CN108416509A - Electric power energy requirements response method and system, the storage medium of industrial enterprise - Google Patents
Electric power energy requirements response method and system, the storage medium of industrial enterprise Download PDFInfo
- Publication number
- CN108416509A CN108416509A CN201810130412.5A CN201810130412A CN108416509A CN 108416509 A CN108416509 A CN 108416509A CN 201810130412 A CN201810130412 A CN 201810130412A CN 108416509 A CN108416509 A CN 108416509A
- Authority
- CN
- China
- Prior art keywords
- load
- industrial enterprise
- electric
- energy consumption
- prediction
- 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 47
- 230000004044 response Effects 0.000 title claims abstract description 35
- 238000003860 storage Methods 0.000 title claims abstract description 9
- 238000005265 energy consumption Methods 0.000 claims abstract description 92
- 230000005611 electricity Effects 0.000 claims abstract description 88
- 238000005457 optimization Methods 0.000 claims abstract description 31
- 238000013528 artificial neural network Methods 0.000 claims abstract description 17
- 238000013135 deep learning Methods 0.000 claims abstract description 14
- 239000011159 matrix material Substances 0.000 claims description 52
- 230000006870 function Effects 0.000 claims description 11
- 235000006508 Nelumbo nucifera Nutrition 0.000 claims description 5
- 240000002853 Nelumbo nucifera Species 0.000 claims description 5
- 235000006510 Nelumbo pentapetala Nutrition 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 230000004888 barrier function Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 8
- 230000008901 benefit Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000000306 recurrent effect Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010025 steaming Methods 0.000 description 1
- 230000000153 supplemental effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P80/00—Climate change mitigation technologies for sector-wide applications
- Y02P80/10—Efficient use of energy, e.g. using compressed air or pressurized fluid as energy carrier
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The present invention provides a kind of electric power energy requirements response method of industrial enterprise and system, storage medium, method include:Acquire part throttle characteristics data of multiple energy consumption equipments in default historical time section in industrial enterprise;Deep learning is carried out using default neural network, obtains prediction electric load of the energy consumption equipment in default future time section;Determine prediction total electricity load of the industrial enterprise in default future time section;The both sides' non-cooperative game for carrying out Utilities Electric Co. of industrial enterprise, obtains expectation demand load of the Utilities Electric Co. to industrial enterprise;Prediction electric load respective to each energy consumption equipment is adjusted, and obtains the optimization electric load in each comfortable default future time section of each energy consumption equipment;According to the respective optimization electric load of each energy consumption equipment, determine that the electricity consumption of industrial enterprise arranges strategy, and demand response is carried out to Utilities Electric Co..The present invention can break the barrier of information asymmetry between industrial enterprise and Utilities Electric Co., realize that common interest maximizes as possible.
Description
Technical field
The present invention relates to multiplexe electric technology fields, and in particular to a kind of electric power energy requirements response method of industrial enterprise and is
System, storage medium.
Background technology
Currently, the safe operation of electric system and economical operation faces kinds of risks, and the control that power cuts to limit consumption etc. is traditional
Method processed also greatly increases the Unit Commitment cost of electricity power enterprise, and to electricity consumption master other than influencing normal life
The production of body-industrial enterprise has certain influence.Most electricity generation system is still based on thermal power generation at present in China
Meet the needs of peak load of grid and ensure power system stability, if be only improved electric system, needs to pay
Go out huge repeated construction cost to respond peak of power consumption load, but during low power consumption load, this part electric energy is again in vain
Waste.Therefore only by every resource to Generation Side be adjusted with optimize approach can not fundamentally solve it is above-mentioned
Problem.
Since industrial enterprise is electricity consumption main body, driving industrial enterprise, which actively carries out electricity needs response, can be effectively relieved electricity
Net pressure, and one of the approach for transferring Power Consumption of Industrial Enterprises enthusiasm is to make industrial enterprise's cost reduction, benefit improves.It can
See, the management and optimization to Demand-side become most important.In this context, it is that industrial enterprise establishes effective electric power energy
Consumption demand response scheme is particularly important.
Invention content
(1) the technical issues of solving
In view of the deficiencies of the prior art, the present invention provides a kind of electric power energy requirements response method of industrial enterprise and it is
System, storage medium, can break the barrier of information asymmetry between the two, realize industrial enterprise and Utilities Electric Co. both sides profit as possible
The maximization of benefit.
(2) technical solution
In order to achieve the above object, the present invention is achieved by the following technical programs:
In a first aspect, the embodiment of the present invention provides a kind of electric power energy requirements response method of industrial enterprise, this method packet
It includes:
Acquire part throttle characteristics data of multiple energy consumption equipments in default historical time section in the industrial enterprise;
According to the part throttle characteristics data of each energy consumption equipment, deep learning is carried out using default neural network, is somebody's turn to do
Prediction electric load of the energy consumption equipment in default future time section;
According to the prediction electric load of each energy consumption equipment, determine the industrial enterprise in the default future time
Prediction total electricity load in section;
According to the prediction total electricity load of the industrial enterprise and the power supply strategy of Utilities Electric Co., industrial enterprise is carried out
Both sides' non-cooperative game of industry-Utilities Electric Co. obtains expectation demand load of the Utilities Electric Co. to the industrial enterprise;
According to the expectation demand load, the prediction electric load respective to each energy consumption equipment is adjusted, and is obtained
To the optimization electric load in each leisure of each energy consumption equipment default future time section;
According to the respective optimization electric load of each energy consumption equipment, determine that the electricity consumption of the industrial enterprise arranges strategy, and
Strategy is arranged to carry out demand response to the Utilities Electric Co. according to the electricity consumption.
Second aspect, the embodiment of the present invention provide a kind of industrial enterprise's electric power energy requirements response system, which includes:
Data acquisition module, it is negative in default historical time section for acquiring multiple energy consumption equipments in the industrial enterprise
Lotus performance data;
Load prediction module, for according to the part throttle characteristics data of each energy consumption equipment, using default neural network into
Row deep learning obtains prediction electric load of the energy consumption equipment in default future time section;
Load integrates module, for the prediction electric load according to each energy consumption equipment, determines the industrial enterprise
Prediction total electricity load in the default future time section;
Non-cooperative game module, according to the prediction total electricity load of the industrial enterprise and the power supply plan of Utilities Electric Co.
Slightly, the both sides' non-cooperative game for carrying out industrial enterprise-Utilities Electric Co., obtains expectation of the Utilities Electric Co. to the industrial enterprise
Demand load;
Load adjustment module, for according to the expectation demand load, the prediction electricity respective to each energy consumption equipment
Power load is adjusted, and obtains the optimization electric load in each leisure of each energy consumption equipment default future time section;
Demand response module, for according to the respective optimization electric load of each energy consumption equipment, determining the industrial enterprise
Electricity consumption arrange strategy, and according to the electricity consumption arrange strategy to the Utilities Electric Co. carry out demand response.
The third aspect, the embodiment of the present invention provide a kind of computer readable storage medium, computer are stored on the medium
Program can realize the above method when processor executes the computer program.
(3) advantageous effect
An embodiment of the present invention provides electric power energy requirements response method and system, the storage medium of a kind of industrial enterprise,
Has following advantageous effect:
The embodiment of the present invention carries out depth using neural network to the part throttle characteristics data of the energy consumption equipment of industrial enterprise
It practises, obtains prediction electric load, and then integrate to the prediction electric load of each energy consumption equipment, obtain the pre- of industrial enterprise
Total electricity load is surveyed, industrial enterprise and Utilities Electric Co., which are then carried out non-cooperative game, obtains it is expected demand load, then in conjunction with
It is expected that demand load is adjusted prediction electric load, and then obtains optimization electric load, and then according to optimization electric load
Strategy is arranged to formulating electricity consumption, and then is responded to Utilities Electric Co. according to the electricity consumption arrangement strategy.This method not only ensure that
The validity and practicability for predicting electric load also strengthen contacting for industrial enterprise and Utilities Electric Co., break and believe between the two
Cease asymmetric barrier so that industrial enterprise recognizes that it can be that enterprise brings benefit actively to carry out demand response to Utilities Electric Co.
Promotion, transferred the enthusiasm that industrial enterprise responds Utilities Electric Co.'s Power policy;It is negative more can effectively to mitigate power grid peak
Lotus, improves vacant electricity consumption period utilization rate of electrical, realizes that electric power energy utilization rate maximizes, to realize as possible Utilities Electric Co. and
The maximization of industrial enterprise's common interest.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 shows the flow diagram of the electric power energy requirements response method of industrial enterprise in the embodiment of the present invention;
Fig. 2 shows the structure diagrams of industrial enterprise's electric power energy requirements response system in the embodiment of the present invention.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
The every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
In a first aspect, the embodiment of the present invention provides a kind of electric power energy requirements response method of industrial enterprise, such as Fig. 1 institutes
Show, this method includes:
Part throttle characteristics data of multiple energy consumption equipments in default historical time section in S100, the acquisition industrial enterprise;
It will be appreciated that different industrial enterprises, energy consumption equipment are same.For example, Air Compressor Equipment, Fan Equipment, motor
Equipment, process heating equipment, pumping unit and steaming plant etc..If some industrial enterprises of some of which equipment do not possess,
It can be indicated with zero or null vector when gathered data.
So-called part throttle characteristics data refer to the supplemental characteristics such as the attribute that can embody energy consumption equipment load behavior, feature, example
Such as:Load day attribute, all attributes and year attribute;Weather temperature when electric load;Festivals or holidays frequency;PPI indexes are (i.e. raw
Produce price index, Producer Price Index), CPI indexes (i.e. Consumer Prices index, consumer price
index);Headcount;Industrial enterprise's season benefit.
It will be appreciated that default historical time section, can be set as needed, for example, one month, week etc..
In the specific implementation, the part throttle characteristics data of acquisition can also be pre-processed, removes abnormal data.When to work
After each energy consumption equipment in industry enterprise is collected part throttle characteristics data and is pre-processed to it, the data that can will obtain
It stores to database, subsequently to use.
S200, the part throttle characteristics data according to each energy consumption equipment carry out deep learning using default neural network, obtain
To prediction electric load of the energy consumption equipment in default future time section;
It will be appreciated that each energy consumption equipment is directed to, to it in future by way of deep learning in step S200
Electric load in period predicted, obtained prediction electric load be to this energy consumption equipment in future time section
The prediction result of electric load.Wherein neural network model used by deep learning can select as needed, for example, using
Recognition with Recurrent Neural Network model RNN.
A kind of mode carrying out deep learning for some energy consumption equipment is described below:
S201, situation is fluctuated according to the power price of Utilities Electric Co., determines the input step of acquired part throttle characteristics data
Suddenly:With matrix XtIndicate the part throttle characteristics data of t step inputs, t is by t-th yuan in the corresponding time arrow of the data acquired
Element processing obtains, Xt=[d1t, d2t, d3t...].
S202, after inputting part throttle characteristics data S is obtained after RNN Processing with Neural Network enters hidden layert:
St=f (UXt+WSt-1)
Wherein, U is that for input layer to the connection weight of middle layer, W is to be exported in Recognition with Recurrent Neural Network in Recognition with Recurrent Neural Network
Unit returns to the connection weight of hidden unit, these weights help neural network to be trained to obtain more essence to data
Accurate prediction electric load.The two parameters are first random to be determined, then by constantly training to obtain required network knot
The weights of structure.F is general activation primitive, and it is line rectification function that can select ReLU, ReLU, it can be learnt with Corrected Depth
The deviation occurred in journey is common activation primitive in a kind of artificial neural network.
S203, loss function is built followed by predicted value and actual value:
Ln(yε, oε)=- ∑n∈N yn logon
Wherein, actual value y is predicted as o, training sample total amount N.
S204, network is trained then according to BPTT algorithms, that is, backpropagation bp algorithms, wherein:
Wherein, W represents the connection weight that output unit in Recognition with Recurrent Neural Network returns to hidden unit.
It is recycled according to RNN characteristics and executes above-mentioned steps, this energy consumption equipment can be obtained in default future time section
Prediction electric load.
In addition, before part throttle characteristics data are inputted deep learning network model, it can also be to collected load spy
Property data be normalized, by all part throttle characteristics data normalizations between [0,1], to carry out with top-down supervision
During mode of learning is the deep learning of training method.
S300, the prediction electric load according to each energy consumption equipment determine that the industrial enterprise presets not described
Carry out the prediction total electricity load in the period;
It will be appreciated that the step is actually the process for integrating the prediction electric load of each energy consumption equipment.
Prediction total electricity load is the prediction result of the electric load total in future time section to industrial enterprise.
For example, the prediction electric load of each energy consumption equipment have it is multiple, when each prediction electric load corresponds to following
Between time point in section, each prediction electric load of each energy consumption equipment in this way can use a vectorial form table
Show, and then the vector of each energy consumption equipment is summed, obtain a total vector, each value in total vector is equal
The prediction total electricity load at time point is corresponded in future time section for industrial enterprise.
S400, according to the prediction total electricity load of the industrial enterprise and the power supply strategy of Utilities Electric Co., carry out work
Both sides' non-cooperative game of industry enterprise-Utilities Electric Co. obtains expectation demand load of the Utilities Electric Co. to the industrial enterprise;
It will be appreciated that it is expected that demand load is the electricity that Utilities Electric Co. wishes industrial enterprise.
In this step, there are many modes for carrying out both sides' non-cooperative game, for example, being carried out according to the situation of Profit of both sides
Non-cooperative game, detailed process may include:
S401, according to it is described prediction total electricity load and Utilities Electric Co. power supply strategy, determine the receipts of the industrial enterprise
The avail data of beneficial data and the Utilities Electric Co.;
S402, the avail data of the industrial enterprise and the avail data progress Nash Equilibrium of the Utilities Electric Co. are won
It plays chess, obtains the expectation demand load.
Here, by the Nash Equilibrium game between the avail data of industrial enterprise and the avail data of Utilities Electric Co., just
It can obtain Utilities Electric Co. and wish that the electricity of industrial enterprise it is expected demand load.
In above-mentioned steps S401, the form table of matrix may be used in the avail data of industrial enterprise and Utilities Electric Co.
Show, following procedure determination may be used in the gain matrix of wherein industrial enterprise:
The total electricity load vector of industrial enterprise described in S4011, the unit price vector sum according to the Utilities Electric Co., really
The Cost matrix that the fixed industrial enterprise need to pay to the Utilities Electric Co.;
Wherein, the unit price vector is the unit price of power of Each point in time of the Utilities Electric Co. in time arrow
It is formed by vector, the total electricity load vector is the prediction total electricity of the industrial enterprise in the Each point in time
Load is formed by vector, and the time arrow is to be formed by vector at multiple time points in the default future time section,
The power supply strategy includes unit price vector.
For example, Cost matrix that the industrial enterprise need to pay to the Utilities Electric Co. is determined using the first formula,
First formula includes:
In formula, P is the Cost matrix that the industrial enterprise need to pay to the Utilities Electric Co.,For the total electricity load
Vector,For unit price vector.
S4012, the effectiveness parameter according to each energy consumption equipment of total electricity load vector sum of the industrial enterprise, really
The utility matrix of the fixed industrial enterprise;
For example, determine that the utility matrix of the industrial enterprise, second formula include using the second formula:
In formula, U is the utility matrix of the industrial enterprise, and α, beta, gamma ... is the effectiveness parameter of each energy consumption equipment,For
The total electricity load vector.
S4013, the Cost matrix according to the industrial enterprise and the utility matrix, determine the industrial enterprise
Gain matrix.
For example, determine that the gain matrix of the industrial enterprise, the third formula include using third formula:
Wn=U-P
In formula, Wn is the gain matrix of the industrial enterprise, and U is the utility matrix of the industrial enterprise, and P is the industry
The Cost matrix that enterprise need to pay to the Utilities Electric Co..
In addition, the gain matrix of Utilities Electric Co. can also use similar procedure to determine, for example, determining institute using the 4th formula
The avail data of Utilities Electric Co. is stated, the 4th formula includes:
Ws=Y-C
In formula, Ws is gain matrix, that is, avail data of the Utilities Electric Co., and Y is all users to Utilities Electric Co.'s branch
The cost metrix paid, C are the Cost matrix of the Utilities Electric Co..
Wherein, the cost metrix Y=Σ y that all users pay to the Utilities Electric Co.i,yi=A Φ B, A, B select for user
Matrix is selected, Φ is user's payoff matrix;Cost in Cost matrix C includes company operation, equipment investment, power grid maintenance, production
Cost, actual electric network loss etc..
However, it is expected demand load in practice and predicting that total electricity load is unequal, it is therefore desirable to each energy
The electric load of consumption equipment is adjusted, i.e., is adjusted by step S500.
S500, according to the expectation demand load, the prediction electric load respective to each energy consumption equipment is adjusted
It is whole, obtain the optimization electric load in each leisure of each energy consumption equipment default future time section;
Plan in future time section it will be appreciated that the optimization electric load of each energy consumption equipment refers to industrial enterprise
Distribute to the electricity of the energy consumption equipment, i.e. the electricity arrangement to the energy consumption equipment in future time section.When due to default future
Between section the form of time arrow may be used indicate that therefore the optimization electric load of each energy consumption equipment may be used one
The form of vector indicates that each value in the vector is optimization electric load corresponding with Each point in time in time arrow.
By to each energy consumption equipment prediction electric load adjustment, obtain corresponding optimization electric load, using pair
The optimization electric load answered controls the electricity consumption behavior of energy consumption equipment, to realize the pipe of the electricity consumption behavior to industrial enterprise
Reason.
In the specific implementation, the prediction electric load of each energy consumption equipment is adjusted to obtain optimization electric load
Following manner realization may be used in process:
S501, according to the expectation demand load, be fitted effect of each energy consumption equipment in the default future time section
It can function;
It is assumed that have N class energy consumption equipments in industrial enterprise, and the energy consumption equipment number of units in a kind of energy consumption equipment is M platforms, fitting
Efficiency Function can be indicated with following formula:
Eij=Eij(Qij)=αij+βijQij+γijQij 2+δijQij 3+… …
Wherein, EijFor the efficiency of the jth platform machine of the i-th class energy consumption equipment, QijWhat is actually represented is the phase obtained after game
Hope demand load QDR, αij、βij、γij、δij... for the part throttle characteristics parameter of the jth platform machine of the i-th class energy consumption equipment, pass through
αij、βij、γij、δij... these parameters are to QDRIt is adjusted to obtain the optimization electric load of single energy consumption equipment.And these are joined
As defined in number will be carried out according to actual conditions combination industrial enterprise and social factor.
S502, the Efficiency Function is solved using equal increment method, obtains the corresponding optimization electricity of each energy consumption equipment
Power load.
In step S502, during solving the Efficiency Function using equal increment method, existed with the industrial enterprise
The minimum object function of load total cost in the default future time section is with the part throttle characteristics data of each energy consumption equipment
Constraints is solved, to obtain optimization electric load.
Prediction total electricity load can use Q0Indicate, it is Δ Q=that industrial enterprise, which needs the load adjusted, | Q0-QDR|。ΔQ
That represent is prediction total electricity load Q0It is expected industrial enterprise in future time section between electricity to be used with Utilities Electric Co.
The absolute value of difference.It is realized because prediction total electricity load is the part throttle characteristics data based on industrial enterprise in historical time section
Prediction, and QDRWhat is represented is that whole society's factor is accounted for rear Utilities Electric Co. it is expected that industrial enterprise wants in future time section
The electricity used, therefore the meaning of Δ Q is exactly that industrial enterprise is arranged into response Utilities Electric Co. base from the electricity consumption considered based on itself
In the key for the transformation that whole society's factor considers, only Q0It is inadequate, only uses Q0Carrying out electric power distribution arrangement means industrial enterprise
Industry only may slightly be adjusted, either electricity consumption behavior, and equipment arrangement might as well all be fine tune, and have Δ Q
Introducing means that industrial enterprise may carry out strategical reajustment in conjunction with the condition of itself, it may be possible to the significantly tune of electricity consumption behavior
It is whole, it may be possible to which that the substantially transformation of plant process flow, the realization that can break a deadlock is really to the demand response of Utilities Electric Co..
S600, according to the respective optimization electric load of each energy consumption equipment, determine that the electricity consumption of the industrial enterprise arranges plan
Slightly, and according to the electricity consumption strategy is arranged to carry out demand response to the Utilities Electric Co..
Due to can be obtained by step S500 the optimization electric load of each energy consumption equipment to get to industrial enterprise to each
Electricity arrangement of a energy consumption equipment in default future time section, therefore the electricity consumption that can formulate industrial enterprise arranges strategy, into
And responded to Utilities Electric Co. according to the electricity consumption arrangement strategy, so that Utilities Electric Co. carries out the power demand of the industrial enterprise
Understand.
It is understood that electricity consumption arrangement strategy is corresponding with the power supply strategy of electricity consumption company, i.e., and electric company
Unit price of power arrangement in future time section is corresponding, and the different unit price of power arrangement of Utilities Electric Co., industrial enterprise has
Different electricity consumptions arranges strategy, industrial enterprise to be fed back to Utilities Electric Co., and the industrial enterprise can be learnt in its power supply strategy
Under power demand.
The electric power energy requirements response method of industrial enterprise provided in an embodiment of the present invention looks forward to industry using neural network
The part throttle characteristics data of the energy consumption equipment of industry carry out deep learning, obtain prediction electric load, and then to each energy consumption equipment
Prediction electric load is integrated, and the prediction total electricity load of industrial enterprise is obtained, then by industrial enterprise and Utilities Electric Co. into
Row non-cooperative game obtains it is expected demand load, is adjusted to prediction electric load then in conjunction with desired demand load, in turn
Optimization electric load is obtained, and then strategy is arranged to formulating electricity consumption according to optimization electric load, and then plan is arranged according to the electricity consumption
Slightly responded to Utilities Electric Co..This method not only ensure that the validity and practicability of prediction electric load, also strengthen work
Industry enterprise and Utilities Electric Co. contact, and break the barrier of information asymmetry between the two so that industrial enterprise recognizes actively right
It can be the promotion that enterprise brings benefit that Utilities Electric Co., which carries out demand response, transfer industrial enterprise to Utilities Electric Co.'s Power policy
The enthusiasm of response;It more can effectively mitigate peak load of grid, improve vacant electricity consumption period utilization rate of electrical, realize electric power energy
Source utilization rate maximizes.
Second aspect, the embodiment of the present invention provide a kind of industrial enterprise's electric power energy requirements response system, as shown in Fig. 2,
The system includes:
Data acquisition module, it is negative in default historical time section for acquiring multiple energy consumption equipments in the industrial enterprise
Lotus performance data;
Load prediction module, for according to the part throttle characteristics data of each energy consumption equipment, using default neural network into
Row deep learning obtains prediction electric load of the energy consumption equipment in default future time section;
Load integrates module, for the prediction electric load according to each energy consumption equipment, determines the industrial enterprise
Prediction total electricity load in the default future time section;
Non-cooperative game module, according to the prediction total electricity load of the industrial enterprise and the power supply plan of Utilities Electric Co.
Slightly, the both sides' non-cooperative game for carrying out industrial enterprise-Utilities Electric Co., obtains expectation of the Utilities Electric Co. to the industrial enterprise
Demand load;
Load adjustment module, for according to the expectation demand load, the prediction electricity respective to each energy consumption equipment
Power load is adjusted, and obtains the optimization electric load in each leisure of each energy consumption equipment default future time section;
Demand response module, for according to the respective optimization electric load of each energy consumption equipment, determining the industrial enterprise
Electricity consumption arrange strategy, and according to the electricity consumption arrange strategy to the Utilities Electric Co. carry out demand response.
In some embodiments, load prediction module will also be born using before presetting neural network progress deep learning
Lotus performance data is normalized.
In some embodiments, non-cooperative game module includes:
Income determination unit, described according to the power supply strategy for predicting total electricity load and Utilities Electric Co., determining
The avail data of the avail data of industrial enterprise and the Utilities Electric Co.;
Game unit, the avail data for avail data and the Utilities Electric Co. to the industrial enterprise receive assorted
Equilibrium Game obtains the expectation demand load.
In some embodiments, income determination unit includes:
Cost determination subelement, total electricity for industrial enterprise described in the unit price vector sum according to the Utilities Electric Co.
Power load vector, determines the Cost matrix that the industrial enterprise need to pay to the Utilities Electric Co.;Wherein, the unit price to
Amount is that the unit price of power of Each point in time of the Utilities Electric Co. in time arrow is formed by vector, the total electricity load
Vector is that the industrial enterprise is formed by vector in the prediction total electricity load of the Each point in time, the time to
Amount is to be formed by vector at multiple time points in the default future time section, and the power supply strategy includes the unit price
Vector;
Effectiveness determination subelement, for each energy consumption equipment of total electricity load vector sum according to the industrial enterprise
Effectiveness parameter, determine the utility matrix of the industrial enterprise;
Income determination subelement is used for the Cost matrix according to the industrial enterprise and the utility matrix, determines
The gain matrix of the industrial enterprise.
In some embodiments, cost determination subelement determines that the industrial enterprise need to be to the electric power using the first formula
The Cost matrix of company's payment, first formula include:
In formula, P is the Cost matrix that the industrial enterprise need to pay to the Utilities Electric Co.,For the total electricity load
Vector,For unit price vector;And/or
Effectiveness determination subelement determines the utility matrix of the industrial enterprise, the second formula packet using the second formula
It includes:
In formula, U is the utility matrix of the industrial enterprise, and α, beta, gamma ... is the effectiveness parameter of each energy consumption equipment,
For total electricity load vector;And/or
Income determination subelement determines the gain matrix of the industrial enterprise, the third formula packet using third formula
It includes:
Wn=U-P
In formula, Wn is the gain matrix of the industrial enterprise, and U is the utility matrix of the industrial enterprise, and P is the industry
The Cost matrix that enterprise need to pay to the Utilities Electric Co..
In some embodiments, income determination unit determines the avail data of the Utilities Electric Co., institute using the 4th formula
Stating the 4th formula includes:
Ws=Y-C
In formula, Ws is gain matrix, that is, avail data of the Utilities Electric Co., and Y is all users to Utilities Electric Co.'s branch
The cost metrix paid, C are the Cost matrix of the Utilities Electric Co..
In some embodiments, load adjustment module is specifically used for:According to the expectation demand load, it is fitted each energy consumption
Efficiency Function of the equipment in the default future time section;The Efficiency Function is solved using equal increment method, is obtained each
The corresponding optimization electric load of energy consumption equipment.
It will be appreciated that the electric power energy requirements response system of industrial enterprise provided in an embodiment of the present invention is real with the present invention
The electric power energy requirements response method for applying the industrial enterprise of example offer is corresponding, explanation, citing, advantageous effect in relation to content etc.
Part can refer to the corresponding contents in electric power energy requirements response method, not repeat herein.
The third aspect, the embodiment of the present invention provide a kind of computer readable storage medium, computer journey are stored on medium
Sequence can realize the above method when processor executes the computer program.
It should be noted that herein, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also include other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although with reference to the foregoing embodiments
Invention is explained in detail, it will be understood by those of ordinary skill in the art that:It still can be to aforementioned each implementation
Technical solution recorded in example is modified or equivalent replacement of some of the technical features;And these modification or
It replaces, the spirit and scope for various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution.
Claims (9)
1. a kind of electric power energy requirements response method of industrial enterprise, which is characterized in that including:
Acquire part throttle characteristics data of multiple energy consumption equipments in default historical time section in the industrial enterprise;
According to the part throttle characteristics data of each energy consumption equipment, deep learning is carried out using default neural network, obtains the energy consumption
Prediction electric load of the equipment in default future time section;
According to the prediction electric load of each energy consumption equipment, determine the industrial enterprise in the default future time section
Prediction total electricity load;
According to the prediction total electricity load of the industrial enterprise and the power supply strategy of Utilities Electric Co., industrial enterprise-electricity is carried out
Both sides' non-cooperative game of power company obtains expectation demand load of the Utilities Electric Co. to the industrial enterprise;
According to the expectation demand load, the prediction electric load respective to each energy consumption equipment is adjusted, and is obtained each
Optimization electric load in a each leisure of energy consumption equipment default future time section;
According to the respective optimization electric load of each energy consumption equipment, it is tactful to determine that the electricity consumption of the industrial enterprise arranges, and according to
The electricity consumption arranges strategy to carry out demand response to the Utilities Electric Co..
2. according to the method described in claim 1, it is characterized in that, it is described using preset neural network carry out deep learning it
Before, the method further includes:Collected part throttle characteristics data are normalized.
3. according to the method described in claim 1, it is characterized in that, the prediction total electricity according to the industrial enterprise
The power supply strategy of load and Utilities Electric Co. carries out both sides' non-cooperative game of industrial enterprise-Utilities Electric Co., including:
According to the power supply strategy of prediction the total electricity load and Utilities Electric Co., avail data and the institute of the industrial enterprise are determined
State the avail data of Utilities Electric Co.;
The avail data of avail data and the Utilities Electric Co. to the industrial enterprise carries out Nash Equilibrium game, obtains described
It is expected that demand load.
4. according to the method described in claim 3, it is characterized in that, the avail data of the determination industrial enterprise, including:
The total electricity load vector of industrial enterprise described in unit price vector sum according to the Utilities Electric Co., determines the industry
The Cost matrix that enterprise need to pay to the Utilities Electric Co.;Wherein, the unit price vector is the Utilities Electric Co. in the time
The unit price of power of Each point in time in vector is formed by vector, and the total electricity load vector is the industrial enterprise in institute
The prediction total electricity load for stating Each point in time is formed by vector, and the time arrow is the default future time section
Interior multiple time points are formed by vector, and the power supply strategy includes unit price vector;
According to the effectiveness parameter of each energy consumption equipment of total electricity load vector sum of the industrial enterprise, the industry is determined
The utility matrix of enterprise;
According to the Cost matrix of the industrial enterprise and the utility matrix, the gain matrix of the industrial enterprise is determined.
5. according to the method described in claim 4, it is characterized in that,
The Cost matrix that the industrial enterprise need to pay to the Utilities Electric Co., the first formula packet are determined using the first formula
It includes:
In formula, P is the Cost matrix that the industrial enterprise need to pay to the Utilities Electric Co.,It is vectorial for the total electricity load,For unit price vector;And/or
Determine that the utility matrix of the industrial enterprise, second formula include using the second formula:
In formula, U is the utility matrix of the industrial enterprise, and α, beta, gamma ... is the effectiveness parameter of each energy consumption equipment,It is described
Total electricity load vector;And/or
Determine that the gain matrix of the industrial enterprise, the third formula include using third formula:
Wn=U-P
In formula, Wn is the gain matrix of the industrial enterprise, and U is the utility matrix of the industrial enterprise, and P is the industrial enterprise
The Cost matrix that need to be paid to the Utilities Electric Co..
6. according to the method described in claim 3, it is characterized in that, determining the income number of the Utilities Electric Co. using the 4th formula
According to the 4th formula includes:
Ws=Y-C
In formula, Ws is gain matrix, that is, avail data of the Utilities Electric Co., and Y is what all users paid to the Utilities Electric Co.
Cost metrix, C are the Cost matrix of the Utilities Electric Co..
7. according to claim 1~6 any one of them method, which is characterized in that it is described according to the expectation demand load, it is right
Each respective prediction electric load of energy consumption equipment is adjusted, including:
According to the expectation demand load, it is fitted Efficiency Function of each energy consumption equipment in the default future time section;
The Efficiency Function is solved using equal increment method, obtains the corresponding optimization electric load of each energy consumption equipment.
8. a kind of electric power energy requirements response system of industrial enterprise, which is characterized in that including:
Data acquisition module, it is special for acquiring load of multiple energy consumption equipments in default historical time section in the industrial enterprise
Property data;
Load prediction module is carried out deep for the part throttle characteristics data according to each energy consumption equipment using default neural network
Degree study obtains prediction electric load of the energy consumption equipment in default future time section;
Load integrates module, for the prediction electric load according to each energy consumption equipment, determines the industrial enterprise in institute
State the prediction total electricity load in default future time section;
Non-cooperative game module, according to the prediction total electricity load of the industrial enterprise and the power supply strategy of Utilities Electric Co.,
The both sides' non-cooperative game for carrying out industrial enterprise-Utilities Electric Co., obtaining the Utilities Electric Co. needs the expectation of the industrial enterprise
Seek load;
Load adjustment module, for according to the expectation demand load, the prediction power load respective to each energy consumption equipment
Lotus is adjusted, and obtains the optimization electric load in each leisure of each energy consumption equipment default future time section;
Demand response module, for according to the respective optimization electric load of each energy consumption equipment, determining the use of the industrial enterprise
Electricity arranges strategy, and arranges strategy to carry out demand response to the Utilities Electric Co. according to the electricity consumption.
9. a kind of computer readable storage medium, computer program is stored on the medium, which is characterized in that execute in processor
Claim 1~7 any method can be realized when the computer program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810130412.5A CN108416509A (en) | 2018-02-08 | 2018-02-08 | Electric power energy requirements response method and system, the storage medium of industrial enterprise |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810130412.5A CN108416509A (en) | 2018-02-08 | 2018-02-08 | Electric power energy requirements response method and system, the storage medium of industrial enterprise |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108416509A true CN108416509A (en) | 2018-08-17 |
Family
ID=63128131
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810130412.5A Pending CN108416509A (en) | 2018-02-08 | 2018-02-08 | Electric power energy requirements response method and system, the storage medium of industrial enterprise |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108416509A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110276534A (en) * | 2019-06-05 | 2019-09-24 | 北京科技大学 | A kind of non-cooperation differential game method and device of smart grid-oriented energy consumption control |
CN110705756A (en) * | 2019-09-07 | 2020-01-17 | 创新奇智(重庆)科技有限公司 | Electric power energy consumption optimization control method based on input convex neural network |
CN111027785A (en) * | 2019-12-30 | 2020-04-17 | 源创芯动科技(宁波)有限公司 | Intelligent power utilization system and method for distributed power grid users |
-
2018
- 2018-02-08 CN CN201810130412.5A patent/CN108416509A/en active Pending
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110276534A (en) * | 2019-06-05 | 2019-09-24 | 北京科技大学 | A kind of non-cooperation differential game method and device of smart grid-oriented energy consumption control |
CN110276534B (en) * | 2019-06-05 | 2021-05-14 | 北京科技大学 | Non-cooperative differential game method and device for energy consumption control of smart power grid |
CN110705756A (en) * | 2019-09-07 | 2020-01-17 | 创新奇智(重庆)科技有限公司 | Electric power energy consumption optimization control method based on input convex neural network |
CN111027785A (en) * | 2019-12-30 | 2020-04-17 | 源创芯动科技(宁波)有限公司 | Intelligent power utilization system and method for distributed power grid users |
CN111027785B (en) * | 2019-12-30 | 2023-10-10 | 上海芯联芯智能科技有限公司 | Intelligent power utilization system and power utilization method for distributed power grid users |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Fang et al. | Multi-agent deep reinforcement learning for distributed energy management and strategy optimization of microgrid market | |
Guo et al. | Optimal strategies for the closed-loop supply chain with the consideration of supply disruption and subsidy policy | |
Luo et al. | Distributed peer-to-peer energy trading based on game theory in a community microgrid considering ownership complexity of distributed energy resources | |
Lotfi et al. | Target setting in the general combined-oriented CCR model using an interactive MOLP method | |
Kouaissah et al. | Optimizing sustainable and renewable energy portfolios using a fuzzy interval goal programming approach | |
CN108876132B (en) | Industrial enterprise energy efficiency service recommendation method and system based on cloud | |
CN108416509A (en) | Electric power energy requirements response method and system, the storage medium of industrial enterprise | |
CN111626587B (en) | Comprehensive energy system topology optimization method considering energy flow delay characteristics | |
Zhao et al. | Competition equilibrium of ride-sourcing platforms and optimal government subsidies considering customers’ green preference under peak carbon dioxide emissions | |
CN106779219A (en) | A kind of electricity demand forecasting method and system | |
CN109741103A (en) | A kind of short-term multiple target dual-layer optimization dispatching method | |
CN115860241B (en) | SALR-based distributed scheduling method and device for interconnected multi-region comprehensive energy system | |
CN107392366A (en) | The integrated energy system supply and demand bilateral comprehensive optimization method of meter and user behavior analysis | |
Yin et al. | Equilibrium stability of asymmetric evolutionary games of multi-agent systems with multiple groups in open electricity market | |
CN116862551A (en) | New energy consumption price decision method considering user privacy protection | |
Paredes V et al. | Activity analysis in forest planning | |
Wang et al. | Application of hybrid artificial bee colony algorithm based on load balancing in aerospace composite material manufacturing | |
Salameh et al. | Demand side management for smart houses: A survey | |
Li et al. | Deep Reinforcement Learning-Based Explainable Pricing Policy for Virtual Storage Rental Service | |
Zeng et al. | Multiobjective Optimized Dispatching for Integrated Energy System Based on Hierarchical Progressive Parallel NSGA‐II Algorithm | |
CN115776138A (en) | Micro-grid capacity planning method and device considering multi-dimensional uncertainty and energy management strategy | |
Lyu et al. | Cooperative game consistency optimal strategy of multi-microgrid system considering flexible load | |
Josaphat et al. | On optimization of copula-based extended tail value-at-risk and its application in energy risk | |
Li et al. | A demand–supply cooperative responding strategy in power system with high renewable energy penetration | |
Wang et al. | Development of cooperative game model between urban landscape design and urban brand image recognition |
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 |