CN110991718A - Gridding planning method for power distribution network - Google Patents
Gridding planning method for power distribution network Download PDFInfo
- Publication number
- CN110991718A CN110991718A CN201911162135.7A CN201911162135A CN110991718A CN 110991718 A CN110991718 A CN 110991718A CN 201911162135 A CN201911162135 A CN 201911162135A CN 110991718 A CN110991718 A CN 110991718A
- Authority
- CN
- China
- Prior art keywords
- power
- data
- planning
- spatial prediction
- grid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 80
- 238000013439 planning Methods 0.000 title claims abstract description 73
- 230000005611 electricity Effects 0.000 claims abstract description 76
- 230000000737 periodic effect Effects 0.000 claims abstract description 51
- 230000035945 sensitivity Effects 0.000 claims abstract description 46
- 238000012937 correction Methods 0.000 claims abstract description 18
- 238000005192 partition Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000011161 development Methods 0.000 abstract description 14
- 238000011156 evaluation Methods 0.000 abstract description 4
- 238000013461 design Methods 0.000 abstract description 2
- 230000018109 developmental process Effects 0.000 description 12
- 238000010276 construction Methods 0.000 description 9
- 238000005259 measurement Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 7
- 238000010248 power generation Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000010606 normalization Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 230000007774 longterm Effects 0.000 description 4
- 230000009022 nonlinear effect Effects 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 3
- 230000009021 linear effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000003786 synthesis reaction Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 239000003921 oil Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013442 quality metrics Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
- Y04S50/14—Marketing, i.e. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a gridding planning method for a power distribution network, which belongs to the field of power distribution network design of a power system, and comprises the following steps of: step one, collecting data; step two, power supply grid division is carried out, and periodic dynamic pricing electricity charge data of each power user in a distribution area covered by one grid division are obtained; step three, analyzing the current situation power grid; step four, load prediction, namely, carrying out superposition correction on the spatial prediction data obtained by a spatial prediction method and the price sensitivity vector space to obtain new spatial prediction data; and step five, planning the target network, and planning the target network according to the new spatial prediction data. The method combines specific local economic indexes to carry out more-basis load prediction and economic development evaluation, and improves the applicability of grid planning of the power distribution network to local development differences.
Description
Technical Field
The invention belongs to the field of design of a power distribution network of a power system, and particularly relates to a method for realizing grid planning of the power distribution network by combining economic indexes.
Background
The grid planning of the power distribution network refers to that on the basis of the demand of land block power utilization, a target network frame is used as a guide, on the basis of power supply area division, a power supply area, a power supply network and a power supply unit three-layer network are further formed in a subdivided mode, the power distribution network planning is developed in a layered and graded mode, the power distribution network planning generally follows the principle from far to near and from bottom to top, namely, the near planning is guided by the long-term planning, the planning is extended from a low-voltage grade to a high-voltage grade, the long-term and near-term connection is generally emphasized, the long-term is preferably based on saturated load, and the short. For example, in a technical scheme provided by online documents such as a power distribution network overall planning method and system disclosed in chinese patent 2017102406329, the planning process mainly includes: the method comprises the steps of data collection, power supply grid division, current situation power grid analysis, load prediction, target network planning, excessive network frame determination, electric power corridor planning and the like.
In the prior art, a power supply area is divided into a planned built area, a natural development area and the like according to the saturation degree of power loads in the area, and due to the interference of social factors such as economic indexes and the like, the setting of different areas is difficult to plan absolutely according to the current or predictable power loads, so that more accurate guidance parameters are required to support during power supply grid division, current grid analysis and load prediction, and the aim of fine management of power distribution network construction is fulfilled by grid planning of a power distribution network.
Disclosure of Invention
The invention aims to provide a power distribution network gridding planning method, which is combined with specific local economic indexes to carry out more-basis load prediction and economic development evaluation and improve the applicability of power distribution network gridding planning to local development difference.
The technical scheme provided by the invention is that the power distribution network gridding planning method is used for predicting the data of the power load including the periodic dynamic pricing electricity fee in the stages of power supply grid division, current situation power grid analysis or load prediction.
Some method embodiments of the invention comprise the steps of:
step one, collecting data, wherein the collected data comprises periodic dynamic pricing electricity fee data of power users in each district;
step two, power supply grid division is carried out, and periodic dynamic pricing electricity charge data of each power user in a distribution area covered by one grid division are obtained;
analyzing the current situation power grid, analyzing regional price sensitivity according to the periodic dynamic pricing electricity charge data of each power consumer, and generating a price sensitivity vector space with at least two dimensions based on the geographic position;
step four, load prediction, namely, carrying out superposition correction on the spatial prediction data obtained by a spatial prediction method and the price sensitivity vector space to obtain new spatial prediction data;
step five, planning a target network, and planning the target network according to the new spatial prediction data;
step six, determining an excessive net rack;
and step seven, making a power corridor plan.
In some specific embodiments, the one grid division is a power supply area, a power supply grid, or a power supply unit.
In some specific embodiments, the dimensions of the price sensitivity vector space include planar geographic coordinates and price sensitivity levels.
Some method embodiments of the invention comprise the steps of:
step one, collecting data, wherein the collected data comprises periodic dynamic pricing electricity fee data of power users in each district;
step two, power supply grid division;
analyzing the current situation power grid, acquiring periodic dynamic pricing electricity charge data of each power user in a distribution area covered by one grid division, analyzing regional price sensitivity according to the periodic dynamic pricing electricity charge data of each power user, and generating a price sensitivity vector space with at least two dimensions based on the geographic position;
step four, load prediction, namely, carrying out superposition correction on the spatial prediction data obtained by a spatial prediction method and the price sensitivity vector space to obtain new spatial prediction data;
step five, planning a target network, and planning the target network according to the new spatial prediction data;
step six, determining an excessive net rack;
and step seven, making a power corridor plan.
In some embodiments, the period of the periodic dynamic pricing of electricity charges includes a quarterly, annual, or climatic period.
In some embodiments, the ratio of the number of switchyards to substations in a power grid is no less than 3: 1.
Some method embodiments of the invention comprise the steps of:
step one, collecting data, wherein the collected data comprises periodic dynamic pricing electricity fee data of power users in each district;
step two, power supply grid division;
analyzing the current situation power grid, acquiring periodic dynamic pricing electricity charge data of each power user in a distribution area covered by one grid division, analyzing regional price sensitivity according to the periodic dynamic pricing electricity charge data of each power user, and generating a price sensitivity vector space with at least two dimensions based on the geographic position;
step four, load prediction, namely, carrying out superposition correction on the spatial prediction data obtained by a spatial prediction method and the price sensitivity vector space to obtain new spatial prediction data;
step five, planning a target network, and planning the target network according to the new spatial prediction data;
step six, determining an excessive net rack;
and step seven, making a power corridor plan.
Some method embodiments of the invention comprise the steps of:
step one, collecting data, wherein the collected data comprises periodic dynamic pricing electricity fee data of power users in each district;
step two, power supply grid division;
step three, analyzing the current situation power grid;
step four, load prediction is carried out, periodic dynamic pricing electricity charge data of each power user in a distribution area covered by one grid partition are obtained, regional price sensitivity is analyzed according to the periodic dynamic pricing electricity charge data of each power user, price sensitivity vector spaces of at least two dimensions are generated based on geographic positions, and the spatial prediction data obtained through a spatial prediction method and the price sensitivity vector spaces are subjected to superposition correction to obtain new spatial prediction data;
step five, planning a target network, and planning the target network according to the new spatial prediction data;
step six, determining an excessive net rack;
and step seven, making a power corridor plan.
In some preferred embodiments, the data for predicting the electrical load includes calculating a periodic dynamic pricing electricity rate versus load shape function.
The invention has the beneficial effects that: the invention provides a power distribution network gridding planning method, which is combined with specific local economic indexes to carry out more-basis load prediction and economic development evaluation and improve the applicability of power distribution network gridding planning to local development difference.
Drawings
The technical solutions provided by the present invention will be further explained and explained with reference to the accompanying drawings and specific embodiments, so that those skilled in the art can implement and improve the present invention.
Fig. 1 is a conventional power distribution grid structure.
FIG. 2 is a flow chart of a method in one embodiment of the invention.
Detailed Description
It should be noted that the power grid is generally divided by combining with distinct geographical chenchenchen tables of roads, rivers, hills and the like, corresponding to functional partitions in detailed urban and rural control planning, each power grid should include 2 to 4 higher-level public substations with 10kV level outgoing lines in a long term, and it is recommended not to cross over 220kV power supply partitions. One trend of the existing electricity charging strategy is that the final electricity charge is a function related to the type, unit price, time period and transformer capacity of the electricity, wherein the unit price and the specific calculation mode are related to factors such as regional power generation cost and economic condition, and the like, which is a specific form of dynamic electricity pricing. One development direction of the smart grid in deployment is to provide technical support for dynamic power pricing.
The invention provides a method for realizing rolling type power distribution network gridding planning by combining periodic electric charge data, in particular to a method for predicting the electric load of a specified area in a power supply grid based on the shape of regional electric charge and using the electric load for the planning.
As shown in fig. 1, the existing distribution network structure in a divided power supply area according to this embodiment includes a power supply area configured by taking distribution of a high-voltage distribution network as a reference, a power supply grid of a palace based on division of a medium-voltage target grid, and a power supply unit based on division of a medium-voltage project plan, and generally starts a geographical layout of a 10kV switchgear station, i.e., a related substation, in the power supply grid.
Generally, the planning of the invention is to adopt a differential planning strategy for the planned built-up area, the planned built-up area and the natural development area according to the development maturity of the power distribution network. The planning principle is as follows:
(1) planning power supply units within the built-up area:
a) and for the power supply unit with the formed standard wiring, gradually transitioning to a cable ring network and an overhead three-section three-connection target network frame according to the principle of minimum transformation amount.
b) For the area with a complex space truss structure and without standard wiring, the wiring mode of the line is properly simplified, redundant connection and segmentation are cancelled, and one-time transformation is completed.
(2) Planning power supply units in a construction area: on the basis of solidifying the operation mode of the existing line, the transition from a cable ring network, an overhead three-section two-contact or single-contact network frame is gradually carried out according to the principle of minimum investment and minimum later construction waste by combining factors such as transformer substation resources, user power utilization time sequences, municipal supporting cable trench construction conditions, medium-voltage line utilization rate and the like, and the conditional area is constructed according to a target network frame.
(3) Power supply units in the natural development area: for the region where municipal planning is not clear temporarily and a load increase point cannot be determined, the prominent problem of the power grid is mainly solved according to the current power grid evaluation conclusion in the power supply unit, short plate indexes are improved, and standard wiring such as a single ring network, a three-section two-contact or single-contact is constructed by combining with the load development condition.
Corridor planning adopts a differential construction strategy according to the regional development condition. (1) For planning a built-up area, the communication between the existing tunnel and the pipe well is increased. (2) For planning a construction area, a tunnel pipe well is constructed along with a newly-built road in the initial construction stage, and the fully communication of a newly-built pipe ditch is realized. In the middle stage of construction, the tunnel and the pipe well are developed according to a construction and transformation plan of the urban main road or the secondary main road, and the tunnel or the pipe well is planned in advance and special treatment of a natural development area of a crossing point of the tunnel or the pipe well is reserved depending on municipal works such as rail transit and the like.
The day-to-day operations of a utility company, such as fuel resource planning and strategic real-time decision making to balance supply and demand of electricity, are strongly influenced by the prediction of electricity demand. There is typically a 10-20 times cost difference between the base load generating sources of the utility compared to purchases made through the grid at spot market rates to ensure customer demand is met. Such demand forecasting is used by electric utility companies to perform important operations, such as demand-side management; storage maintenance and scheduling; integration of renewable energy sources; selling excess electric energy on the power grid; coordinating the availability of cheaper power by alternative means such as energy exchange; establishing a bilateral power supply protocol; and to minimize the need to purchase expensive electricity from the grid at spot market prices.
Short-term load shape (Loadshape) prediction has become the current major research direction because utilities can achieve significant cost savings by accurately predicting demand and more accurate advance predictions within the upcoming 15 minutes to 4 hours. In the past, utilities have obtained such predictions from historical total supply curves for the urban areas served by the utilities.
Based on the above description, the core technical idea of the invention is that in the power grid division, current grid analysis or load prediction stage of the grid planning of the power distribution network, the data for predicting the power load includes the periodic dynamic pricing electricity fee.
In one method embodiment of the first aspect of the present invention, as illustrated in fig. 2, the following steps are included:
step one, collecting data, wherein the collected data comprises periodic dynamic pricing electricity fee data of power users in each district;
step two, power supply grid division is carried out, and periodic dynamic pricing electricity charge data of each power user in a distribution area covered by one grid division are obtained;
analyzing the current situation power grid, analyzing regional price sensitivity according to the periodic dynamic pricing electricity charge data of each power consumer, and generating a price sensitivity vector space with at least two dimensions based on the geographic position;
step four, load prediction, namely, carrying out superposition correction on the spatial prediction data obtained by a spatial prediction method and the price sensitivity vector space to obtain new spatial prediction data;
step five, planning a target network, and planning the target network according to the new spatial prediction data;
step six, determining an excessive net rack;
and step seven, making a power corridor plan.
In a specific implementation, the one grid partition is a power supply area, a power supply grid or a power supply unit.
In a specific implementation, the dimensions of the price sensitivity vector space include a plane geographic coordinate and a price sensitivity level.
In particular implementations, the period of the periodic dynamic pricing electricity charges includes a quarterly, annual, or climatic period.
In a specific implementation, the ratio of the number of switchyard stations to the number of substations in a power grid is not less than 3: 1.
In particular implementations, the data used to predict the electrical load includes calculating a periodic dynamic pricing electricity rate versus load shape function.
It can be seen that any embodiment of the invention should comprise the following steps: collecting data including periodic dynamic pricing electricity charge data of each power user in each distribution area, analyzing regional price sensitivity according to the periodic dynamic pricing electricity charge data of each power user, generating price sensitivity vector spaces of at least two dimensions based on geographic positions, performing superposition correction on spatial prediction data obtained by a spatial prediction method and the price sensitivity vector spaces to obtain new spatial prediction data, and performing target network planning according to the new spatial prediction data.
Other embodiments based on the above concept are also provided below
In a method embodiment of the second aspect of the invention, the method comprises the steps of:
step one, collecting data, wherein the collected data comprises periodic dynamic pricing electricity fee data of power users in each district;
step two, power supply grid division;
analyzing the current situation power grid, acquiring periodic dynamic pricing electricity charge data of each power user in a distribution area covered by one grid division, analyzing regional price sensitivity according to the periodic dynamic pricing electricity charge data of each power user, and generating a price sensitivity vector space with at least two dimensions based on the geographic position;
step four, load prediction, namely, carrying out superposition correction on the spatial prediction data obtained by a spatial prediction method and the price sensitivity vector space to obtain new spatial prediction data;
step five, planning a target network, and planning the target network according to the new spatial prediction data;
step six, determining an excessive net rack;
and step seven, making a power corridor plan.
In one embodiment of the method of the third aspect of the present invention, the method comprises the steps of:
step one, collecting data, wherein the collected data comprises periodic dynamic pricing electricity fee data of power users in each district;
step two, power supply grid division;
analyzing the current situation power grid, acquiring periodic dynamic pricing electricity charge data of each power user in a distribution area covered by one grid division, analyzing regional price sensitivity according to the periodic dynamic pricing electricity charge data of each power user, and generating a price sensitivity vector space with at least two dimensions based on the geographic position;
step four, load prediction, namely, carrying out superposition correction on the spatial prediction data obtained by a spatial prediction method and the price sensitivity vector space to obtain new spatial prediction data;
step five, planning a target network, and planning the target network according to the new spatial prediction data;
step six, determining an excessive net rack;
and step seven, making a power corridor plan.
In a method embodiment of the fourth aspect of the invention, the method comprises the steps of:
step one, collecting data, wherein the collected data comprises periodic dynamic pricing electricity fee data of power users in each district;
step two, power supply grid division;
step three, analyzing the current situation power grid;
step four, load prediction is carried out, periodic dynamic pricing electricity charge data of each power user in a distribution area covered by one grid partition are obtained, regional price sensitivity is analyzed according to the periodic dynamic pricing electricity charge data of each power user, price sensitivity vector spaces of at least two dimensions are generated based on geographic positions, and the spatial prediction data obtained through a spatial prediction method and the price sensitivity vector spaces are subjected to superposition correction to obtain new spatial prediction data;
step five, planning a target network, and planning the target network according to the new spatial prediction data;
step six, determining an excessive net rack;
and step seven, making a power corridor plan.
The above embodiments and specific embodiments relate to specific embodiments such as periodic dynamic pricing electricity charges, spatial prediction data, calculating a relationship function between the periodic dynamic pricing electricity charges and the load shape, and can be understood and implemented from the further description and embodiments below.
The inventive method is an improved technique for load shape prediction based on usage data obtained from smart meters that provides each customer with fine grained data about varying electricity usage. These improved load shape prediction techniques operate by using inference models that use historical smart meter Advanced Metering Infrastructure (AMI) signals, weather data, and real-time consumption loads obtained from the AMI signals to predict the most likely load shape in the upcoming 1 hour, 4 hour, or 24 hour time interval.
These existing load shape prediction techniques all assume that the electricity prices are constant. However, recently developed "smart grid" systems are beginning to support "dynamic electricity pricing," i.e., dynamically priced electricity charges, where the electricity price is dynamically adjusted based on current demand, and the resulting dynamic pricing information is communicated to the consumer in real time. For example, some european regions already have smart grid systems that provide consumers with hourly variable electricity prices through smart phone applications. This enables users to adjust their power usage when they see a cost change. However, as users adjust their power usage, the overall demand changes, which in turn changes the cost of the power. This "feedback effect" results in highly non-linear changes in electrical demand that cannot be accurately predicted using existing load shape prediction techniques.
Accordingly, there is a need in some embodiments to employ a technique for more accurately predicting electricity usage demand in a utility system that supports dynamic electricity pricing.
The disclosed embodiments relate to a system for predicting power demand in a utility system that supports dynamic pricing. During operation, the system receives a set of input signals containing electricity usage data from a set of smart meters that collect electricity usage data from users of the utility system. The system then uses the set of input signals and a projection technique to generate a projected load shape associated with the power usage in the utility system. Next, the system optimizes the predicted load shape to account for non-linear effects resulting from dynamic pricing. In this process, the system identifies a recent time period in a database containing recent empirically obtained load-related parameters for the utility system, wherein the load-related parameters in the recent time period are closest to a current set of load-related parameters for the utility system. The system then iteratively adjusts the predicted load shape based on the indicated change in the load-related parameter over the closest time period until the adjustment magnitude falls below the threshold value. Finally, the system predicts the power demand on the utility system based on the predicted load shape.
In some embodiments, the load-related parameters include one or more of a current time of day; the current demand for electricity; the current electricity charge; and the rate of change of the current electricity rate.
In some embodiments, the method further comprises using the predicted power demand to control a supply of power provided by the utility system.
In some embodiments, controlling the supply of power provided by a utility system includes one or more of controlling the amount of power generated by one or more power plants in the utility system; purchasing power to a public system through a power grid; selling the electricity generated by the invention through the power grid; storing the electricity for later use; and planning to build a new power plant for the utility system. In some embodiments, when using the set of input signals and a projection technique to generate a projected load shape, the system trains an inference model using the set of input signals, the inference model learning correlations between the set of input signals. The system then generates a set of inferred signals using an inference model, where the inference model generates an inferred signal for each input signal in the set of input signals. The system then uses a fourier-based decomposition and reconstruction technique that decomposes each signal in the inferred signal set into deterministic and random components, and uses the deterministic and random components to generate a set of synthetic signals that are statistically indistinguishable from the inferred signals. Finally, the system projects the combined signal into the future to produce a projected load shape for the power demand of the utility system. In some embodiments, in generating the combined signal, the system first generates a set of non-normalized signals. Next, the system performs an ambient weather normalization operation on the set of un-normalized signals to generate the combined signal, wherein the ambient weather normalization operation adjusts the set of un-normalized signals using historical, current, and predicted weather measurements and historical electrical usage data to account for the predicted impact of weather on electrical demand. In some embodiments, when using fourier-based decomposition and reconstruction techniques to generate the combined signal, the system uses a telemetry parameter synthesis (TPSS) technique that creates a high fidelity synthesis equation for generating the combined signal. In some embodiments, the system additionally uses predicted reactive and resistive loads in the predicted power demand to optimize power factor correction operations for the residential utility users. In some embodiments, the inference model is trained using Multivariate State Estimation Techniques (MSET). In some embodiments, receiving the set of input signals includes receiving a set of AMI signals.
Detailed description the following description is presented to enable any person skilled in the art to make and use the embodiments, and is provided in the context of a particular application and its requirements. Various modifications to the disclosed embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the present embodiments. Thus, the present embodiments are not limited to the embodiments shown, but are to be accorded the widest scope consistent with the principles and features disclosed herein. The data structures and code described in this detailed description are typically stored on a computer-readable storage medium, which may be any device or medium that can store code and/or data for use by a computer system. The computer readable storage medium includes, but is not limited to, volatile memory, non-volatile memory, magnetic and optical storage devices such as disk drives, magnetic tape, CDs (compact discs), DVDs (digital versatile discs or digital video discs), or other media capable of storing computer readable media now known or later developed. The methods and processes described in the detailed description section can be embodied as code and/or data, which can be stored in a computer-readable storage medium as described above. When a computer system reads and executes the code and/or data stored on the computer-readable storage medium, the computer system performs the methods and processes embodied as data structures and code and stored within the computer-readable storage medium. Further, the methods and processes described below may be included in hardware modules. For example, hardware modules may include, but are not limited to, Application Specific Integrated Circuit (ASIC) chips, Field Programmable Gate Arrays (FPGAs), and other programmable logic devices now known or later developed. When the hardware module is activated, the hardware module performs the methods and processes included within the hardware module.
Summary the disclosed embodiments facilitate reliable and safe operation of power generation and distribution systems by maintaining appropriate voltages at variable pricing structures and balancing supply and demand in an economical manner. To accomplish this, the disclosed embodiments use empirical multiple-input multiple-output (MIMO) control techniques that learn nonlinear and delayed feedback and control interactions between various load shape metrics on a real-time and early basis. More specifically, during operation, the disclosed embodiments receive real-time AMI signals, commercially available local weather feedback, and pricing signals for areas that support variable pricing of the smart grid. The disclosed embodiments process these signals using advanced machine learning models (e.g., MSET) to balance supply and demand and optimize power factor correction operations for residential users, thereby avoiding losses in residential power distribution. Thus, in addition to addressing a feedback control loop that couples the "load to a variable cost to induce consumer demand back to the load", the disclosed embodiments address the reactive load (from the ACS, by dynamically adjusting the capacitors in the distribution feeder to adjust fluorescent lamps, pool pumps) and the ac voltage/current phase. Note that this additional reactive load based feedback control loop also depends on the total load, which in turn depends on the "load-cost-demand-load" control loop. Both interacting coupled control loops also depend on the real-time solar power load, which depends on the real-time cloud dynamics and the time of day and month of the year that affects the illumination angle factor. However, integrating all these nonlinear feedback control parameters into conventional mathematical MIMO control techniques can be problematic. This is because conventional MIMO control techniques require mathematical functional relationships between the measured variables and the control actuator measurements, and such mathematical functional relationships are not readily available and may not exist in practice. Our new technology provides an alternative method to implement real-time empirical inference that is continuously adaptive as the relationship between continuously changing and interacting variables changes due to varying costs, lagging consumer demand, real-time changes in sunlight, and the degree of reactive and resistive loading. More specifically, the disclosed embodiments use an inference model to learn a plurality of load shapes from historical log files containing various measurements, e.g., in kilowatt-hours (KWH) and kilo-volt ampere-hours (KVA), from various systems such as solar arrays, wind power generation systems, electric vehicle charging stations, and local battery storage. The inference model is then used to predict power distribution system power flow based on load shape and predicted changes in load shape caused by changes in real-time weather, variable pricing signals, a recipe for adjusting variable prices, demand response feedback, utility demand control actuators that do not require changes, such as turning on and off interruptible power sources (e.g., from high cost gas turbines), and other feedback control related actions, such as automatically changing a customer's smart inverter power factor setting. The predicted power flow is then used to economically "balance" and "optimize" the load, voltage and current on the distribution network feeders. Our new technique uses an iterative process to optimize the load shape prediction to account for non-linearities. During the first iteration, the plurality of load shapes are projected forward as if there were no feedback control interaction between the predicted load shape and the most recently measured load shape, and as if there were no feedback control mechanism interaction between the parallel load shapes, e.g., the altered solar power generation components reduce the higher cost base load power generation components, which reduces cost and increases demand.
During the second iteration, the predicted load shape from the previous iteration is regressed (e.g., using a non-linear, non-parametric regression) against the historical database of signals to identify a past "closest" time period that matches (e.g., based on the global R) during a "moving window" iteration. 2 quality metric) of the predicted load shape and a first time derivative of the predicted load shape. (We empirically determined that the values of the load shapes and their rates of change correlate with the past interaction dynamics between the set of load shapes.)
During a third and subsequent iterations, the new projected load shape is regressed against the moving window historical load shape to more closely match the projected load shape and the first time derivative of the projected load shape relative to the historical dynamic load shape and related derivatives. The iterative process continues until the total difference between the current iteration output and the previous iteration output, such as the Root Mean Square Error (RMSE), drops to less than 1% improvement.
This non-linear empirical MIMO iterative loop repeats periodically in a "guided" fashion whenever the load shape projection begins to deviate from the new input measurement load shape observations. For example, a "trigger" of a new invocation to initiate an iteration may be activated when the most recent projection deviates from the new incoming measured load shape s by 2% of the aggregate RMSE.
Exemplary Utility System
An exemplary utility system includes an embodiment according to the disclosure in which a group of power plants are connected to a domestic and commercial power grid. The power plant may generally comprise any type of power generation facility, such as a nuclear power plant, a solar power plant, a wind or wind farm, or a coal, natural gas or oil fired power plant. Access of the power plant to the grid may deliver electrical energy to homes and businesses within areas served by the utility system and may also transfer electricity to and from other utility systems. Power grid delivery to homes and businesses periodically sends AMI signals to a data center containing electricity usage data, including kilowatt-hour measurements and kilowatt-hour measurements, through individual smart meters.
The control system in the data center receives the AMI signals from the smart meters along with the weather data, including historical, current and forecasted weather information, and generates a load forecast for controlling the power plant and other operations of the power grid, the operations involved in calculating the load forecast will be discussed in more detail below.
Dynamic price
According to the disclosed embodiments, how the dynamic price affects the electrical load through a feedback loop. During system operation, the dynamic price 132 of power is displayed to utility customer 136 via some type of electronic device, such as mobile phone 1342. If the dynamic price 132 changes significantly, the utility consumer 136 may perform an action 140 that changes the utility user's demand for electricity, e.g., if the dynamic price increases significantly, the utility consumer 136 may increase the thermostat setting of the air conditioner, or may delay the operation of the clothing until a later time when the electricity is cheaper. If the total demand 140 for power varies significantly, this will result in a change 132 in the dynamic price which will result in a further change in demand in the continuous feedback loop.
Generating load shape predictions
In some embodiments showing how the above-described system calculates an optimized load shape prediction, the system is obtained by the utility system from a multitude of smart meters starting from the AMI meter signal. These AMI meter signals include two historical AMI signals and a recent AMI signal. The system feeds back the most recent AMI signals into an inferential MSET module to train an inferential model to learn correlations between the most recent AMI signals and to use the trained inferential model to produce a set of inferential signals next, the system feeds the inferential signals into each signal 206 in the set of decomposed inferential signals that the TPSS synthesis module performs the TPSS training operation and then uses the deterministic and stochastic components to generate a corresponding set of synthetic signals that is statistically indistinguishable from the inferred signals. (for a more detailed description of TPSS, please see "SpectraDe composition and Restructionno Telemetric Signals from Enterprise computing systems", KCGross and ESChuster, Proc2006IEEEInternational multiconductor computer science & computer Eng., LasVegas, New Jun, No. 6.05 2004). The system then projects this combined signal into the future to produce an unnormalized TPSS forecast for a group of utility users with large demand for power.
Next, the system feeds the non-normalized TPSS predictions into an ambient weather normalization module that normalizes the non-normalized TPSS predictions to account for power usage changes caused by predicted changes in ambient weather. The normalization process includes analyzing the historical AMI signal with respect to historical weather measurements to determine how the AMI meter signal changes for different weather patterns. The normalization process then modifies the non-normalized TPSS predictions using the current and predicted weather measurements to account for the predicted weather conditions. This produces a load shape prediction input to a nonlinear optimizer that uses empirical load-related data to optimize the load shape prediction to take into account the nonlinear effects of dynamic pricing and power factor correction to produce an optimized load shape prediction.
Next, the optimized load shape prediction is used to perform various operations to control the power supply provided by the utility system. It can also be used to optimally apply power factor correction operations to residential customers, avoiding residential power distribution losses.
The optimized load shape prediction may also be used to generate updated power rate feedbacks, further altering the optimized load shape as described above.
Generating optimized load shape predictions
Some embodiments illustrate operations involving predicting an optimized load shape that is optimized to account for non-linear effects resulting from dynamic pricing according to the disclosed embodiments. During operation, the system receives a set of input signals containing power usage data from a set of smart meters that collect power usage data from users of the utility system. The system then uses the set of input signals and a projection technique to generate a projected load shape associated with the power usage in the utility system. The system then optimizes the predicted load shape to account for the non-linear effects resulting from dynamic pricing. In this process, the system identifies a most recent time period in a database containing most recently empirically obtained load-related parameters of the utility system, wherein the load-related parameters in the most recent time period are closest to a current set of load-related parameters of the utility system. The system then iteratively adjusts the predicted load shape based on the indicated change in the load-related parameter over the closest time period until the adjustment magnitude falls below the threshold value. Finally, the system predicts the power demand of the utility system based on the predicted load shape.
Some embodiments use projection techniques to generate the projected load shape. Details regarding the projection techniques described above are provided in these embodiments, the system can use the set of input signals to train an inference model that learns correlations between the set of input signals, and then use an inference model to generate a set of inference signals, where the inference model generates an inference signal for each input signal in the set of input signals. The system then uses a fourier-based decomposition and reconstruction technique that decomposes each signal in the set of inferred signals into deterministic and random components and uses the deterministic and random components to generate a set of composite signals that are statistically indistinguishable from the inferred signals. Finally, the system projects the combined signal into the future to produce a projected load shape for the power demand of the utility system.
Various modifications to the disclosed embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the present invention. Thus, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
The foregoing descriptions of embodiments have been presented only for purposes of illustration and description. They are not intended to be exhaustive or to limit the specification to the forms disclosed. Accordingly, many modifications and variations will be apparent to practitioners skilled in the art. Additionally, the above disclosure is not intended to limit the present specification. The scope of the present description is defined by the appended claims.
Claims (10)
1. A power distribution network gridding planning method is characterized by comprising the following steps: in the power supply grid division, current grid analysis or load prediction stage, the data for predicting the power load comprises periodic dynamic pricing electricity charges.
2. The power distribution network meshing planning method according to claim 1, comprising the following steps:
step one, collecting data, wherein the collected data comprises periodic dynamic pricing electricity fee data of power users in each district;
step two, power supply grid division is carried out, and periodic dynamic pricing electricity charge data of each power user in a distribution area covered by one grid division are obtained;
analyzing the current situation power grid, analyzing regional price sensitivity according to the periodic dynamic pricing electricity charge data of each power consumer, and generating a price sensitivity vector space with at least two dimensions based on the geographic position;
step four, load prediction, namely, carrying out superposition correction on the spatial prediction data obtained by a spatial prediction method and the price sensitivity vector space to obtain new spatial prediction data;
step five, planning a target network, and planning the target network according to the new spatial prediction data;
step six, determining an excessive net rack;
and step seven, making a power corridor plan.
3. The power distribution network meshing planning method according to claim 2, characterized in that: the one grid division is a power supply area, a power supply grid or a power supply unit.
4. The power distribution network meshing planning method according to claim 2, characterized in that: the dimensions of the price sensitivity vector space comprise plane geographic coordinates and price sensitivity levels.
5. The power distribution network meshing planning method according to claim 1, comprising the following steps:
step one, collecting data, wherein the collected data comprises periodic dynamic pricing electricity fee data of power users in each district;
step two, power supply grid division;
analyzing the current situation power grid, acquiring periodic dynamic pricing electricity charge data of each power user in a distribution area covered by one grid division, analyzing regional price sensitivity according to the periodic dynamic pricing electricity charge data of each power user, and generating a price sensitivity vector space with at least two dimensions based on the geographic position;
step four, load prediction, namely, carrying out superposition correction on the spatial prediction data obtained by a spatial prediction method and the price sensitivity vector space to obtain new spatial prediction data;
step five, planning a target network, and planning the target network according to the new spatial prediction data;
step six, determining an excessive net rack;
and step seven, making a power corridor plan.
6. The power distribution network meshing planning method according to claim 1, characterized in that: the period of the periodic dynamic pricing electricity charges includes a quarterly, annual or climatic period.
7. The power distribution network meshing planning method according to claim 1, characterized in that: in a power grid, the ratio of the number of switchyard to substation is not less than 3: 1.
8. The power distribution network meshing planning method according to claim 1, comprising the following steps:
step one, collecting data, wherein the collected data comprises periodic dynamic pricing electricity fee data of power users in each district;
step two, power supply grid division;
analyzing the current situation power grid, acquiring periodic dynamic pricing electricity charge data of each power user in a distribution area covered by one grid division, analyzing regional price sensitivity according to the periodic dynamic pricing electricity charge data of each power user, and generating a price sensitivity vector space with at least two dimensions based on the geographic position;
step four, load prediction, namely, carrying out superposition correction on the spatial prediction data obtained by a spatial prediction method and the price sensitivity vector space to obtain new spatial prediction data;
step five, planning a target network, and planning the target network according to the new spatial prediction data;
step six, determining an excessive net rack;
and step seven, making a power corridor plan.
9. The power distribution network meshing planning method according to claim 1, comprising the following steps:
step one, collecting data, wherein the collected data comprises periodic dynamic pricing electricity fee data of power users in each district;
step two, power supply grid division;
step three, analyzing the current situation power grid;
step four, load prediction is carried out, periodic dynamic pricing electricity charge data of each power user in a distribution area covered by one grid partition are obtained, regional price sensitivity is analyzed according to the periodic dynamic pricing electricity charge data of each power user, price sensitivity vector spaces of at least two dimensions are generated based on geographic positions, and the spatial prediction data obtained through a spatial prediction method and the price sensitivity vector spaces are subjected to superposition correction to obtain new spatial prediction data;
step five, planning a target network, and planning the target network according to the new spatial prediction data;
step six, determining an excessive net rack;
and step seven, making a power corridor plan.
10. The power distribution network meshing planning method according to claim 1, characterized in that: the data for predicting the electrical load includes calculating a periodic dynamic pricing electricity rate versus load shape function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911162135.7A CN110991718B (en) | 2019-11-25 | 2019-11-25 | Grid planning method for power distribution network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911162135.7A CN110991718B (en) | 2019-11-25 | 2019-11-25 | Grid planning method for power distribution network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110991718A true CN110991718A (en) | 2020-04-10 |
| CN110991718B CN110991718B (en) | 2023-10-17 |
Family
ID=70086248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911162135.7A Active CN110991718B (en) | 2019-11-25 | 2019-11-25 | Grid planning method for power distribution network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110991718B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111697570A (en) * | 2020-05-25 | 2020-09-22 | 国网河北省电力有限公司石家庄市藁城区供电分公司 | Power grid load prediction method |
| CN111738555A (en) * | 2020-07-08 | 2020-10-02 | 国网河北省电力有限公司石家庄市藁城区供电分公司 | Rural power grid planning method based on spot price |
| CN112734333A (en) * | 2020-12-31 | 2021-04-30 | 华润电力技术研究院有限公司 | Method, device and equipment for scheduling coal fuel inventory |
| CN116090795A (en) * | 2023-03-28 | 2023-05-09 | 佰聆数据股份有限公司 | DNN-based distribution network grid dynamic resource planning method and device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013123443A1 (en) * | 2012-02-16 | 2013-08-22 | Lazaris Spyros | System and method for managing the generation, transmission and distribution of power |
| US20140365022A1 (en) * | 2013-06-06 | 2014-12-11 | International Business Machines Corporation | Managing Time-Substitutable Electricity Usage using Dynamic Controls |
| WO2017052362A1 (en) * | 2015-09-22 | 2017-03-30 | Peeeks B.V. | System for balancing an electricity network with a grid |
| CN107038530A (en) * | 2017-04-13 | 2017-08-11 | 天津天大求实电力新技术股份有限公司 | A kind of power distribution network overall planning method and system |
| CN107067104A (en) * | 2017-03-30 | 2017-08-18 | 昆明能讯科技有限责任公司 | A kind of power supply grid load forecasting method based on GIS-Geographic Information System |
| CN107563571A (en) * | 2017-09-26 | 2018-01-09 | 国网安徽省电力公司合肥供电公司 | A kind of electric power facility is laid out automatic planning |
| CN108199367A (en) * | 2017-12-11 | 2018-06-22 | 上海交通大学 | One kind is based on medium voltage distribution network unit style grid power supply plan method |
| CN109559250A (en) * | 2018-12-10 | 2019-04-02 | 国网浙江省电力有限公司 | A kind of city power distribution net gridding planing method |
| US20190295190A1 (en) * | 2018-03-26 | 2019-09-26 | Oracle International Corporation | Electric loadshape forecasting for utility systems that support dynamic power pricing |
| CN110443402A (en) * | 2019-06-19 | 2019-11-12 | 国家电网有限公司 | A kind of urban distribution network gridding planing method adapting to high reliability power demands |
-
2019
- 2019-11-25 CN CN201911162135.7A patent/CN110991718B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013123443A1 (en) * | 2012-02-16 | 2013-08-22 | Lazaris Spyros | System and method for managing the generation, transmission and distribution of power |
| US20140365022A1 (en) * | 2013-06-06 | 2014-12-11 | International Business Machines Corporation | Managing Time-Substitutable Electricity Usage using Dynamic Controls |
| WO2017052362A1 (en) * | 2015-09-22 | 2017-03-30 | Peeeks B.V. | System for balancing an electricity network with a grid |
| CN107067104A (en) * | 2017-03-30 | 2017-08-18 | 昆明能讯科技有限责任公司 | A kind of power supply grid load forecasting method based on GIS-Geographic Information System |
| CN107038530A (en) * | 2017-04-13 | 2017-08-11 | 天津天大求实电力新技术股份有限公司 | A kind of power distribution network overall planning method and system |
| CN107563571A (en) * | 2017-09-26 | 2018-01-09 | 国网安徽省电力公司合肥供电公司 | A kind of electric power facility is laid out automatic planning |
| CN108199367A (en) * | 2017-12-11 | 2018-06-22 | 上海交通大学 | One kind is based on medium voltage distribution network unit style grid power supply plan method |
| US20190295190A1 (en) * | 2018-03-26 | 2019-09-26 | Oracle International Corporation | Electric loadshape forecasting for utility systems that support dynamic power pricing |
| CN109559250A (en) * | 2018-12-10 | 2019-04-02 | 国网浙江省电力有限公司 | A kind of city power distribution net gridding planing method |
| CN110443402A (en) * | 2019-06-19 | 2019-11-12 | 国家电网有限公司 | A kind of urban distribution network gridding planing method adapting to high reliability power demands |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111697570A (en) * | 2020-05-25 | 2020-09-22 | 国网河北省电力有限公司石家庄市藁城区供电分公司 | Power grid load prediction method |
| CN111738555A (en) * | 2020-07-08 | 2020-10-02 | 国网河北省电力有限公司石家庄市藁城区供电分公司 | Rural power grid planning method based on spot price |
| CN112734333A (en) * | 2020-12-31 | 2021-04-30 | 华润电力技术研究院有限公司 | Method, device and equipment for scheduling coal fuel inventory |
| CN116090795A (en) * | 2023-03-28 | 2023-05-09 | 佰聆数据股份有限公司 | DNN-based distribution network grid dynamic resource planning method and device |
| CN116090795B (en) * | 2023-03-28 | 2023-07-14 | 佰聆数据股份有限公司 | DNN-based distribution network grid dynamic resource planning method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110991718B (en) | 2023-10-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kumar et al. | Strategic integration of battery energy storage systems with the provision of distributed ancillary services in active distribution systems | |
| Hafiz et al. | Energy management and optimal storage sizing for a shared community: A multi-stage stochastic programming approach | |
| Qiu et al. | Distributed generation and energy storage system planning for a distribution system operator | |
| CN110991718B (en) | Grid planning method for power distribution network | |
| Gitizadeh et al. | Battery capacity determination with respect to optimized energy dispatch schedule in grid-connected photovoltaic (PV) systems | |
| Coignard et al. | Will electric vehicles drive distribution grid upgrades?: The case of California | |
| Vandael et al. | Decentralized coordination of plug-in hybrid vehicles for imbalance reduction in a smart grid. | |
| Short et al. | Regional energy deployment system (ReEDS) | |
| Yang et al. | Optimal energy flow control strategy for a residential energy local network combined with demand-side management and real-time pricing | |
| Ratnam et al. | Receding horizon optimization-based approaches to managing supply voltages and power flows in a distribution grid with battery storage co-located with solar PV | |
| La Scala et al. | From smart grids to smart cities: new challenges in optimizing energy grids | |
| Zhang et al. | Grid-connected photovoltaic battery systems: A comprehensive review and perspectives | |
| Panda et al. | A comprehensive review on demand side management and market design for renewable energy support and integration | |
| Varzaneh et al. | Optimal energy management for PV‐integrated residential systems including energy storage system | |
| Zhang et al. | Aggregating distributed energy storage: Cloud-based flexibility services from China | |
| Negri et al. | Combined model predictive control and ANN-based forecasters for jointly acting renewable self-consumers: An environmental and economical evaluation | |
| Rocha et al. | Net zero energy cost building system design based on artificial intelligence | |
| Fiorotti et al. | A novel strategy for simultaneous active/reactive power design and management using artificial intelligence techniques | |
| Villa et al. | Oversizing grid-connected microgrids as a business model—An optimisation assessment approach | |
| Jiang et al. | Monthly electricity purchase and decomposition optimization considering wind power accommodation and day-ahead schedule | |
| Massaro et al. | An Algorithm for Optimal Sizing of BESS in Smart Islands Energy Communities: the Case of Pantelleria | |
| Taylor et al. | Energy storage integration | |
| Roy et al. | Performance enhancement of smart grid with demand side management program contemplating the effect of uncertainty of renewable energy sources | |
| CN117273795B (en) | Industrial and commercial energy storage capacity configuration and profit measurement method and system | |
| Govaerts | Distribution Grid Tariff Design-Analysis of the Economic Efficiency of Tariff Structures and Forward-Looking Cost Models |
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 |