CN108876132B - Industrial enterprise energy efficiency service recommendation method and system based on cloud - Google Patents
Industrial enterprise energy efficiency service recommendation method and system based on cloud Download PDFInfo
- Publication number
- CN108876132B CN108876132B CN201810580433.7A CN201810580433A CN108876132B CN 108876132 B CN108876132 B CN 108876132B CN 201810580433 A CN201810580433 A CN 201810580433A CN 108876132 B CN108876132 B CN 108876132B
- Authority
- CN
- China
- Prior art keywords
- user
- power utilization
- strategy
- power
- electricity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000005611 electricity Effects 0.000 claims abstract description 113
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000005265 energy consumption Methods 0.000 claims abstract description 15
- 238000013500 data storage Methods 0.000 claims abstract description 13
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 230000003993 interaction Effects 0.000 claims abstract description 8
- 238000009499 grossing Methods 0.000 claims description 28
- 238000011156 evaluation Methods 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 17
- 238000005457 optimization Methods 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 9
- 210000000349 chromosome Anatomy 0.000 claims description 6
- 230000002068 genetic effect Effects 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 5
- 238000005065 mining Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000007418 data mining Methods 0.000 claims description 4
- 238000012300 Sequence Analysis Methods 0.000 claims description 3
- 230000006978 adaptation Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 108090000623 proteins and genes Proteins 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 2
- 238000007726 management method Methods 0.000 abstract description 6
- 230000006872 improvement Effects 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 13
- 238000011161 development Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000009191 jumping Effects 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000012731 temporal analysis Methods 0.000 description 2
- 238000000700 time series analysis Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000005242 forging Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005316 response function Methods 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000006467 substitution reaction 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
- G06Q10/06—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
- G06Q10/06313—Resource planning in a project environment
-
- 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)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a cloud-based industrial enterprise energy efficiency service recommendation method and system, and relates to the technical field of electric power. The technical problem that the industrial power utilization service strategy cannot carry out differential power utilization strategy recommendation according to the actual conditions of different enterprises can be solved. The method comprises the following steps: s101, collecting power utilization information of power utilization equipment of different users in real time; s102, generating an electricity utilization data sequence from the collected electricity utilization information data to perform distributed data storage; s103, performing trend analysis on historical power consumption of the user through cloud data processing, predicting the power consumption condition of the user, and generating a final power consumption strategy aiming at factors influencing the power consumption level; and S104, recommending the final power utilization strategy to the user through human-computer interaction. The invention can carry out differentiated power utilization strategy recommendation according to the actual conditions of different users, improves the user acceptance to the greatest extent, realizes the improvement of power demand side management with lower cost, realizes the reasonable allocation of power resources, saves energy and reduces energy consumption.
Description
Technical Field
The invention relates to the technical field of computer networks, in particular to a cloud-based industrial enterprise energy efficiency service recommendation method and system.
Background
In order to guarantee sustainable development of energy environment in China, meet power utilization requirements of economic society, change economic development modes and build smart power grids, the development is not slow at all. With the rapid development of smart power grids in China, the requirements on the reliability of the power grids and the energy utilization rate are higher and higher. The intelligent power utilization is an important component of an intelligent power grid, and the intelligent power utilization is characterized in that the power grid flexibly and bidirectionally interacts with users, demand response is one of the most important implementation modes in energy utilization interaction, the users are guided to change power utilization loads through price or excitation and the like so as to participate in power grid peak shaving, and the effect of demand side management in a power market is improved through the active participation and optimization of the users in the power utilization mode. At present, the proportion of industrial power consumption in the power consumption of the whole society exceeds 70%, and the contradiction between the energy consumption structure and the green development of industrial enterprises and environmental restriction factors gradually appear. In the new situation, power demand side management should be well done in the industrial field, the industrial energy utilization mode and the energy utilization efficiency are optimized, green manufacturing is developed, and the coordinated development of industry, power and environment is ensured.
At present, the power utilization strategy of the group enterprise is optimized on the premise of saving power resources, the maximum operating income is won, the new power utilization idea of employees is cultured as a support, and the power utilization strategy of the group enterprise can properly increase the power consumption to further enlarge the production scale and ensure that the group enterprise wins greater profit besides insisting on the previous saving, high efficiency and efficiency maximization. The research on the production power load modeling based on the STN mainly comprises the production process based on the STN, the production equipment power load modeling, the temperature control equipment power load modeling considering the comfort degree and the mathematical model of intelligent power consumption management.
In the prior art, the power utilization strategy emphasizes taking measures from the electric energy supply side, adopts modes of updating equipment and the like to manage power utilization, and has higher cost. And the interactivity of the user at the demand side is low, and the user acceptance is not high. In a word, the power utilization service in the prior art is not high in personalization degree, and differential power utilization strategy recommendation cannot be performed according to actual conditions of different enterprises.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a cloud-based industrial enterprise energy efficiency service recommendation system, which can solve the technical problem that the power utilization service in the prior art can not carry out differentiated power utilization strategy recommendation according to the actual conditions of different enterprises.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
a cloud-based industrial enterprise energy efficiency service recommendation method comprises the following steps:
s101, collecting power utilization information of power utilization equipment of different users in real time;
s102, generating an electricity utilization data sequence from the collected electricity utilization information data to perform distributed data storage, gathering various different types of storage equipment in a network through application software by using a cloud storage technology to cooperatively work, and providing data storage and service access functions;
s103, providing a reasonable power utilization strategy set according to the dynamic pricing rule set through cloud data processing;
trend analysis is carried out on historical power utilization of the user, the power utilization condition of the user is predicted, and a preliminary power utilization strategy is generated by combining a power utilization strategy set;
analyzing the incidence relation of the internal electric equipment of the user by using an incidence rule algorithm, finding out factors influencing the power utilization level of the user, and generating a final power utilization strategy by combining the factors influencing the power utilization level based on the initial power utilization strategy;
and S104, recommending the final power utilization strategy to the user through human-computer interaction.
Further, after the step S104, the method further includes:
s105, evaluating the used electricity utilization strategy by a user;
and S106, respectively carrying out learning optimization on the system according to the user evaluation information and the actual power utilization condition, and returning an optimization result to the step S103.
Further, in step S103, trend analysis is performed on the historical power consumption of the user to predict the power consumption of the user, and a prediction model is set to implement, where the prediction model algorithm is as follows: setting an exponential smoothing for one time:
second exponential smoothing:
cubic exponential smoothing:
the prediction model is then:
wherein
T represents the T-th period, T represents the number of periods which are shifted backwards from the T period, alpha represents a smoothing coefficient, the electric quantity increase speed is high, and the value of alpha is larger;
respectively representing a first exponential smoothing value, a second exponential smoothing value, a third exponential smoothing value, ytIndicates the amount of power used during the t-th period of the history,
and (4) representing the predicted value of the electric quantity in the T + T period.
Further, in step S103, the association relationship of the internal electric equipment of the user is analyzed by using an association rule algorithm, and a method for finding a factor affecting the electric power consumption level of the user is as follows:
data mining is carried out on the electricity utilization information of all users, association rules of factors influencing the electricity utilization level of the users are mined, the electricity utilization process of the users is subdivided from different angles, and the subdivided angles are factors possibly influencing the electricity utilization level and compriseIndustry, month, economy, weather, and possible influence factor is IiIf the power level item set is { I ═ I1，I2，...，ImB } m ═ 1, 2, 3.., m, b denotes electricity usage levels, ordering the electricity usage database D to the user, where each transaction is a non-empty subset of I; the calculation formulas of the support degree and the confidence degree are respectively shown as a formula (1) and a formula (2);
wherein A represents factors which may influence the electricity utilization level, B represents the electricity utilization level, a threshold value is set manually according to the mining requirement, if a minimum support degree threshold value and a minimum confidence degree threshold value are met, the A, B is considered to have an association relationship, and then the factors which influence the electricity utilization level of the user are found.
Further, the step S106 of performing learning optimization on the system according to the user evaluation information, and returning the optimization result to the step S103 includes:
collecting user evaluation and analyzing the quality influence factor x of the corresponding strategyiAnd evaluating x according to the useriFrequency and degree of (c) determining factor weight omegai；
Let factor function f (x)i)＝ωixiThe policy function is
Finding the optimal strategy f (x) using genetic algorithmsopt；f(xi) Represents the evaluation factor function, xiTo influence the quality of the strategy, ωiRepresenting factor xiThe weight of (c);
when x isiAs a positive factor, f (x)i) Is a positive value; otherwise, f (x)i) Is a negative value;
for f (x)i) Carrying out binary coding; is suitable forThe response function is g (x)i)＝f(xi)；g(xi) The larger the value, the better the strategy; otherwise, the worse the strategy;
for a given n-scale factor group pop ═ x1，x2，x3，...xn}, individual xiHas an adaptation value of g (x)i) Then its probability of enrollment is
Selecting individuals with high entering probability to enter the selected population, eliminating individuals with low probability, and using x with maximum entering probabilityiSupplementing the population to obtain a population with the same size as the original population;
performing crossover and mutation; setting cross probability, and exchanging partial genes of two different chromosomes to be crossed according to the cross probability by a single-point cross method; setting variation probability, and carrying out chromosome variation according to the variation probability; the cross probability is relatively high, and the variation probability is extremely low;
setting termination conditions, and finding out the optimal strategy f (x)optAnd returning the optimal strategy to the step S103, and updating the power utilization strategy set.
Further, in the step S106, the system is optimized by learning according to the actual power consumption of the user, and the optimization result is returned to the step S103, which specifically includes: optimizing parameters of an exponential smoothing method;
knowing the actual power consumption yiPredicted value is
Then predict the most accurate time
When the prediction is most accurate, the difference between the actual value and the predicted value is minimum, and the optimal parameter alpha is determined by a golden section method;
suppose that at k iterations, the search interval is [ a ]k，bk]To further shorten the search interval, two points λ within the interval may be selectedk，μk∈[ak，bk]And λk＜μkThen, there are:
when in use
When, alpha is ∈ [ a ]k，μk]＝[ak+1，bk+1]，
When in use
When, alpha is epsilon [ lambda ]k，bk]＝[ak+1，bk+1]；
Returning the optimal smoothing coefficient alpha to step S103 makes the prediction of the electricity utilization condition of the user by the exponential smoothing method more accurate.
A cloud-based industrial enterprise energy efficiency service recommendation system comprises a power utilization information real-time acquisition module, an intelligent cloud service program module, an energy efficiency service recommendation program module and a system learning optimization program module; wherein,
the power utilization information real-time acquisition module is used for acquiring power utilization information of the user in real time and classifying the power utilization equipment of the user according to the actual power utilization condition;
the intelligent cloud service program module is used for performing distributed data storage on a user power utilization data sequence generated by data acquired by the power utilization information real-time acquisition module, predicting the power utilization trend of a user by using a time sequence analysis method through cloud data processing, and selecting a corresponding pricing rule according to the user power utilization prediction condition and the power utilization rule to generate a preliminary power utilization strategy; determining factors influencing the power utilization level according to the association relation found by the association rule, and giving a final power utilization strategy based on the preliminary power utilization strategy and in combination with the factors influencing the power utilization level;
the energy efficiency service recommendation program module is used for performing man-machine interaction with a user and presenting a final power utilization strategy generated by the intelligent cloud service program module to the user; then, the user evaluates according to the adopted and used electricity utilization strategy conditions;
and the system learning optimization program module performs learning optimization on the system according to the user evaluation information and the actual power utilization condition.
Preferentially, the intelligent cloud service program module comprises a dynamic pricing rule set submodule, a cloud storage submodule, a cloud data processing submodule and an electricity utilization strategy submodule; wherein,
the dynamic pricing rule set submodule stores a plurality of electricity price pricing rules;
the cloud storage sub-module stores the electricity utilization information acquired by the electricity utilization information real-time acquisition module;
the cloud data processing submodule processes the power utilization data and provides a reasonable power utilization strategy list according to the dynamic pricing rule set;
the power utilization strategy sub-module determines factors influencing the power utilization level according to the association relation found by the association rule, and gives a final power utilization strategy based on the preliminary power utilization strategy and in combination with the factors influencing the power utilization level;
preferably, the dynamic pricing rule set sub-module comprises electricity purchasing price rules set by power supply enterprises, and the electricity purchasing price rules comprise time-sharing pricing rules, large-user direct purchasing rules, high energy consumption limiting rules and reward rules, which are all input by power suppliers.
Preferably, the energy efficiency service recommendation program module comprises an intelligent recommendation sub-module and a manual assistance sub-module; wherein,
the intelligent recommendation sub-module is used for the incoming line consultation of the user electric power responsible person, automatically identifies the user information through the power utilization information real-time acquisition module, intensively extracts the power utilization strategy and the recommendation reason which accord with the user from the power utilization strategy through the processing of the intelligent cloud service program module, presents the power utilization strategy and the recommendation reason to the user and selects the power utilization strategy and the recommendation reason by the user;
the manual assisting sub-module is used for communicating with an online professional strategy recommender when the power utilization strategy recommended by the intelligent recommending sub-module does not meet the user requirement, and after the professional strategy recommender knows the user requirement, the user question is solved, the power utilization strategy satisfied by the user is given, and the user decision is assisted.
(III) advantageous effects
By adopting the cloud-based industrial enterprise energy efficiency service recommendation method and system, the user category can be automatically identified according to different users, the enterprise power utilization trend is predicted by applying a time series analysis method according to the dynamic power pricing rule, the historical power utilization data and the real-time power utilization data of the enterprise, a preliminary power utilization strategy is generated according to the prediction result, trend analysis is carried out on the historical power utilization of the user, the power utilization condition of the user is predicted, and the preliminary power utilization strategy is generated by combining a power utilization strategy set; and then analyzing the incidence relation of the internal electric equipment of the user by using an incidence rule algorithm, finding out factors influencing the power utilization level of the user, generating a final power utilization strategy by combining the factors influencing the power utilization level based on the initial power utilization strategy, and recommending the final power utilization strategy to the user through human-computer interaction. The invention can carry out differentiated power utilization strategy recommendation according to the actual conditions of different users, improves the user acceptance to the greatest extent, realizes the improvement of power demand side management with lower cost, realizes the reasonable allocation of power resources, saves energy and reduces energy consumption. Meanwhile, the cloud service technology is used, storage and processing of a large amount of data are distributed in the cloud, and the system service efficiency is improved.
The method continuously updates the strategy set, optimizes the operation parameters, improves the prediction precision and realizes the personalized power utilization strategy recommendation through the interactive feedback link with the user.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of the method steps of an embodiment of the present invention;
FIG. 2 is a block diagram of a system module architecture of an embodiment of the present invention;
FIG. 3 is a schematic flow chart illustrating the use of an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described, and it is obvious that the described embodiments are a part of the embodiments of the present invention, but not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example (b):
in the prior art, the power utilization strategy emphasizes taking measures from the electric energy supply side, and adopts modes of updating equipment and the like to carry out power utilization management, so that the cost is higher. The interactivity of the demand side user is low, and the user acceptance is not high. The embodiment of the invention provides a cloud-based industrial enterprise energy efficiency service recommendation method, which comprises the following steps of:
s101, collecting power utilization information of power utilization equipment of different users in real time;
s102, generating an electricity utilization data sequence from the collected electricity utilization information data to perform distributed data storage, gathering various different types of storage equipment in a network through application software by using a cloud storage technology to cooperatively work, and providing data storage and service access functions;
s103, providing a reasonable power utilization strategy set according to the dynamic pricing rule set through cloud data processing;
trend analysis is carried out on historical power utilization of the user, the power utilization condition of the user is predicted, and a preliminary power utilization strategy is generated by combining a power utilization strategy set;
analyzing the incidence relation of the internal electric equipment of the user by using an incidence rule algorithm, finding out factors influencing the power utilization level of the user, and generating a final power utilization strategy by combining the factors influencing the power utilization level based on the initial power utilization strategy;
s104, recommending the final power utilization strategy to a user through man-machine interaction;
s105, evaluating the used electricity utilization strategy by a user;
and S106, respectively carrying out learning optimization on the system according to the user evaluation information and the actual power utilization condition, and returning an optimization result to the step S103.
As shown in fig. 2, the energy efficiency service recommendation method according to the embodiment of the present invention is implemented by the following system modules:
the utility model discloses a real-time collection module of enterprise power consumption information: the method comprises the steps of specifically acquiring the power utilization information of the enterprise in real time, classifying the power utilization equipment of the enterprise according to the actual conditions of the enterprise, wherein the acquired information comprises the real-time power consumption, the power utilization power, the power utilization fluctuation rate, the power quality and the total power consumption of the enterprise of various power utilization equipment.
II, an intelligent cloud service program module: the system comprises a dynamic pricing rule set submodule, a cloud storage submodule and a cloud data processing submodule;
1. dynamic pricing rule set submodule: the electricity purchasing price rules set by the power supply enterprises, such as time-sharing pricing rules, large-user direct purchasing rules, high-energy consumption limiting rules, reward rules and the like, are input by the power suppliers;
2. cloud storage submodule: the distributed data storage is carried out on an enterprise electricity utilization data sequence generated by data collected by an enterprise electricity utilization information collection module, a large number of various different types of storage devices in a network are gathered through application software to cooperatively work by utilizing a cloud storage technology, and data storage and service access functions are provided;
3. cloud data processing submodule:
(1) performing trend analysis on historical power consumption of the enterprise by using a time sequence analysis method, and predicting the power consumption condition of the enterprise;
first exponential smoothing:
second exponential smoothing:
cubic exponential smoothing:
the prediction model is:
wherein
T represents the T-th period, T represents the period number which is shifted backwards from the T period, alpha represents a smoothing coefficient, the increasing speed of general electric quantity is high, and the value of alpha is larger;
respectively representing a first exponential smoothing value, a second exponential smoothing value, a third exponential smoothing value, ytIndicates the amount of power used during the t-th period of the history,
representing the predicted value of the electric quantity in the T + T period;
(2) carrying out data mining on the electricity utilization information of all enterprise users by using an Apriori algorithm based on cloud computing, mining association rules of factors influencing the electricity utilization level of the enterprise, subdividing the electricity utilization process of the enterprise from different angles, wherein the subdivided angles are factors possibly influencing the electricity utilization level, such as industry, months, economy, weather and the like, and the possible influencing factor is IiIf the power consumption level item set is I ═ I1，I2，...，ImB } m ═ 1, 2, 3.., m, b denotes electricity usage levels, a database D of electricity usage is rated for the enterprise, where each transaction is a non-empty subset of I;
the support degree and the confidence degree calculation formulas are respectively shown as formula (1) and formula (2):
wherein A represents factors possibly influencing the electricity utilization level, B represents the electricity utilization level, a threshold value is manually set according to the mining requirement, if a minimum support degree threshold value and a minimum confidence degree threshold value are met, the A, B is considered to have an incidence relation, and then the factors influencing the electricity utilization level of the enterprise are found;
4. the electricity utilization strategy set submodule comprises: after the enterprise electricity utilization data are processed by the cloud data processing submodule, generating an enterprise electricity utilization prediction result and finding enterprise electricity utilization level correlation factors;
firstly, knowing the power utilization forecasting condition of an enterprise and the power utilization rules in the dynamic pricing rule set submodule, selecting the corresponding pricing rules, and generating a power utilization strategy;
and secondly, according to the association relationship found by the association rule, giving a power utilization suggestion aiming at the factors influencing the power utilization level.
Thirdly, an energy efficiency service recommending program module: the system comprises an intelligent recommendation submodule and an artificial assistance submodule;
1. an intelligent recommendation submodule: the method comprises the steps that incoming line consultation is conducted on the electric power responsible person of the user enterprise, enterprise user information is automatically identified through an enterprise power utilization information acquisition module, power utilization strategies and recommendation reasons which accord with the user enterprise are extracted from strategy sets through processing of an intelligent cloud service program module, the power utilization strategies and the recommendation reasons are presented to the electric power responsible person of the user enterprise, and selection is conducted by a user.
2. A manual assistance submodule: when the power utilization strategy recommended by the intelligent recommendation sub-module does not meet the user requirements, the power responsible person of the user enterprise can communicate with the online professional strategy recommender, and after the professional strategy recommender knows the user requirements, the user questions are solved, the satisfied power utilization strategy of the user is given, and the decision of the user is assisted.
Fourthly, a system learning optimization program module:
1. evaluating the power utilization strategy after the user uses the power utilization strategy, collecting the user evaluation by the system, and optimizing the strategy set by using a genetic algorithm;
the method comprises the following steps:
(1) collecting user evaluation and analyzing the quality influence factor x of the corresponding strategyiAnd evaluating x according to the useriFrequency and degree of (c) determining factor weight omegai
(2) Let factor function f (x)i)＝ωixiThe policy function is
Finding the optimal f (x) by genetic algorithmopt。f(xi) Represents the evaluation factor function, xiTo influence the quality of the strategy, ωiRepresenting factor xiThe weight of (c). When x isiAs a positive factor, f (x)i) Is a positive value; otherwise, f (x)i) Is negative. For f (x)i) Binary coding is performed. The fitness function is therefore g (x)i)＝f(xi)。g(xi) The larger the value, the better the strategy; otherwise, the worse the strategy;
for a given n-scale factor group pop ═ x1，x2，x3，...xn}, individual xiHas an adaptation value of g (x)i) Then its probability of enrollment is
Selecting individuals with high entering probability to enter the selected population, eliminating individuals with low probability, and using x with maximum entering probabilityiSupplementing the population to obtain a population with the same size as the original population; setting cross probability, and exchanging partial genes of two different chromosomes (parents) to be crossed according to the cross probability by a single-point cross method; setting variation probability, and carrying out chromosome variation according to the variation probability, wherein the cross probability is generally large and the variation probability is extremely low; setting termination conditions, and finding out the optimal strategy f (x)opt。
2. And the prediction processing of the data processing module is predicted and optimized according to the actual power consumption of the enterprise, so that the prediction is more accurate.
And optimizing the power utilization prediction according to the actual power utilization condition of the enterprise. The parameters of the exponential smoothing method are optimized, and the actual electricity consumption y is knowniPredicted value is
Then predict the most accurate time
I.e. the difference between the actual value and the predicted value is minimal when the prediction is the most accurate. Determining an optimal parameter alpha by a golden section method, so that the prediction of an exponential smoothing method is more accurate;
suppose that at k iterations, the search interval is [ a ]k，bk]To further shorten the search interval, two points λ within the interval may be selectedk，μk∈[ak，bk]And λk＜μkThen, there are:
when in use
When a is in [ lambda ]k，μk]＝[ak+1，bk+1].
When in use
When, alpha is epsilon [ lambda ]k，bk]＝[ak+1，bk+1]
The method comprises the following specific steps:
(1) selecting initial data, and determining initial search interval [ a1，b1]Allowable error
The interval shortening rate τ is 0.618.
(2) Calculate the first two probe points λk＝ak+(1-τ)(bk-ak)，μk＝ak+τ(bk-ak) To find out
And set k to 1.
(3) If λk-ukIf | <, stop iteration, return to
Otherwise, jump to (4).
(4) If it is not
Jumping to (5); if it is not
Jump to (6).
(5) Search to the left, order
Calculate lambdak+1＝ak+1+(1-τ)(bk+1-ak+1) And an
And (7) jumping to.
(6) The search is performed to the right side,
calculating muk+1＝ak+1+τ(bk+1-ak+1) And
and (7) jumping to.
(7) Let k: k +1, jump to (3).
The following examples further illustrate the invention:
the enterprise power utilization information acquisition module acquires power utilization conditions of various production workshops and different types of equipment of an enterprise in real time, and for example, manufacturing enterprises are taken as examples, and the production equipment can be divided into metal cutting machine tools, forging and pressing equipment, hoisting and transporting equipment, woodworking casting equipment, professional production equipment, kinetic energy generation equipment, electrical equipment, industrial furnace and kiln equipment and the like. The enterprise electricity consumption information acquired by the enterprise electricity consumption information acquisition module comprises real-time electricity consumption, electricity consumption power, electricity consumption fluctuation rate, electricity consumption and electric energy quality of various electric equipment and total electricity consumption of an enterprise.
And carrying out distributed data storage on an enterprise power utilization behavior sequence generated by the data acquired by the enterprise power utilization information acquisition module. Through the function of the distributed file system, a large number of storage devices of different types in a network are integrated through application software to cooperatively work, and the functions of data storage and service access are provided.
The dynamic pricing rule set submodule stores electricity price rules formulated by power supply enterprises, including traditional rules, time-of-use pricing rules, large-user direct purchase rules, high-energy-consumption limiting rules, reward rules and the like, for example: the traditional rule is that the capacity of the transformer is below 315KVA, and a single electricity price is executed, namely the electricity charge of one-degree electricity and one-degree alternating electricity is used; and secondly, executing 'two-part electricity price' for the transformer with the capacity of 315KVA or more, and paying 'basic electricity price' according to the capacity of the transformer besides the electricity charges of using and alternating one-degree electricity. The time-sharing pricing rule adjusts the electricity price according to time-sharing periods, for example, the price is increased in the peak period of electricity utilization, and the price is reduced in the low peak period of electricity utilization, so that enterprises are prompted to avoid the peak period of electricity utilization. The direct purchasing rule of the large users accords with the national industrial policy, the power load is relatively stable, the unit output value energy consumption is low, the pollution emission is small, the power generation enterprise directly supplies power to the users with higher voltage level or larger power consumption and the power distribution network, the direct purchasing price is determined by negotiation between the power generation enterprise and the users, and the state-specified power transmission and distribution price is executed. The high energy consumption limiting rule provides certain limit to the production electricity consumption of high energy consumption enterprises. The reward rule gives a certain preferential policy to enterprises with good electricity utilization habits. And the power supply enterprise inputs the power utilization rule and stores the power utilization rule into the dynamic pricing rule set submodule.
And the cloud data processing submodule is responsible for processing the data of the power utilization enterprise and giving a reasonable power utilization strategy list according to the dynamic pricing rule set. Performing trend analysis on historical power consumption of the enterprise by using a time series analysis method, predicting the power consumption condition of the enterprise, and determining a preliminary strategy by combining a power consumption strategy set; and analyzing the incidence relation of the electric equipment in the enterprise by using an incidence rule algorithm to determine a final strategy.
After the electricity utilization data of the enterprise of the electricity utilization strategy set submodule is processed by the cloud data processing submodule, an enterprise electricity utilization prediction result is generated and the enterprise electricity utilization level relevant factors are found: firstly, knowing the power consumption forecasting situation of an enterprise and the power consumption rules in the dynamic pricing rule set submodule, selecting the corresponding pricing rules, and generating a power consumption strategy, such as the power consumption forecasting situation of the enterprise in the next month; the production operation is carried out by staggering the peak time of power utilization, and the production operation steps with high energy consumption and high power are arranged in a reasonable time interval as far as possible; the balance between the electricity saving control cost and the electricity utilization energy saving reward policy and the like. And secondly, according to the association relation discovered by the association rule, a power utilization suggestion is given for factors influencing the power utilization level, and an enterprise decision maker can make a specific decision according to the factors influencing the power utilization, so that the purposes of saving the power utilization, reducing the energy consumption and the cost are achieved, and the enterprise profit is improved.
And the intelligent recommendation submodule extracts the power utilization strategy and the recommendation reason which are in accordance with the user enterprise from the strategy set, and presents the power utilization strategy and the recommendation reason to the power responsible person of the user enterprise for selection by the user.
When the power utilization strategy recommended by the artificial auxiliary sub-module intelligent recommendation sub-module does not meet the user requirement, the user enterprise power responsible person can communicate with the online professional strategy recommendation personnel to finally meet the user requirement.
The system learning optimization module is used for evaluating the power utilization strategy after the user uses the power utilization strategy, collecting the user evaluation by the system and optimizing a strategy set by using a genetic algorithm; on the other hand, the prediction processing of the data processing module is optimized according to the actual power consumption of the enterprise, so that the prediction is more accurate.
As shown in fig. 3, in use, firstly, when a decision maker of a certain industrial enterprise enters the intelligent recommendation module and logs in the system, the enterprise electricity consumption information acquisition module automatically acquires relevant information of the enterprise, such as the name, the industry, the energy consumption condition, the scale, the distribution of functional blocks, and the like of the industrial enterprise.
And secondly, the cloud data processing submodule acquires the historical electricity utilization information of the enterprise, predicts the electricity utilization amount, and calculates the prediction result and the dynamic pricing strategy set to obtain a primary electricity utilization strategy. And calculating the incidence relation of factors influencing the power utilization level of the enterprise, optimizing the power utilization of the internal power utilization of the enterprise, generating a final power utilization strategy, and presenting the final power utilization strategy to an industrial enterprise user decision maker. And the industrial enterprise user decision maker screens the prediction result according to the actual conditions of the enterprise per se and correspondingly selects the power utilization strategy suitable for the production operation of the enterprise. If the decision maker of the industrial enterprise user has a question or an opinion on the strategy recommended by the power utilization strategy recommendation system, the decision maker can enter a manual assistance module to communicate with professional online customer service so as to determine a reasonable power utilization strategy and assist the enterprise power utilization decision.
And finally, evaluating the used power utilization strategy by the industrial enterprise user decision maker, and optimizing the system according to the actual power utilization condition of the enterprise and the evaluation of the industrial enterprise user decision maker after adopting the strategy. The optimization comprises two aspects, on one hand, the enterprise electricity utilization trend prediction is optimized according to the actual electricity utilization condition of the enterprise, and on the other hand, the strategy set is optimized by utilizing a genetic algorithm according to the evaluation of the electricity utilization enterprise. So as to provide more accurate power utilization trend prediction and a more reasonable power utilization strategy set.
In summary, the cloud-based industrial enterprise energy efficiency service recommendation method and system provided by the embodiment of the invention can assist the upper layer of an enterprise to make a scientific and reasonable electricity utilization decision, reduce the electricity utilization energy consumption of the industrial enterprise, improve the electricity utilization efficiency of the industrial enterprise, save the fund and improve the profit.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (7)
1. A cloud-based industrial enterprise energy efficiency service recommendation method is characterized by comprising the following steps:
s101, collecting power utilization information of power utilization equipment of different users in real time, and classifying the power utilization equipment of the users according to actual power utilization conditions;
s102, generating an electricity utilization data sequence from the collected electricity utilization information data to perform distributed data storage, gathering various different types of storage equipment in a network through application software by using a cloud storage technology to cooperatively work, and providing data storage and service access functions;
s103, providing a reasonable power utilization strategy set according to the dynamic pricing rule set through cloud data processing;
trend analysis is carried out on historical power utilization of the user, the power utilization condition of the user is predicted, and a corresponding pricing rule is selected by combining the power utilization strategy set to generate a preliminary power utilization strategy;
analyzing the incidence relation of the internal electric equipment of the user by using an incidence rule algorithm, finding out factors influencing the power utilization level of the user, and generating a final power utilization strategy by combining the factors influencing the power utilization level based on the initial power utilization strategy;
s104, recommending the final power utilization strategy to a user through man-machine interaction;
the dynamic pricing rule set in the step S103 includes a plurality of electricity price pricing rules, specifically includes electricity purchase price rules formulated by power supply enterprises, and the electricity purchase price rules include time-of-use pricing rules, large user direct purchase rules, high energy consumption limiting rules, and reward rules, which are all entered by power suppliers;
in step S103, the association relationship of the internal electric devices of the user is analyzed by using an association rule algorithm, and a method for finding a factor affecting the electric power level of the user is as follows:
data mining is carried out on the electricity utilization information of all users, association rules of factors influencing the electricity utilization level of the users are mined, the electricity utilization process of the users is subdivided from different angles, the subdivided angles are factors possibly influencing the electricity utilization level, the factors include industry, months, economy and weather, and the possible influencing factor is IiIf the power level item set is { I ═ I1，I2，...，ImB } m ═ 1, 2, 3.., m, b denotes electricity usage levels, ordering the electricity usage database D to the user, where each transaction is a non-empty subset of I; the calculation formulas of the support degree and the confidence degree are respectively shown as a formula (1) and a formula (2);
wherein A represents factors which may influence the electricity utilization level, B represents the electricity utilization level, a threshold value is set manually according to the mining requirement, if a minimum support degree threshold value and a minimum confidence degree threshold value are met, the A, B is considered to have an association relationship, and then the factors which influence the electricity utilization level of the user are found.
2. The cloud-based industrial enterprise energy efficiency service recommendation method according to claim 1, wherein the step S104 is followed by further comprising:
s105: evaluating a used electricity utilization strategy by a user;
s106: and respectively performing learning optimization on the system according to the user evaluation information and the actual power utilization condition, and returning an optimization result to the step S103.
3. The cloud-based industrial enterprise energy efficiency service recommendation method according to claim 1 or 2, wherein in step S103, trend analysis is performed on historical power consumption of the user, and power consumption of the user is predicted by constructing a prediction model, and the prediction model algorithm is as follows:
setting an exponential smoothing for one time:
second exponential smoothing:
cubic exponential smoothing:
the prediction model is then:
wherein
T represents the T-th stage, and T represents the backward push from the T stageThe number of shift periods, alpha represents a smooth coefficient, the electric quantity is increased quickly, and the value of alpha is larger;
respectively representing a first exponential smoothing value, a second exponential smoothing value, a third exponential smoothing value, ytIndicates the amount of power used during the t-th period of the history,
and (4) representing the predicted value of the electric quantity in the T + T period.
4. The cloud-based industrial enterprise energy efficiency service recommendation method according to claim 1, wherein the step S106 of performing learning optimization on the system according to the user evaluation information and returning the optimization result to the step S103 includes:
collecting user evaluation and analyzing the quality influence factor x of the corresponding strategyiAnd evaluating x according to the useriFrequency and degree of (c) determining factor weight omegai；
Let factor function f (x)i)＝ωixiThe policy function is
Finding the optimal strategy f (x) using genetic algorithmsopt；f(xi) Represents the evaluation factor function, xiTo influence the quality of the strategy, ωiRepresenting factor xiThe weight of (c);
when x isiAs a positive factor, f (x)i) Is a positive value; otherwise, f (x)i) Is a negative value;
for f (x)i) Carrying out binary coding; fitness function is g (x)i)＝f(xi)；g(xi) The larger the value, the better the strategy; otherwise, the worse the strategy;
for a given n-scale factor group pop ═ x1，x2，x3，...xn}, individual xiHas an adaptation value of g (x)i) Then its probability of enrollment is
Selecting individuals with high entering probability to enter the selected population, eliminating individuals with low probability, and using x with maximum entering probabilityiSupplementing the population to obtain a population with the same size as the original population;
performing crossover and mutation; setting cross probability, and exchanging partial genes of two different chromosomes to be crossed according to the cross probability by a single-point cross method; setting variation probability, and carrying out chromosome variation according to the variation probability; the cross probability is relatively high, and the variation probability is extremely low;
setting termination conditions, and finding out the optimal strategy f (x)optAnd returning the optimal strategy to the step S103, and updating the power utilization strategy set.
5. The cloud-based industrial enterprise energy efficiency service recommendation method according to claim 3, wherein in step S106: according to the actual electricity utilization condition of the user, learning and optimizing the system, and returning an optimization result to the step S103, specifically comprising: optimizing parameters of an exponential smoothing method;
knowing the actual power consumption yiPredicted value is
Then predict the most accurate time
When the prediction is most accurate, the difference between the actual value and the predicted value is minimum, and the optimal parameter alpha is determined by a golden section method;
suppose that at k iterations, the search interval is [ a ]k，bk]To further shorten the search interval, two points λ within the interval may be selectedk，μk∈[ak，bk]And λk＜μkThen, there are:
when in use
When, alpha is ∈ [ a ]k，μk]＝[ak+1，bk+1]，
When in use
When, alpha is epsilon [ lambda ]k，bk]＝[ak+1，bk+1].；
Returning the optimal smoothing coefficient alpha to step S103 makes the prediction of the electricity utilization condition of the user by the exponential smoothing method more accurate.
6. A cloud-based industrial enterprise energy efficiency service recommendation system is characterized by comprising a power utilization information real-time acquisition module, an intelligent cloud service program module, an energy efficiency service recommendation program module and a system learning optimization program module; wherein,
the power utilization information real-time acquisition module is used for acquiring power utilization information of the user in real time and classifying the power utilization equipment of the user according to the actual power utilization condition;
the intelligent cloud service program module is used for performing distributed data storage on a user power utilization data sequence generated by data acquired by the power utilization information real-time acquisition module, providing a reasonable power utilization strategy set according to the dynamic pricing rule set through cloud data processing, performing trend analysis on historical power utilization of a user by using a time sequence analysis method, predicting the power utilization condition of the user, and generating a preliminary power utilization strategy by combining the power utilization strategy set; determining factors influencing the power utilization level according to the association relation found by the association rule, and giving a final power utilization strategy based on the preliminary power utilization strategy and in combination with the factors influencing the power utilization level; the energy efficiency service recommendation program module is used for performing man-machine interaction with a user and presenting a final power utilization strategy generated by the intelligent cloud service program module to the user; then, the user evaluates according to the adopted and used electricity utilization strategy conditions;
the system learning optimization program module performs learning optimization on the system according to the user evaluation information and the actual power utilization condition;
the method for analyzing the incidence relation of the internal electric equipment of the user by applying the incidence rule algorithm and finding the factors influencing the electric level of the user comprises the following steps:
data mining is carried out on the electricity utilization information of all users, association rules of factors influencing the electricity utilization level of the users are mined, the electricity utilization process of the users is subdivided from different angles, the subdivided angles are factors possibly influencing the electricity utilization level, the factors include industry, months, economy and weather, and the possible influencing factor is IiIf the power level item set is { I ═ I1，I2，...，ImB } m ═ 1, 2, 3.., m, b denotes electricity usage levels, ordering the electricity usage database D to the user, where each transaction is a non-empty subset of I; the calculation formulas of the support degree and the confidence degree are respectively shown as a formula (1) and a formula (2);
wherein A represents factors which may influence the electricity utilization level, B represents the electricity utilization level, a threshold value is manually set according to the mining requirement, if a minimum support degree threshold value and a minimum confidence degree threshold value are met, the A, B is considered to have an association relationship, and then the factors which influence the electricity utilization level of the user are found;
the intelligent cloud service program module comprises a dynamic pricing rule set submodule, a cloud storage submodule, a cloud data processing submodule and an electricity utilization strategy submodule; wherein,
the dynamic pricing rule set submodule stores a plurality of electricity price pricing rules;
the cloud storage sub-module stores the electricity utilization information acquired by the electricity utilization information real-time acquisition module;
the cloud data processing submodule processes the power utilization data and provides a reasonable power utilization strategy list according to the dynamic pricing rule set;
the power utilization strategy sub-module determines factors influencing the power utilization level according to the association relation found by the association rule, and gives a final power utilization strategy based on the preliminary power utilization strategy and in combination with the factors influencing the power utilization level;
the dynamic pricing rule set sub-module comprises electricity purchasing price rules set by power supply enterprises, and the electricity purchasing price rules comprise time-sharing pricing rules, large-user direct purchasing rules, high energy consumption limiting rules and reward rules which are all recorded by power suppliers.
7. The cloud-based industrial enterprise energy efficiency service recommendation system of claim 6, wherein the energy efficiency service recommendation program module comprises an intelligent recommendation sub-module and a human assistance sub-module; wherein,
the intelligent recommendation sub-module is used for the incoming line consultation of the user electric power responsible person, automatically identifies the user information through the power utilization information real-time acquisition module, intensively extracts the power utilization strategy and the recommendation reason which accord with the user from the power utilization strategy through the processing of the intelligent cloud service program module, presents the power utilization strategy and the recommendation reason to the user and selects the power utilization strategy and the recommendation reason by the user;
the manual assisting sub-module is used for communicating with an online professional strategy recommender when the power utilization strategy recommended by the intelligent recommending sub-module does not meet the user requirement, and after the professional strategy recommender knows the user requirement, the user question is solved, the power utilization strategy satisfied by the user is given, and the user decision is assisted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810580433.7A CN108876132B (en) | 2018-06-07 | 2018-06-07 | Industrial enterprise energy efficiency service recommendation method and system based on cloud |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810580433.7A CN108876132B (en) | 2018-06-07 | 2018-06-07 | Industrial enterprise energy efficiency service recommendation method and system based on cloud |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108876132A CN108876132A (en) | 2018-11-23 |
| CN108876132B true CN108876132B (en) | 2020-12-22 |
Family
ID=64337317
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810580433.7A Active CN108876132B (en) | 2018-06-07 | 2018-06-07 | Industrial enterprise energy efficiency service recommendation method and system based on cloud |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108876132B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111966813A (en) * | 2019-05-20 | 2020-11-20 | 阿里巴巴集团控股有限公司 | Information mining method and device and information recommendation method and device |
| CN111311079A (en) * | 2020-01-21 | 2020-06-19 | 南方电网科学研究院有限责任公司 | Comprehensive energy-using service system for large users |
| CN111582911B (en) * | 2020-04-14 | 2023-06-30 | 广东卓维网络有限公司 | Friendly interactive power utilization system for multiple users and power grid |
| CN112995338B (en) * | 2021-04-14 | 2021-08-03 | 中南大学 | Method and system for evaluating access operation efficiency of network public opinion cloud platform |
| CN113723773B (en) * | 2021-08-16 | 2024-03-19 | 盛隆电气集团有限公司 | Electric energy decision system based on big data analysis |
| CN114648163A (en) * | 2022-03-22 | 2022-06-21 | 长沙军民先进技术研究有限公司 | Energy consumption data management system and method suitable for smart city |
| CN116562990B (en) * | 2023-07-03 | 2023-10-27 | 湖北国网华中科技开发有限责任公司 | Electricity selling transaction service recommendation method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102955977A (en) * | 2012-11-16 | 2013-03-06 | 国家电气设备检测与工程能效测评中心（武汉） | Energy efficiency service method and energy efficiency service platform adopting same on basis of cloud technology |
| CN104123134A (en) * | 2014-07-07 | 2014-10-29 | 四川中电启明星信息技术有限公司 | Intelligent electricity use data management method and system based on AMI and J2EE |
| CN105975613A (en) * | 2016-05-19 | 2016-09-28 | 国网重庆市电力公司客户服务中心 | Service channel recommendation method, device and system based on historical access data |
| CN106712040A (en) * | 2017-02-16 | 2017-05-24 | 深圳供电局有限公司 | Power grid demand side load balancing processing method and system |
| CN107256442A (en) * | 2017-04-18 | 2017-10-17 | 国网信通亿力科技有限责任公司 | Line loss calculation method based on mobile client |
| CN107480810A (en) * | 2017-07-21 | 2017-12-15 | 上海电力学院 | A kind of moon electricity demand forecasting method that double smoothing is improved using seasonal index number |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150213035A1 (en) * | 2014-01-24 | 2015-07-30 | Bit Stew Systems Inc. | Search Engine System and Method for a Utility Interface Platform |
-
2018
- 2018-06-07 CN CN201810580433.7A patent/CN108876132B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102955977A (en) * | 2012-11-16 | 2013-03-06 | 国家电气设备检测与工程能效测评中心（武汉） | Energy efficiency service method and energy efficiency service platform adopting same on basis of cloud technology |
| CN104123134A (en) * | 2014-07-07 | 2014-10-29 | 四川中电启明星信息技术有限公司 | Intelligent electricity use data management method and system based on AMI and J2EE |
| CN105975613A (en) * | 2016-05-19 | 2016-09-28 | 国网重庆市电力公司客户服务中心 | Service channel recommendation method, device and system based on historical access data |
| CN106712040A (en) * | 2017-02-16 | 2017-05-24 | 深圳供电局有限公司 | Power grid demand side load balancing processing method and system |
| CN107256442A (en) * | 2017-04-18 | 2017-10-17 | 国网信通亿力科技有限责任公司 | Line loss calculation method based on mobile client |
| CN107480810A (en) * | 2017-07-21 | 2017-12-15 | 上海电力学院 | A kind of moon electricity demand forecasting method that double smoothing is improved using seasonal index number |
Non-Patent Citations (3)
| Title |
|---|
| 中长期电力负荷预测的研究与应用;侯勇辉;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20140415;第C042-405页 * |
| 基于AMI的智能交互终端设计与实现;吕静;《中国优秀硕士学位论文全文数据库 信息科技辑》;20120415;第I137-74页 * |
| 基于黄金分割法优选的中长期负荷变权组合预测;王森等;《电测与仪表》;20160210;第85-92页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108876132A (en) | 2018-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108876132B (en) | Industrial enterprise energy efficiency service recommendation method and system based on cloud | |
| CN111353656B (en) | Steel enterprise oxygen load prediction method based on production plan | |
| Cheng et al. | Estimate at completion for construction projects using evolutionary support vector machine inference model | |
| CN110332605B (en) | BP neural network-based heat supply network energy consumption index analysis and early warning method | |
| CN111080101A (en) | AHP-based multi-dimensional evaluation method for service efficiency of power supply channel | |
| CN109376971A (en) | A kind of load curve forecasting method and system towards power consumer | |
| CN107944602A (en) | The evaluation of cloud manufacturing service and matching process based on trust model | |
| CN110796293A (en) | Power load prediction method | |
| CN112819225A (en) | Carbon market price prediction method based on BP neural network and ARIMA model | |
| CN113177366A (en) | Comprehensive energy system planning method and device and terminal equipment | |
| CN115965154A (en) | Knowledge graph-based digital twin machining process scheduling method | |
| CN115994778A (en) | Behavior fine portrait method for multiple users | |
| CN115049102A (en) | Electricity price prediction method and device, mobile terminal and storage medium | |
| CN110796296A (en) | Multi-objective investment optimization model construction method and device and computing equipment | |
| CN110570091A (en) | Load identification method based on improved F-score feature selection and particle swarm BP neural network | |
| CN112288187A (en) | Big data-based electricity sales amount prediction method | |
| CN116883057A (en) | XGBoost-based high-precision power customer marketing channel preference prediction system | |
| CN113011779A (en) | Energy consumption price compensation method and device based on fuzzy comprehensive evaluation | |
| CN114971696A (en) | Quotation method based on electricity consumption and flow information uploading system | |
| Wang et al. | Joint optimization decision of service provider selection and CODP positioning based on mass customization in a cloud logistics environment | |
| CN114819292A (en) | Park microgrid intelligent scheduling method and system based on comprehensive safety evaluation | |
| Zhang et al. | Batch sizing control of a flow shop based on the entropy-function theorems | |
| CN111915435A (en) | End-to-end electric energy transaction auction method based on evaluation mechanism | |
| CN110852480B (en) | Electric power data completion method | |
| CN110766426A (en) | Electricity price making method and device |
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 |