CN106682999A - Electric power user baseline load calculating method and apparatus thereof - Google Patents
Electric power user baseline load calculating method and apparatus thereof Download PDFInfo
- Publication number
- CN106682999A CN106682999A CN201611033053.9A CN201611033053A CN106682999A CN 106682999 A CN106682999 A CN 106682999A CN 201611033053 A CN201611033053 A CN 201611033053A CN 106682999 A CN106682999 A CN 106682999A
- Authority
- CN
- China
- Prior art keywords
- load
- load curve
- characteristic
- baseline
- curves
- 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 36
- 238000004364 calculation method Methods 0.000 claims abstract description 71
- 238000003066 decision tree Methods 0.000 claims abstract description 48
- 230000005611 electricity Effects 0.000 claims description 7
- BTCSSZJGUNDROE-UHFFFAOYSA-N gamma-aminobutyric acid Chemical compound NCCCC(O)=O BTCSSZJGUNDROE-UHFFFAOYSA-N 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000000611 regression analysis Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 abstract description 9
- 230000003993 interaction Effects 0.000 abstract description 8
- 230000008569 process Effects 0.000 abstract description 3
- 238000007726 management method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
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
- 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
-
- 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"
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an electric power user baseline load calculating method and an apparatus thereof. The method is characterized by according to a history day load curve set and a reference load curve set, forming several characteristic load curves; determining a key factor influencing a user baseline load and establishing a decision tree associated with the characteristic load curves and the key factor; and using the decision tree to carry out prediction calculating on the user baseline load, and feeding back a calculation result to each service system. A lot of data loading time is saved, accuracy of a baseline load calculating result is effectively increased, and an accurate data basis is provided for reasonably making and implementing electric power demand side management and demand response measures. Simultaneously, the apparatus is used for executing the method; an automation degree of electric power user baseline load prediction calculating is increased; baseline load prediction calculating efficiency is improved; and a problem that each service system is easy to frequently generate faults during a data interaction process is avoided.
Description
Technical Field
The invention relates to the technical field of power systems and automation thereof, in particular to a method and a device for calculating a baseline load of a power consumer.
Background
Load characteristic analysis is the basis of intelligent power grid research, budget of user baseline load according to load characteristics is an important decision basis for power grid expansion planning, scheduling operation, power supply construction and load management, and has important significance for guaranteeing safety, economy and high-quality operation of a power grid; the demand response, that is, the short-term power demand response, refers to that when the power wholesale market price increases or the system reliability is threatened, after receiving a direct compensation notification of an inductive reduction load or a power price increase signal sent by a power supplier, a power consumer changes its inherent conventional power consumption mode to reduce or push a certain period of power consumption load to respond to power supply, so as to ensure the stability of a power grid and suppress a short-term behavior of power price increase.
The traditional power load characteristic analysis methods mainly comprise two types: firstly, analyzing according to influence factors, namely extracting dependent variables one by one on the premise that the other variables are kept unchanged, and describing the influence degree of the dependent variables on the independent variables qualitatively or quantitatively; and secondly, performing classification analysis according to industries, namely analyzing the electricity utilization characteristics of various industries or users detailed to certain types, and qualitatively or quantitatively obtaining the influence of various types of users on the electricity utilization characteristics of the regional power grid.
However, in particular practice, baseline load prediction based on demand response has been a difficult problem. At present, due to the fact that loads are various in types, the characteristic difference is large, the load change randomness is strong, the difficulty in accurately calculating the baseline load of demand response is large, and particularly the baseline load prediction accuracy of singly considering a certain factor is very low. Moreover, the current baseline load prediction method and system lack an automatic means for baseline load prediction, so that the baseline load prediction efficiency is low, and frequent errors are easily caused in the data interaction process of each business system.
Disclosure of Invention
The invention aims to provide a method and a device for calculating a baseline load of a power consumer, and aims to solve the technical problems that in the prior art, due to the fact that the loads are various, the characteristic difference is large, the load change randomness is strong, the baseline load difficulty in accurate calculation of demand response is large, especially the baseline load prediction accuracy of a certain factor is low singly considered, and the baseline load prediction method and the baseline load prediction system lack an automatic means for predicting the baseline load, the baseline load prediction efficiency is low, and frequent errors are easy to occur in the data interaction process of each service system.
According to a first aspect of the embodiments of the present invention, there is provided a power consumer baseline load calculation method, including:
acquiring historical load data to obtain a historical daily load curve set, wherein the historical daily load curves contained in the historical daily load curve set correspond to the data structures of the reference load curves contained in the prestored reference load curve set;
forming a plurality of characteristic load curves according to the historical daily load curve set and the reference load curve set, converting the characteristic load curves into a CIM/OWL body object representation, and forming a characteristic load curve set by a plurality of the characteristic load curves;
determining key factors influencing the baseline load of a user;
establishing a decision tree associating the characteristic load curve and the key factors;
and performing predictive calculation on the user baseline load by using the decision tree, and feeding back the calculation result to each service system.
Further, the specific steps of forming a plurality of characteristic load curves according to the historical daily load curve set and the reference load curve set are as follows:
judging whether the compared historical daily load curve and the reference load curve meet preset similar standards or not;
and if the historical daily load curve meets the preset similar standard, forming a plurality of characteristic load curves by the historical daily load curve and the reference load curve.
Further, the step of judging whether the compared historical daily load curve and the reference load curve meet preset similarity criteria specifically includes:
calculating the Euclidean distance between all historical daily load curves in the historical daily load curve set and each reference load curve in the reference load curve set;
judging whether the Euclidean distance is less than or equal to a preset threshold value,
if the Euclidean distance is smaller than or equal to a preset threshold value, the historical daily load curve and the reference load curve meet a preset similar standard;
and if the Euclidean distance is larger than a preset threshold value, the historical daily load curve and the reference load curve do not meet a preset similar standard.
Further, if the preset similarity standard is met, forming a plurality of characteristic load curves by the historical daily load curve and the reference load curve specifically comprises:
calculating the load average value of all time points corresponding to the historical daily load curve and the reference load curve, wherein the average value and all corresponding time points form a characteristic load curve; and forming a plurality of characteristic load curves by the array of the historical daily load curves meeting the preset similar standard and the reference load curve.
Further, the step of determining key factors affecting the baseline load of the user specifically includes:
obtaining factors influencing the baseline load of a user;
extracting peak values and valley values of the historical load data and calculating the mean value of the historical load data to form three data sequences;
calculating the grey correlation degree between the historical load data and the factors by combining the data sequence and utilizing a grey correlation analysis method;
and determining key factors influencing the baseline load of the user according to the grey correlation degree.
Further, the step of establishing a decision tree associating the characteristic load curve and the key factors specifically includes:
calculating the characteristic load curve of the category and the GINI index of the key factor according to the characteristic load curve;
establishing a decision tree associating the characteristic load curve model and the key factors according to the GINI index;
the formula for calculating the GINI index of the characteristic load curve of the category and the key factor is as follows:
and D is the characteristic load curve set of the category, m is the number of key factors, i is the serial number of the key factors, Pi represents the probability that any characteristic load curve in D is influenced by the factor i, and Pi is equal to the number of the characteristic load curves influenced by the key factor i in D divided by the total number of the characteristic load curves in D.
Further, the step of performing predictive computation on the user baseline load by using the decision tree specifically includes:
acquiring a characteristic load curve corresponding to the baseline load to be calculated, historical load data belonging to the class of load curves and key factors through the decision tree;
and selecting a prediction method for prediction, wherein the prediction method comprises regression analysis prediction, similar trend prediction and neural network prediction, and performing smooth weight calculation to obtain a baseline load calculation result.
Further, the method further comprises: while the method is being performed, the historical load data, the historical daily load curve, the characteristic load curve, the key factors, the decision tree, and the baseline load calculation result are also stored.
Further, before the performing the predictive computation on the user baseline load by using the decision tree, the method further includes:
starting a service interface, and circularly waiting for an instruction which needs to perform baseline load calculation and/or data transmission, wherein the instruction is sent by each service system;
and receiving the instruction, and sending a message for confirming that the instruction is received to each service system through the service interface.
According to another aspect of the embodiments of the present invention, there is provided a power consumer baseline load calculation apparatus, configured to perform the power consumer baseline load calculation method provided by the first aspect of the embodiments of the present invention, where the apparatus includes:
the control system comprises a memory and a control processor, wherein the memory stores a reference load curve set;
the control processor comprises an electricity utilization characteristic modeling unit, a key factor identification unit, a decision tree establishment unit and a baseline load prediction calculation unit; wherein,
the power utilization characteristic modeling unit is used for acquiring historical load data to obtain a historical daily load curve set; the historical daily load curves contained in the historical daily load curve set correspond to a data structure of reference load curves contained in a prestored reference load curve set; the characteristic load curve is converted into a CIM/OWL body object to be represented, and a plurality of characteristic load curves form a characteristic load curve set;
the key factor determining unit is used for determining key factors influencing the baseline load of the user;
the decision tree establishing unit is used for establishing a decision tree associating the characteristic load curve and the key factors;
and the base line load prediction calculation unit is used for performing prediction calculation on the user base line load by using the decision tree and feeding back the base line load calculation result to each service system.
According to the technical scheme, the method and the device for calculating the baseline load of the power consumer, provided by the embodiment of the invention, have the advantages that a historical daily load curve set is obtained by acquiring historical load data, and the historical daily load curve contained in the historical daily load curve set corresponds to the data structure of the reference load curve contained in the prestored reference load curve set; forming a plurality of characteristic load curves according to the historical daily load curve set and the reference load curve set, converting the characteristic load curves into a CIM/OWL body object representation, and forming a characteristic load curve set by a plurality of the characteristic load curves; determining key factors influencing the baseline load of the user, and establishing a decision tree associating the characteristic load curve with the key factors; the decision tree is utilized to quickly determine the class of the characteristic load curve to which the baseline load to be calculated of the power consumer belongs and the historical load data of the power consumer, save a large amount of data loading time, effectively improve the accuracy of the baseline load calculation result, and provide accurate data basis for reasonably making and implementing power demand side management and demand response measures.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a flow chart illustrating a method for power consumer baseline load calculation in accordance with a preferred embodiment;
fig. 2 is a block diagram of a power consumer baseline load calculation apparatus according to a preferred embodiment.
The system comprises a memory 1, a control processor 2, a power utilization characteristic modeling unit 21, a key factor identification unit 22, a decision tree building unit 23 and a baseline load prediction calculation unit 24.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and 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.
According to a first aspect of the embodiments of the present invention, there is provided a power consumer baseline load calculation method, referring to fig. 1, which is a flowchart of the power consumer baseline load calculation method, as can be seen from fig. 1, the method includes:
step S1, obtaining historical load data to obtain a historical daily load curve set, wherein the historical daily load curves contained in the historical daily load curve set correspond to the data structures of the reference load curves contained in the prestored reference load curve set;
the historical load data of a certain power consumer refers to the power load data of the user in a limited period before the current time point, the end point of the limited period before the current time point includes but is not limited to the current time point, and the unit of the current time point can be hour, day or specific current time; for example, assuming that the current time point is 2016, 1, 10, years, the load data of the power consumer may be power load data in a period from one month before 2016, 1, 9, years to 12, 9, years; the length of the period can be set according to the requirement; in addition, the historical daily load curve is drawn according to the coordinates formed by the electric loads and the corresponding time points, and the change rule of the electric loads of the user in a certain period before the current time point can be displayed more intuitively.
The data structure of the historical daily load curve included in the historical daily load curve set corresponds to the data structure of the reference load curve included in the reference load curve set stored in advance, and means that the time points included in the two curves coincide with each other.
Step S2, forming a plurality of characteristic load curves according to the historical daily load curve set and the reference load curve set, converting the characteristic load curves into a Common Information Model (CIM)/Web Ontology object representation, and forming a characteristic load curve set by a plurality of characteristic load curves;
for the same power consumer, the historical daily load curves are different according to different contained time points, and for different power consumers, the historical daily load curves are different due to different electricity utilization habits among the consumers and different contained time points, so that historical daily load curves of different types form a historical daily load curve set; the reference load curve set is pre-stored in a memory, and each reference load curve has a respective characteristic. On this basis, the step of comparing the historical daily load curve set with the reference load curve set in step S2, and the step of forming a plurality of characteristic load curve refinements according to the comparison result further includes:
determining whether the calculated historical daily load curve and the reference load curve meet a preset similarity standard;
and if the historical daily load curve meets the preset similar standard, forming a plurality of characteristic load curves by the historical daily load curve and the reference load curve.
Further, the specifically determining whether the calculated historical daily load curve and the reference load curve satisfy a preset similarity standard is:
calculating the Euclidean distance between all historical daily load curves in the historical daily load curve set and each reference load curve in the reference load curve set; specifically, selecting characteristic time points; traversing the reference load curve set, and calculating Euclidean distances between all the historical daily load curves in the historical daily load curve set and each reference load curve in the reference load curve set one by one according to the characteristic time points; the characteristic time point can be set according to needs, for example, the golden time at night can be from eight to ten times later, because most of residential users have the habit of watching television in the period of time, and therefore the power load has a certain rule and can be circulated; for example, it may also be a certain point in time on a weekend or legal holiday, etc.
Judging whether the Euclidean distance is less than or equal to a preset threshold value,
if the Euclidean distance is smaller than or equal to a preset threshold value, the historical daily load curve and the reference load curve meet a preset similar standard;
and if the Euclidean distance is larger than a preset threshold value, the historical daily load curve and the reference load curve do not meet a preset similar standard.
Further, if the preset similarity standard is met, forming a plurality of characteristic load curves by the historical daily load curve and the reference load curve specifically comprises:
calculating the load average value of all time points corresponding to the historical daily load curve and the reference load curve, wherein the average value and all corresponding time points form a characteristic load curve; and forming a plurality of characteristic load curves by the historical daily load curves and the reference load curves which are similar in array.
Step S3, determining key factors influencing the baseline load of the user;
the baseline load of the power consumer may be affected by certain factors, such as weather factors; if the weather of the day is thunderstorm, common residential users can reduce the use of household electrical appliances so as to prevent the electrical appliances from being damaged by lightning; if the weather is cloudy, most of the power consumers can increase the use of the illuminating lamp in the daytime. As another example, a time factor; in the morning from eight to eleven hours, the electricity load of most residential users is lower than that in the evening from eight to eleven hours. As another example, a date factor; the power load of the legal holiday or weekend is higher than that of the working day; for the same reason, the power consumer baseline load is also affected by temperature, humidity, and special events. Based on the method, the inventor lists all factors which possibly influence the baseline load, and then identifies key factors which influence the baseline load of the user; the step S3 further includes the following steps:
obtaining factors influencing the baseline load of a user;
extracting peak values and valley values of the historical load data and calculating the mean value of the historical load data to form three data sequences;
calculating the grey correlation degree between the historical load data and the factors by combining the data sequence and utilizing a grey correlation analysis method;
and determining key factors influencing the baseline load of the user according to the grey correlation degree.
By determining key factors influencing the baseline load, non-key factors in all factors possibly influencing the baseline load are removed, the non-key factors are factors which have no influence on the baseline load or have negligible influence, and when the baseline load is predicted, the key factors are only listed in the range of prediction basis, so that the calculation time is saved, the interference of the non-key factors is avoided, and the prediction calculation efficiency of the baseline load is further improved.
Step S4, establishing a decision tree associating the characteristic load curve and the key factors;
the step of establishing a decision tree associating the characteristic load curve with the key factors specifically comprises:
calculating the characteristic load curve of the category and the GINI index of the key factor according to the characteristic load curve;
establishing a decision tree associating the characteristic load curve model and the key factors according to the GINI index;
the formula for calculating the GINI index of the characteristic load curve of the category and the key factor is as follows:
and D is the characteristic load curve set of the category, m is the number of key factors, i is the serial number of the key factors, Pi represents the probability that any characteristic load curve in D is influenced by the factor i, and Pi is equal to the number of the characteristic load curves influenced by the key factor i in D divided by the total number of the characteristic load curves in D.
By utilizing the decision tree, the class of the characteristic load curve to which the baseline load to be calculated of the power consumer belongs and the historical load data of the power consumer are quickly determined, so that a large amount of data loading time is saved, and the accuracy of the baseline load calculation result is effectively improved.
And step S5, performing predictive calculation on the user baseline load by using the decision tree, and feeding back the calculation result to each service system.
The step S5 of utilizing the decision tree to perform the predictive computation on the user baseline load further includes the following steps:
acquiring a characteristic load curve corresponding to the baseline load to be calculated, historical load data belonging to the class of load curves and key factors through the decision tree;
and selecting a prediction method for prediction, wherein the prediction method comprises regression analysis prediction, similar trend prediction and neural network prediction, and performing smooth weight calculation to obtain a baseline load calculation result.
Further, the method further comprises: while executing the method, storing the historical load data, the historical daily load curve, the characteristic load curve, the key factors, the decision tree, and the baseline load calculation.
Further, the method also comprises the steps of starting a service interface before predicting and calculating the user baseline load by utilizing the decision tree, and circularly waiting for an instruction which needs baseline load calculation and/or data transmission, wherein the instruction is sent by each service system;
and receiving the instruction, and sending a message for confirming that the instruction is received to each service system through the service interface.
The service systems refer to the power grid company service systems related to the baseline load, such as a marketing system or a dispatching system, and are determined by the application of the power grid company to the baseline load calculation method and device. The above-mentioned cyclic waiting refers to that for every service system, it is inquired one by one whether the instruction is received, if the instruction is received, it is executed correspondingly, if the instruction is not received, it is inquired for next service system, after all service systems are inquired, it is inquired one by one again.
In addition, before feeding back the calculation result to each service system in step S5, the method further includes converting the calculation result into standard interface interaction information, where the standard interface interaction information refers to an information interaction requirement that needs to be met for exchanging information with other service systems.
According to the technical scheme, the power consumer baseline load calculation method provided by the embodiment of the invention obtains a historical daily load curve set by acquiring historical load data, wherein the historical daily load curve contained in the historical daily load curve set corresponds to the data structure of a reference load curve contained in a pre-stored reference load curve set; forming a plurality of characteristic load curves according to the historical daily load curve set and the reference load curve set, converting the characteristic load curves into a CIM/OWL body object representation, and forming a characteristic load curve set by a plurality of the characteristic load curves; determining key factors influencing the baseline load of the user, and establishing a decision tree associating the characteristic load curve with the key factors; by utilizing the decision tree, the class of the characteristic load curve to which the baseline load to be calculated of the power consumer belongs and the historical load data of the power consumer are quickly determined, so that a large amount of data loading time is saved, the accuracy of the baseline load calculation result is effectively improved, and an accurate data basis is provided for reasonably making and implementing power demand side management and demand response measures.
According to another aspect of the embodiments of the present invention, there is provided a power consumer baseline load calculation apparatus, configured to execute the baseline load calculation method provided by the embodiments of the present invention, referring to fig. 2, which is a schematic structural diagram of the power consumer baseline load calculation apparatus, as can be seen from fig. 2, the apparatus includes:
the system comprises a memory 1 storing a reference load curve set and a control processor 2 connected with the memory 1;
the control processor 2 comprises an electricity utilization characteristic modeling unit 21, a key factor identification unit 22, a decision tree establishing unit 23 and a baseline load prediction calculation unit 24; wherein,
the power utilization characteristic modeling unit 21 is used for acquiring historical load data to obtain a historical daily load curve set; the historical daily load curves contained in the historical daily load curve set correspond to a data structure of reference load curves contained in a prestored reference load curve set; the characteristic load curve is converted into a CIM/OWL body object to be represented, and a plurality of characteristic load curves form a characteristic load curve set;
the key factor identifying unit 22 is configured to determine key factors affecting the baseline load of the user;
the decision tree establishing unit 23 is configured to establish a decision tree associating the characteristic load curve with the key factor;
the base line load prediction calculation unit 24 is configured to perform prediction calculation on the user base line load by using the decision tree, and feed back a base line load calculation result to each service system;
it should be noted that the memory 1 is used for storing the historical load data, the historical daily load curve, the characteristic load curve, the key factors, the decision tree, and the calculation result.
Preferably, the baseline load prediction calculation unit 24 is further configured to, before being configured to perform prediction calculation on the user baseline load by using the decision tree:
starting a service interface, and circularly waiting for an instruction which needs to perform baseline load calculation and/or data transmission, wherein the instruction is sent by each service system;
receiving the instruction, and sending a message for confirming that the instruction is received to each service system through the service interface;
and converting the baseline load calculation result into standard interface interaction information and feeding back the standard interface interaction information to each service system.
As can be seen from the foregoing technical solutions, the electric power consumer baseline load calculation apparatus provided in the embodiment of the present invention is configured to execute the electric power consumer baseline load calculation method provided in the embodiment of the present invention, in which a historical daily load curve set is obtained by acquiring historical load data, and a historical daily load curve included in the historical daily load curve set corresponds to a data structure of a reference load curve included in a reference load curve set stored in advance; forming a plurality of characteristic load curves according to the historical daily load curve set and the reference load curve set, converting the characteristic load curves into a CIM/OWL body object representation, and forming a characteristic load curve set by a plurality of the characteristic load curves; determining key factors influencing the baseline load of the user, and establishing a decision tree associating the characteristic load curve with the key factors; the decision tree is utilized to quickly determine the class of the characteristic load curve to which the baseline load to be calculated of the power consumer belongs and the historical load data of the power consumer, save a large amount of data loading time, effectively improve the accuracy of the baseline load calculation result, and provide accurate data basis for reasonably making and implementing power demand side management and demand response measures.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (10)
1. A power consumer baseline load calculation method, the method comprising:
acquiring historical load data to obtain a historical daily load curve set, wherein the historical daily load curves contained in the historical daily load curve set correspond to the data structures of the reference load curves contained in the prestored reference load curve set;
forming a plurality of characteristic load curves according to the historical daily load curve set and the reference load curve set, converting the characteristic load curves into a CIM/OWL body object representation, and forming a characteristic load curve set by a plurality of the characteristic load curves;
determining key factors influencing the baseline load of a user;
establishing a decision tree associating the characteristic load curve and the key factors;
and performing predictive calculation on the user baseline load by using the decision tree, and feeding back the calculation result to each service system.
2. The power consumer baseline load calculation method according to claim 1, wherein the specific steps of forming a plurality of characteristic load curves according to the historical daily load curve set and the reference load curve set are as follows:
judging whether the compared historical daily load curve and the reference load curve meet preset similar standards or not;
and if the historical daily load curve meets the preset similar standard, forming a plurality of characteristic load curves by the historical daily load curve and the reference load curve.
3. The power consumer baseline load calculation method according to claim 2, wherein the step of judging whether the compared historical daily load curve and the reference load curve meet preset similarity criteria is specifically as follows:
calculating the Euclidean distance between all historical daily load curves in the historical daily load curve set and each reference load curve in the reference load curve set;
judging whether the Euclidean distance is smaller than or equal to a preset threshold value or not;
if the Euclidean distance is smaller than or equal to a preset threshold value, the historical daily load curve and the reference load curve meet a preset similar standard;
and if the Euclidean distance is larger than a preset threshold value, the historical daily load curve and the reference load curve do not meet a preset similar standard.
4. The power consumer baseline load calculation method according to claim 2, wherein if the preset similarity criterion is satisfied, the forming of the historical daily load curve and the reference load curve into a plurality of characteristic load curves is specifically:
calculating the load average value of all time points corresponding to the historical daily load curve and the reference load curve, wherein the average value and all corresponding time points form a characteristic load curve; and forming a plurality of characteristic load curves by the array of the historical daily load curves meeting the preset similar standard and the reference load curve.
5. The power consumer baseline load calculation method of claim 1, wherein the step of determining key factors affecting the consumer baseline load specifically comprises:
obtaining factors influencing the baseline load of a user;
extracting peak values and valley values of the historical load data and calculating the mean value of the historical load data to form three data sequences;
calculating the grey correlation degree between the historical load data and the factors by combining the data sequence and utilizing a grey correlation analysis method;
and determining key factors influencing the baseline load of the user according to the grey correlation degree.
6. The power consumer baseline load calculation method of claim 1, wherein the step of establishing a decision tree associating the characteristic load curve with the key factors specifically comprises:
calculating the characteristic load curve of the category and the GINI index of the key factor according to the characteristic load curve;
establishing a decision tree associating the characteristic load curve model and the key factors according to the GINI index;
the formula for calculating the GINI index of the characteristic load curve of the category and the key factor is as follows:
wherein D is the characteristic load curve set of the category, m is the number of key factors, i is the number of key factors, PiRepresenting the probability that any one of the characteristic load curves in D is influenced by the factor i, PiEqual to the number of characteristic load curves in D affected by the critical factor i divided by the total number of characteristic load curves in D.
7. The power consumer baseline load calculation method of claim 6, wherein the step of performing predictive calculation on the consumer baseline load using the decision tree specifically comprises:
acquiring a characteristic load curve corresponding to the baseline load to be calculated, historical load data belonging to the class of load curves and key factors through the decision tree;
and selecting a prediction method for prediction, wherein the prediction method comprises regression analysis prediction, similar trend prediction and neural network prediction, and performing smooth weight calculation to obtain a baseline load calculation result.
8. The power consumer baseline load calculation method of claim 1, further comprising: storing the historical load data, the historical daily load curve, the characteristic load curve, the key factors, the decision tree, and the baseline load calculation while performing the method of claim 1.
9. The method according to claim 1, wherein before the predictive computation of the customer base line load using the decision tree, the method further comprises:
starting a service interface, and circularly waiting for an instruction which needs to perform baseline load calculation and/or data transmission, wherein the instruction is sent by each service system;
and receiving the instruction, and sending a message for confirming that the instruction is received to each service system through the service interface.
10. A consumer baseline load calculation apparatus for performing the method of any one of claims 1-9, the apparatus comprising: the control system comprises a memory and a control processor, wherein the memory stores a reference load curve set;
the control processor comprises an electricity utilization characteristic modeling unit, a key factor identification unit, a decision tree establishment unit and a baseline load prediction calculation unit; wherein,
the power utilization characteristic modeling unit is used for acquiring historical load data to obtain a historical daily load curve set;
the historical daily load curves contained in the historical daily load curve set correspond to a data structure of reference load curves contained in a prestored reference load curve set; the characteristic load curve is converted into a CIM/OWL body object to be represented, and a plurality of characteristic load curves form a characteristic load curve set;
the key factor determining unit is used for determining key factors influencing the baseline load of the user;
the decision tree establishing unit is used for establishing a decision tree associating the characteristic load curve and the key factors;
and the base line load prediction calculation unit is used for performing prediction calculation on the user base line load by using the decision tree and feeding back the base line load calculation result to each service system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611033053.9A CN106682999A (en) | 2016-11-18 | 2016-11-18 | Electric power user baseline load calculating method and apparatus thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611033053.9A CN106682999A (en) | 2016-11-18 | 2016-11-18 | Electric power user baseline load calculating method and apparatus thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106682999A true CN106682999A (en) | 2017-05-17 |
Family
ID=58866061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611033053.9A Pending CN106682999A (en) | 2016-11-18 | 2016-11-18 | Electric power user baseline load calculating method and apparatus thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106682999A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111381959A (en) * | 2018-12-29 | 2020-07-07 | 中兴通讯股份有限公司 | Capacity expansion method and device |
| CN111583063A (en) * | 2020-05-11 | 2020-08-25 | 国网四川省电力公司电力科学研究院 | Business start and end time detection method based on standard template and storage medium |
| CN113869601A (en) * | 2021-10-18 | 2021-12-31 | 深圳供电局有限公司 | Power consumer load prediction method, device and equipment |
| CN114565250A (en) * | 2022-02-21 | 2022-05-31 | 国网宁夏电力有限公司营销服务中心(国网宁夏电力有限公司计量中心) | Ordered electricity utilization intelligent monitoring method and system based on big data |
| CN114581263A (en) * | 2022-03-03 | 2022-06-03 | 广东电网有限责任公司 | Power grid load analysis method and device, electronic equipment and storage medium |
| CN114662043A (en) * | 2022-05-25 | 2022-06-24 | 广东电网有限责任公司佛山供电局 | Real-time evaluation method for user load response condition and related device thereof |
| CN115630753A (en) * | 2022-12-19 | 2023-01-20 | 西南交通大学 | Load baseline prediction method for electrolytic hydrogen production based on new energy multi-space-time scene |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100082172A1 (en) * | 2008-09-25 | 2010-04-01 | Korea Electric Power Corporation | Load forecasting analysis system for calculating customer baseline load |
| KR20130082960A (en) * | 2011-12-26 | 2013-07-22 | 주식회사 케이티 | Method and system of producing realtime customer baseline load |
| CN104239983A (en) * | 2014-10-13 | 2014-12-24 | 东南大学 | Big data perspective based demand response cutting load measurement method |
| CN104881706A (en) * | 2014-12-31 | 2015-09-02 | 天津弘源慧能科技有限公司 | Electrical power system short-term load forecasting method based on big data technology |
| KR20160022540A (en) * | 2014-08-20 | 2016-03-02 | 서강대학교산학협력단 | Method for estimating customer baseline load using data maning and apparatus thereof |
-
2016
- 2016-11-18 CN CN201611033053.9A patent/CN106682999A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100082172A1 (en) * | 2008-09-25 | 2010-04-01 | Korea Electric Power Corporation | Load forecasting analysis system for calculating customer baseline load |
| KR20130082960A (en) * | 2011-12-26 | 2013-07-22 | 주식회사 케이티 | Method and system of producing realtime customer baseline load |
| KR20160022540A (en) * | 2014-08-20 | 2016-03-02 | 서강대학교산학협력단 | Method for estimating customer baseline load using data maning and apparatus thereof |
| CN104239983A (en) * | 2014-10-13 | 2014-12-24 | 东南大学 | Big data perspective based demand response cutting load measurement method |
| CN104881706A (en) * | 2014-12-31 | 2015-09-02 | 天津弘源慧能科技有限公司 | Electrical power system short-term load forecasting method based on big data technology |
Non-Patent Citations (1)
| Title |
|---|
| 蔡洋主编: "《电力系统运行管理》", 31 August 1985, 北京：水利电力出版社 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111381959A (en) * | 2018-12-29 | 2020-07-07 | 中兴通讯股份有限公司 | Capacity expansion method and device |
| CN111583063A (en) * | 2020-05-11 | 2020-08-25 | 国网四川省电力公司电力科学研究院 | Business start and end time detection method based on standard template and storage medium |
| CN111583063B (en) * | 2020-05-11 | 2022-07-01 | 国网四川省电力公司电力科学研究院 | Business start and end time detection method based on standard template and storage medium |
| CN113869601A (en) * | 2021-10-18 | 2021-12-31 | 深圳供电局有限公司 | Power consumer load prediction method, device and equipment |
| CN114565250A (en) * | 2022-02-21 | 2022-05-31 | 国网宁夏电力有限公司营销服务中心(国网宁夏电力有限公司计量中心) | Ordered electricity utilization intelligent monitoring method and system based on big data |
| CN114565250B (en) * | 2022-02-21 | 2024-07-12 | 国网宁夏电力有限公司营销服务中心(国网宁夏电力有限公司计量中心) | Ordered electricity utilization intelligent monitoring method and system based on big data |
| CN114581263A (en) * | 2022-03-03 | 2022-06-03 | 广东电网有限责任公司 | Power grid load analysis method and device, electronic equipment and storage medium |
| CN114662043A (en) * | 2022-05-25 | 2022-06-24 | 广东电网有限责任公司佛山供电局 | Real-time evaluation method for user load response condition and related device thereof |
| CN115630753A (en) * | 2022-12-19 | 2023-01-20 | 西南交通大学 | Load baseline prediction method for electrolytic hydrogen production based on new energy multi-space-time scene |
| CN115630753B (en) * | 2022-12-19 | 2023-03-03 | 西南交通大学 | Load baseline prediction method for electrolytic hydrogen production based on new energy multi-space-time scene |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106682999A (en) | Electric power user baseline load calculating method and apparatus thereof | |
| Chaouch | Clustering-based improvement of nonparametric functional time series forecasting: Application to intra-day household-level load curves | |
| Meng et al. | A profit maximization approach to demand response management with customers behavior learning in smart grid | |
| AU2010257261B2 (en) | Method and system for demand response management in a network | |
| CN116646933A (en) | Big data-based power load scheduling method and system | |
| Ardakanian et al. | Computing Electricity Consumption Profiles from Household Smart Meter Data. | |
| Wahid et al. | A prediction approach for demand analysis of energy consumption using k-nearest neighbor in residential buildings | |
| Kim | Modeling special-day effects for forecasting intraday electricity demand | |
| Bassamzadeh et al. | Robust scheduling of smart appliances with uncertain electricity prices in a heterogeneous population | |
| EP2813979A1 (en) | Electric power consumption management system and method | |
| CN112508306A (en) | Self-adaptive method and system for power production configuration | |
| CN117874470B (en) | Analysis processing method for monitoring data of special transformer acquisition terminal | |
| Zhai et al. | Analysis of dynamic appliance flexibility considering user behavior via non-intrusive load monitoring and deep user modeling | |
| US20180225779A1 (en) | System and method for determining power production in an electrical power grid | |
| Jaaz et al. | A review on energy-efficient smart home load forecasting techniques | |
| CN117709554B (en) | Energy scheduling method and system combining heat storage with electromagnetic heater | |
| CN108346009A (en) | A kind of power generation configuration method and device based on user model self study | |
| Xu et al. | Spatial-temporal load forecasting using AMI data | |
| Stephen et al. | Non-Gaussian residual based short term load forecast adjustment for distribution feeders | |
| CN106651005B (en) | Baseline load prediction method and device | |
| Wang et al. | Three-dimensional maturity model of regional power users against the background of the ubiquitous power internet of things | |
| Miyasawa et al. | Energy disaggregation based on semi-supervised matrix factorization using feedback information from consumers | |
| CN116151509A (en) | Power information management method and system based on data fusion | |
| CN116862036A (en) | Load prediction method and device | |
| Bu et al. | Distributed unit commitment scheduling in the future smart grid with intermittent renewable energy resources and stochastic power demands |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170517 |