-27 | 2003-01-30 | Harper Charles N. | Decision support system and method |
| JP2005168251A (en) * | 2003-12-05 | 2005-06-23 | Chugoku Electric Power Co Inc:The | Device, system, program, and method for predicting power demand, and recording medium |
| JP2010063320A (en) * | 2008-09-05 | 2010-03-18 | Toshiba Corp | Method and apparatus for controlling supply and demand for power system |
| CN104218570A (en) * | 2014-08-21 | 2014-12-17 | 国家电网公司 | Method and system for online evaluating overall measuring errors of electric energy measuring device |
| CN107784440A (en) * | 2017-10-23 | 2018-03-09 | 国网辽宁省电力有限公司 | A kind of power information system resource allocation system and method |
| KR20180130945A (en) * | 2017-05-31 | 2018-12-10 | 세림티에스지(주) | Energy consumption and electic fee prediction information system of Domestic using prediction analysis with perodic characteristics of energy consumption big data |
| CN110365056A (en) * | 2019-08-14 | 2019-10-22 | 南方电网科学研究院有限责任公司 | A kind of distributed energy participation power distribution network pressure regulation optimization method based on DDPG |
| CN110365057A (en) * | 2019-08-14 | 2019-10-22 | 南方电网科学研究院有限责任公司 | Distributed energy based on intensified learning participates in power distribution network peak regulation method for optimizing scheduling |
| CN110535146A (en) * | 2019-08-27 | 2019-12-03 | 哈尔滨工业大学 | The Method for Reactive Power Optimization in Power of Policy-Gradient Reinforcement Learning is determined based on depth |
| CN110766236A (en) * | 2019-10-31 | 2020-02-07 | 云南电网有限责任公司昆明供电局 | Power equipment state trend prediction method based on statistical analysis and deep learning |
| CN111324358A (en) * | 2020-02-14 | 2020-06-23 | 南栖仙策(南京)科技有限公司 | Training method for automatic operation and maintenance strategy of information system |
| CN111600851A (en) * | 2020-04-27 | 2020-08-28 | 浙江工业大学 | Feature filtering defense method for deep reinforcement learning model |
| US20210044444A1 (en) * | 2019-08-06 | 2021-02-11 | Cisco Technology, Inc. | Controller-based management of noncompliant power over ethernet devices |
| CN112686445A (en) * | 2020-12-30 | 2021-04-20 | 南京工程学院 | Photovoltaic power generation prediction method based on ARIMA-LSTM-DBN |
| CN113852082A (en) * | 2021-09-03 | 2021-12-28 | 清华大学 | Method and device for preventing and controlling transient stability of power system |
| CN114188997A (en) * | 2021-12-07 | 2022-03-15 | 国网甘肃省电力公司电力科学研究院 | Dynamic reactive power optimization method for high-ratio new energy power access area power grid |
| CN114243718A (en) * | 2021-12-23 | 2022-03-25 | 华北电力大学（保定） | Power grid reactive voltage coordination control method based on DDPG algorithm |
-
2022
- 2022-05-12 CN CN202210515703.2A patent/CN114648178B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030023466A1 (en) * | 2001-07-27 | 2003-01-30 | Harper Charles N. | Decision support system and method |
| JP2005168251A (en) * | 2003-12-05 | 2005-06-23 | Chugoku Electric Power Co Inc:The | Device, system, program, and method for predicting power demand, and recording medium |
| JP2010063320A (en) * | 2008-09-05 | 2010-03-18 | Toshiba Corp | Method and apparatus for controlling supply and demand for power system |
| CN104218570A (en) * | 2014-08-21 | 2014-12-17 | 国家电网公司 | Method and system for online evaluating overall measuring errors of electric energy measuring device |
| KR20180130945A (en) * | 2017-05-31 | 2018-12-10 | 세림티에스지(주) | Energy consumption and electic fee prediction information system of Domestic using prediction analysis with perodic characteristics of energy consumption big data |
| CN107784440A (en) * | 2017-10-23 | 2018-03-09 | 国网辽宁省电力有限公司 | A kind of power information system resource allocation system and method |
| US20210044444A1 (en) * | 2019-08-06 | 2021-02-11 | Cisco Technology, Inc. | Controller-based management of noncompliant power over ethernet devices |
| CN110365057A (en) * | 2019-08-14 | 2019-10-22 | 南方电网科学研究院有限责任公司 | Distributed energy based on intensified learning participates in power distribution network peak regulation method for optimizing scheduling |
| CN110365056A (en) * | 2019-08-14 | 2019-10-22 | 南方电网科学研究院有限责任公司 | A kind of distributed energy participation power distribution network pressure regulation optimization method based on DDPG |
| CN110535146A (en) * | 2019-08-27 | 2019-12-03 | 哈尔滨工业大学 | The Method for Reactive Power Optimization in Power of Policy-Gradient Reinforcement Learning is determined based on depth |
| CN110766236A (en) * | 2019-10-31 | 2020-02-07 | 云南电网有限责任公司昆明供电局 | Power equipment state trend prediction method based on statistical analysis and deep learning |
| CN111324358A (en) * | 2020-02-14 | 2020-06-23 | 南栖仙策(南京)科技有限公司 | Training method for automatic operation and maintenance strategy of information system |
| CN111600851A (en) * | 2020-04-27 | 2020-08-28 | 浙江工业大学 | Feature filtering defense method for deep reinforcement learning model |
| CN112686445A (en) * | 2020-12-30 | 2021-04-20 | 南京工程学院 | Photovoltaic power generation prediction method based on ARIMA-LSTM-DBN |
| CN113852082A (en) * | 2021-09-03 | 2021-12-28 | 清华大学 | Method and device for preventing and controlling transient stability of power system |
| CN114188997A (en) * | 2021-12-07 | 2022-03-15 | 国网甘肃省电力公司电力科学研究院 | Dynamic reactive power optimization method for high-ratio new energy power access area power grid |
| CN114243718A (en) * | 2021-12-23 | 2022-03-25 | 华北电力大学（保定） | Power grid reactive voltage coordination control method based on DDPG algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 林祥勋: "浅析电能计量装置运行误差分析及状态评价方法", 《技术与市场》 * |
| 程瑛颖: "《电能计量装置运行误差分析及状态评价方法研究》", 《电工电能新技术》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115018209A (en) * | 2022-08-08 | 2022-09-06 | 国网湖北省电力有限公司营销服务中心(计量中心) | Long-term prediction method and equipment for operation error of digital electric energy metering system |
| CN115018209B (en) * | 2022-08-08 | 2022-11-08 | 国网湖北省电力有限公司营销服务中心(计量中心) | Long-term prediction method and equipment for operation error of digital electric energy metering system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114648178B (en) | 2022-08-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111047085B (en) | Hybrid vehicle working condition prediction method based on meta-learning | |
| CN108710905A (en) | One kind being based on the united spare part quantitative forecasting technique of multi-model and system | |
| CN110781969A (en) | Air conditioner air volume control method and device based on deep reinforcement learning and medium | |
| WO2020147450A1 (en) | Ai model automatic generation method based on computational graph evolution | |
| CN114648178B (en) | Operation and maintenance strategy optimization method of electric energy metering device based on DDPG algorithm | |
| CN115940294B (en) | Multi-stage power grid real-time scheduling strategy adjustment method, system, equipment and storage medium | |
| CN109242558A (en) | A kind of management data prediction technique, readable storage medium storing program for executing and forecasting system neural network based | |
| CN111695754A (en) | Electric power Internet of things information security risk assessment method and device | |
| CN110794308B (en) | Method and device for predicting train battery capacity | |
| CN115115389A (en) | Express customer loss prediction method based on value subdivision and integrated prediction | |
| CN111008790A (en) | Hydropower station group power generation electric scheduling rule extraction method | |
| Cui et al. | Stochastic planning with lifted symbolic trajectory optimization | |
| Neumann et al. | Scaling laws for a multi-agent reinforcement learning model | |
| CN111400964B (en) | Fault occurrence time prediction method and device | |
| CN112241808A (en) | Road surface technical condition prediction method, device, electronic equipment and storage medium | |
| CN116777281A (en) | ARIMA model-based power equipment quality trend prediction method and device | |
| CN116384251A (en) | New energy generated power combination prediction method and system considering risk avoidance | |
| CN113300884B (en) | GWO-SVR-based step-by-step network flow prediction method | |
| CN113435927B (en) | User willingness prediction method, device, equipment and storage medium | |
| CN110555742A (en) | Generation method and system for generator agent quotation | |
| CN117129895A (en) | Battery state of health calculation method, device, storage medium and vehicle | |
| CN115219910A (en) | Analysis method and device for battery residue prediction error | |
| CN108053266A (en) | A kind of patent value predictor method and device | |
| CN113987261A (en) | Video recommendation method and system based on dynamic trust perception | |
| CN113762591A (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM counterstudy |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Room 1803-1805, building 2-07, guanggu.core center, 303 Guanggu Avenue, Donghu New Technology Development Zone, Wuhan City, Hubei Province, 430000 Patentee after: Wuhan Gelanruo Intelligent Technology Co.,Ltd. Address before: Room 1803-1805, building 2-07, guanggu.core center, 303 Guanggu Avenue, Donghu New Technology Development Zone, Wuhan City, Hubei Province, 430000 Patentee before: WUHAN GLORY ROAD INTELLIGENT TECHNOLOGY Co.,Ltd. |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An optimization method for operation and maintenance strategy of electric energy metering device based on DDPG algorithm Effective date of registration: 20221230 Granted publication date: 20220826 Pledgee: Bank of China Limited Wuhan Donghu New Technology Development Zone Branch Pledgor: Wuhan Gelanruo Intelligent Technology Co.,Ltd. Registration number: Y2022420000404 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Granted publication date: 20220826 Pledgee: Bank of China Limited Wuhan Donghu New Technology Development Zone Branch Pledgor: Wuhan Gelanruo Intelligent Technology Co.,Ltd. Registration number: Y2022420000404 |