CN116255665A - Heat supply combined control method and system based on load prediction of heat supply network system - Google Patents
Heat supply combined control method and system based on load prediction of heat supply network system Download PDFInfo
- Publication number
- CN116255665A CN116255665A CN202310211587.XA CN202310211587A CN116255665A CN 116255665 A CN116255665 A CN 116255665A CN 202310211587 A CN202310211587 A CN 202310211587A CN 116255665 A CN116255665 A CN 116255665A
- Authority
- CN
- China
- Prior art keywords
- heat supply
- load
- information
- area
- network system
- 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
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24D—DOMESTIC- OR SPACE-HEATING SYSTEMS, e.g. CENTRAL HEATING SYSTEMS; DOMESTIC HOT-WATER SUPPLY SYSTEMS; ELEMENTS OR COMPONENTS THEREFOR
- F24D19/00—Details
- F24D19/10—Arrangement or mounting of control or safety devices
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention provides a heat supply combined control method and a system based on heat supply network system load prediction, which belong to the technical field of data processing and comprise the following steps: grid division is carried out on the heat supply coverage area of the target heat supply network system according to the heat supply branches, so that a plurality of heat supply areas are obtained; grading is carried out according to the heat supply demand attribute proportion condition, and a primary heat supply area and a secondary heat supply area are obtained; acquiring primary demand load information; acquiring a historical load information set of a secondary heat supply area; carrying out data analysis on the plurality of historical region load information sets to generate a plurality of target feature sets; acquiring a real-time characteristic value of a secondary heat supply area; inputting a load prediction model to obtain a plurality of secondary prediction load demands; and carrying out heat supply combined control on the target heat supply network system. The invention solves the problems of long joint control period and low intelligent degree when the heat supply is insufficient in the prior art, and achieves the technical effect of efficiently carrying out differential heat supply in the process of ensuring heat supply by joint control on the heat supply unit.
Description
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to a heat supply combined control method and system based on heat supply network system load prediction.
Background
With the rapid development of economy and technology, a heat supply network system becomes an indispensable part of life of people, and the heat supply through the heat supply network system provides great convenience for work and life of people and plays an important role in promoting social development.
At present, the demand of heat supply quantity rises year by year, the existing heat supply network system heat supply control mode has low regulation and control efficiency on the heat supply mode of the heat supply end, and the heat supply control mode cannot be timely and rapidly regulated on a plurality of parameters needing regulation and control, and the demand of the heat supply end cannot be timely regulated and satisfied, so that the heat supply quality is poor. Meanwhile, in the process of adjusting the operation parameters of the unit to ensure heat supply, a unified load reduction mode is carried out, so that the requirement for full-load operation cannot be met, and the result of delay of the production period is caused.
In the prior art, the technical problems of long joint control period and low intelligent degree exist when the heat supply is insufficient.
Disclosure of Invention
The invention provides a heat supply combined control method and a heat supply combined control system based on heat supply network system load prediction, and aims to solve the technical problems of long combined control period and low intelligent degree in the prior art when heat supply is insufficient.
The embodiment of the invention provides a heat supply combined control method based on load prediction of a heat supply network system, wherein the method is applied to an intelligent combined control system, the intelligent combined control system is in communication connection with a data calling module, and the method comprises the following steps: grid division is carried out on the heat supply coverage area of the target heat supply network system according to the heat supply branches, so that a plurality of heat supply areas are obtained;
acquiring the heat supply demand attribute proportion conditions of the plurality of heat supply areas, and grading according to the heat supply demand attribute proportion conditions to acquire a primary heat supply area and a secondary heat supply area;
acquiring primary demand load information of the primary heating area, wherein the primary heating area is a supply protection area, namely an area which needs to be met by the demand load;
acquiring a plurality of historical load information sets of a secondary heating area through the data calling module, and performing feature analysis on the historical load information sets to generate a plurality of target feature sets;
acquiring real-time characteristic values of the secondary heating area according to the target characteristic sets to obtain a plurality of real-time secondary load characteristic value sets;
traversing the real-time secondary load characteristic value sets to input the load prediction model to obtain a plurality of secondary prediction load demands;
And carrying out heat supply combined control on the target heat supply network system according to the primary demand load information and the plurality of secondary predicted load demands.
By adopting the technical scheme, the intelligent control of heat supply based on the load prediction condition of the heat supply network system is achieved, and the technical effect of heat supply requirement is ensured by carrying out differential demand analysis on a heat supply area.
Further, analyzing the fluctuation conditions of the plurality of historical load information sets to obtain a plurality of historical fluctuation information, wherein the plurality of historical fluctuation information comprises a plurality of historical fluctuation amplitudes and a plurality of historical fluctuation association features;
constructing a fluctuation grade evaluation value set;
calculating characteristic association coefficients according to the fluctuation level evaluation value set and the plurality of historical fluctuation amplitudes to obtain a plurality of characteristic association coefficient values;
and screening the associated features of the secondary heating areas according to the feature associated coefficient values, so as to generate the target feature sets.
By adopting the technical scheme, the required load amounts of the primary heat supply area and the secondary heat supply area are separated, the load prediction can be timely adjusted when emergency heat supply protection is met, and the technical effect of finer regulation and control is realized when heat supply is combined.
Further, an emergency supply protection instruction is obtained, and a heating area screening module is called according to the emergency supply protection instruction;
inputting the plurality of secondary predicted load demands into the heating area screening module for load compression to obtain a plurality of secondary predicted compression load demands;
and carrying out heat supply combined control on the target heat supply network system according to the first-level demand load information and the plurality of second-level predicted compression load demands.
By adopting the technical scheme, the load of the secondary heating area can be directly compressed when emergency supply is carried out, so that the efficiency of heating load adjustment control is improved.
Further, calculating the total predicted load demand of the target heat supply network system according to the first-level demand load information and the plurality of second-level predicted load demands to obtain total predicted load information;
acquiring real-time heat source supply conditions of a target heat supply network system, and acquiring preset heat supply mode information, wherein the preset heat supply mode information comprises a heat supply unit operation mode and heat supply unit operation parameters;
and constraining the preset heat supply mode information by using the total predicted load information, judging whether the preset heat supply mode information can meet the requirement, if so, carrying out heat supply according to the preset heat supply mode information, and if not, taking the preset heat supply mode as the heat supply mode information to be optimized.
By adopting the technical scheme, the heat supply control is performed for the heat supply network supply in the area.
Further, a plurality of random adjustment modes are adopted to adjust the heat supply mode information to be optimized, a first neighborhood of the heat supply mode information to be optimized is constructed, the first neighborhood comprises a plurality of first adjustment heat supply modes, and the plurality of random adjustment modes are used for adjusting the operation modes of the heat supply unit and the operation parameters of the heat supply unit;
acquiring the fitness of the plurality of first adjustment heating modes, and acquiring the fitness of the plurality of first adjustment heating modes;
and obtaining the maximum value of the first adjustment fitness as the first fitness, and taking the corresponding first adjustment heat supply mode as first heat supply mode information.
By adopting the technical scheme, the heat supply mode corresponding to the maximum adaptation degree is used as the optimized heat supply mode information, and the heat supply mode is screened and optimized.
Further, adding a random adjustment mode for adjusting and obtaining the first heat supply mode information into a tabu space, wherein the tabu space comprises a tabu iteration number;
continuing to construct a second neighborhood of the first heat supply mode information, performing iterative optimization, and deleting a random adjustment mode for adjusting and obtaining the first heat supply mode information from the tabu space when the iteration number reaches the tabu iteration number;
Stopping optimizing when the iterative optimization reaches the preset iterative times, and obtaining optimized heat supply mode information by the heat supply mode information corresponding to the maximum adaptability value in the iterative optimization process;
and carrying out heat supply combined control according to the optimized heat supply mode information.
By adopting the technical scheme, the aim of determining the optimal heating mode and improving the heating combined control accuracy can be fulfilled.
Further, calculating the real-time maximum loads of the first adjustment heating modes to obtain a plurality of pieces of real-time maximum load information, wherein the real-time maximum load information corresponds to the first adjustment heating modes one by one;
obtaining a plurality of heating costs according to the real-time heating material consumption and the real-time heating material price of the plurality of first adjustment heating modes;
and weighting and calculating the plurality of real-time maximum load information and the plurality of heating costs according to the preset weight ratio to obtain the plurality of first adjustment fitness.
By adopting the technical scheme, the calculation mode of the adjustment fitness is determined, quantization analysis is performed, and accuracy is improved.
The beneficial effects of the invention are as follows:
according to the invention, the load of the heat supply network system is predicted, and the heat supply is controlled in a combined mode according to the predicted result, so that the heat supply control is respectively carried out from the heat supply end and the heat receiving end, the heat supply efficiency is improved, and the heat supply control quality is improved. The technical effect of improving the heating regulation flexibility of the heat supply network system is achieved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic flow diagram of a heat supply combined control method based on heat supply network system load prediction according to an embodiment of the invention;
FIG. 2 is a schematic flow chart of generating multiple target feature sets in a heat supply combined control method based on heat supply network system load prediction according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of obtaining first heat supply mode information in a heat supply combined control method based on heat supply network system load prediction according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a heat supply combined control system based on load prediction of a heat supply network system according to an embodiment of the present invention;
reference numerals: the system comprises a heating area obtaining module 11, a grading module 12, a target feature set primary demand load obtaining module 13, a historical load information obtaining module 14, a real-time target feature value obtaining module 15, a predicted load demand obtaining module 16 and a heating combined control module 17.
Detailed Description
In order to make the objects, technical solutions and advantages of the technical solutions of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of specific embodiments of the present invention. Like reference numerals in the drawings denote like parts. It should be noted that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be made by a person skilled in the art without creative efforts, based on the described embodiments of the present invention fall within the protection scope of the present invention.
Referring to fig. 1, an embodiment of the present invention provides a heat supply combined control method based on load prediction of a heat supply network system, where the method is applied to an intelligent combined control system, and the intelligent combined control system is communicatively connected with a data calling module, and the method includes:
step S100: grid division is carried out on the heat supply coverage area of the target heat supply network system according to the heat supply branches, so that a plurality of heat supply areas are obtained;
specifically, the target heat supply network system is any heat supply network system for load prediction and regional heat supply combined control. The heat supply network is a main component of the central heating system and is responsible for heat energy transmission tasks, and the form of the heat supply network system depends on various factors including heat medium, mutual positions of heat sources and heat users, heat user types in heat supply areas, heat load sizes and properties and the like. The heat supply branch is used as a main pipeline for heat supply in the coverage area of the target heat supply network system, the coverage area is divided into a plurality of grids according to the distribution position of the main heat supply pipeline in the area, and each grid is used as a heat supply area, so that the plurality of heat supply areas are obtained. The plurality of heat supply areas refer to dividing units for supplying heat to the target heat supply network system.
Step S200: acquiring the heat supply demand attribute proportion conditions of the plurality of heat supply areas, and grading according to the heat supply demand attribute proportion conditions to acquire a primary heat supply area and a secondary heat supply area;
specifically, the extraction of the heat supply demand attribute duty ratio of the plurality of heat supply areas is to analyze the duty ratio of the unit attribute requiring heat supply in each heat supply area in the area, wherein the heat supply demand attribute is an attribute describing the usage of the acquired heat, including business attribute, industrial attribute, resident attribute, and the like. The primary heating area is the area where the supply of heat is required, i.e. because of the importance of this area, the supply of heat must be ensured in the case of heat supply. The secondary heating area is an area where load compression, i.e. reduction of heat supply, can be performed when the heat load supply is short.
Specifically, by weighting the heat demand attributes, it is preferable that the resident attributes have a larger duty cycle than the industry attributes, which is larger than the business attributes. And setting a weight distribution result by a worker according to the development condition of the actual area. And carrying out weighted calculation on the attribute proportion condition of each heating area according to the weight distribution result, thereby obtaining a calculation result. And sequencing from large to small according to the calculation result, thereby obtaining a primary heat supply area and a secondary heat supply area.
Step S300: acquiring primary demand load information of the primary heating area, wherein the primary heating area is a supply protection area, namely an area which needs to be met by the demand load;
specifically, according to the distribution conditions of businesses, industries and residents in the primary heat supply area, heat supply demand collection is carried out, and primary demand load information is obtained. Wherein the primary demand load information includes a total load amount and a load demand urgency.
Step S400: acquiring a plurality of historical load information sets of a secondary heating area through the data calling module, and performing feature analysis on the historical load information sets to generate a plurality of target feature sets;
further, referring to fig. 2, step S400 in the embodiment of the present application further includes:
step S410: analyzing the fluctuation conditions of the plurality of historical load information sets to obtain a plurality of historical fluctuation information, wherein the plurality of historical fluctuation information comprises a plurality of historical fluctuation amplitudes and a plurality of historical fluctuation association features;
step S420: constructing a fluctuation grade evaluation value set;
step S430: calculating characteristic association coefficients according to the fluctuation level evaluation value set and the plurality of historical fluctuation amplitudes to obtain a plurality of characteristic association coefficient values;
Step S440: and screening the associated features of the plurality of heating areas according to the plurality of feature associated coefficient values, so as to generate the plurality of target feature sets.
Specifically, the data retrieval module is a functional module for extracting data from a load supply database of the target heat supply network system. And extracting the historical load information of the secondary heat supply area through the data calling module to obtain a plurality of historical load information sets. Wherein the plurality of historical load information sets are information describing load conditions received by the plurality of heating areas in the historical time period, and include daily supply load amount, weekly supply load amount, monthly supply load amount, load fluctuation condition and the like. By calling the historical load information of the plurality of heat supply areas, the basis is provided for the subsequent analysis and prediction of the real-time load condition of the secondary heat supply area. Furthermore, the coverage area is divided into a plurality of small units, namely a plurality of heat supply areas, so that the load change condition in the analysis area is more accurate, the required load amounts of the primary heat supply area and the secondary heat supply area are separated, the load prediction can be timely adjusted when the emergency heat supply protection condition is met, and therefore finer regulation and control are carried out when heat supply combined control is carried out, and the heat supply adjustment efficiency and quality are improved.
Specifically, the plurality of target feature sets are main features of analyzing that the historical load information sets are affected respectively, including periodic features, quarter features, environmental features and the like, wherein the periodic features refer to features of periodically changing the heat supply load based on regional distribution differences, such as heat supply load fluctuation of daily periodicity, quaternary periodicity and the like; the quarter feature refers to a feature that the heat load demand fluctuates due to the difference of the quarters, such as the heat load is reduced in summer and the heat load is increased in winter; the environmental characteristics refer to characteristics of load fluctuation caused by environmental factors such as weather change, for example, when the temperature is suddenly lowered, the demand for heating is increased.
Specifically, the plurality of historical fluctuation information is obtained by counting load fluctuation situations, which exceed a preset fluctuation threshold value, in a plurality of historical load information sets. The preset fluctuation threshold is set by a worker and is a normal fluctuation range of the load. The plurality of historical fluctuation magnitudes are magnitudes of deviations of load fluctuation from the preset fluctuation threshold. The plurality of historical fluctuation association features are influence features for causing a plurality of historical fluctuation, including periodic features, quarter features, environmental features and the like. The fluctuation grade evaluation value set refers to grading of fluctuation degrees, corresponding evaluation values are set, and each grade corresponds to one evaluation value. Preferably, the fluctuation level is divided into three levels, the range of the deviation value of the level is 0-30, and the corresponding evaluation value is 9; the size range of the second-level deviation value is 30-45, and the corresponding evaluation value is 6; the magnitude of the three-level deviation value ranges from 45 to 55, and the corresponding evaluation value is 3. And multiplying the fluctuation grade evaluation value set and the plurality of historical fluctuation amplitudes to obtain a plurality of characteristic association coefficient values reflecting the association degree of a plurality of historical fluctuation association characteristics and load fluctuation. Because each heating area corresponds to one historical area load information set, the most relevant characteristics of the load fluctuation of each heating area are obtained by screening a plurality of characteristic association coefficient values, and preferably, the characteristics arranged in the front three are selected as the target characteristic sets by sorting the characteristic association coefficient values from large to small.
Step S500: acquiring real-time characteristic values of the secondary heating area according to the target characteristic sets to obtain a plurality of real-time secondary load characteristic value sets;
step S600: traversing the real-time secondary load characteristic value sets to input the load prediction model to obtain a plurality of secondary prediction load demands;
specifically, the features in the plurality of target feature sets are used as data extraction indexes, and real-time feature values in the secondary heat supply area are collected to obtain the plurality of real-time secondary load feature value sets. The real-time secondary load characteristic value sets reflect the most relevant characteristic values corresponding to the secondary heat supply areas, can further reflect the load change condition of the heat supply areas, and provide basis for predicting the real-time load demands in each heat supply area. The load prediction model is a functional model for intelligently predicting the heat supply load demand, input data are a plurality of real-time secondary load characteristic value sets, and output data are a plurality of predicted load demands. The plurality of predicted load demands are predicted from the heating load demand in the secondary heating area, including the load demand. And traversing the real-time secondary load characteristic value sets to input the load prediction model, obtaining a plurality of secondary prediction load demands, and intelligently predicting the load demand conditions of each heating area. And the load demand condition of each heating area is predicted independently, and prediction errors are reduced through subdivision, so that the prediction accuracy is improved.
Specifically, the load prediction model with the convolutional neural network as a network structure is trained by taking a plurality of secondary load characteristic value sets and a plurality of historical load information sets as construction data. And taking the secondary load characteristic value sets and the historical load information sets as sample data sets, and dividing the sample data sets into training sets and verification sets according to a certain proportion, wherein the dividing proportion can be 2:1. And training the load prediction model by using the training set until the training is converged, inputting a plurality of secondary load characteristic value sets in the verification set into the converged load prediction model to obtain a plurality of verification historical load information, matching the plurality of verification historical load information with the plurality of historical load information sets, comparing the number of successfully matched historical load information sets with the number of the plurality of historical load information sets to obtain verification accuracy, outputting the load prediction model when the verification accuracy meets the requirements, and acquiring more construction data to perform incremental learning on the load prediction model when the verification accuracy does not meet the requirements until the verification accuracy meets the requirements.
Step S700: and carrying out heat supply combined control on the target heat supply network system according to the primary demand load information and the plurality of secondary predicted load demands.
Further, step S600 in the embodiment of the present application further includes:
step S710: calculating the total predicted load demand of the target heat supply network system according to the primary demand load information and the plurality of secondary predicted load demands to obtain total predicted load information;
step S720: acquiring real-time heat source supply conditions of a target heat supply network system, and acquiring preset heat supply mode information, wherein the preset heat supply mode information comprises a heat supply unit operation mode and heat supply unit operation parameters;
step S730: and constraining the preset heat supply mode information by using the total predicted load information, judging whether the preset heat supply mode information can meet the requirement, if so, carrying out heat supply according to the preset heat supply mode information, and if not, taking the preset heat supply mode as the heat supply mode information to be optimized.
Specifically, the total predicted load information is obtained by adding the first-level demand load information and the plurality of second-level predicted load demands, and the load condition, including the total predicted load amount, required to be supplied by the target heat supply network system is reflected. The preset heat supply mode information is a heat source condition adopted when the target heat supply network system carries out load supply in real time, and comprises a heat supply unit operation mode and heat supply unit operation parameters. The heat supply unit operation mode is to describe the composition of the heat supply unit and the operation mode of each heat supply unit. And the operation parameters of the heat supply unit are obtained by summarizing the parameters of each device in the operation of the heat supply unit.
Specifically, the total predicted load information is used for restraining the preset heat supply mode information, namely, the total predicted load information is used as the requirement that the target heat supply network system must meet, the preset heat supply mode information is judged, and whether the current heat supply mode can meet the load requirement of the area is judged. If yes, heating is carried out according to the preset heating mode information, and if not, the preset heating mode is used as the heating mode information to be optimized. Thus, the supply of heat to the heat supply network in the area is controlled.
Further, referring to fig. 3, step S730 in the embodiment of the present application further includes:
step S731: adjusting the heat supply mode information to be optimized by adopting a plurality of random adjustment modes, and constructing a first neighborhood of the heat supply mode information to be optimized, wherein the first neighborhood comprises a plurality of first heat supply adjustment modes, and the plurality of random adjustment modes are used for adjusting the operation modes of the heat supply unit and the operation parameters of the heat supply unit;
step S732: acquiring the fitness of the plurality of first adjustment heating modes, and acquiring the fitness of the plurality of first adjustment heating modes;
step S733: and obtaining the maximum value of the first adjustment fitness as the first fitness, and taking the corresponding first adjustment heat supply mode as first heat supply mode information.
Further, step S730 in the embodiment of the present application further includes:
step S734: adding a random adjustment mode for adjusting and obtaining the first heat supply mode information into a tabu space, wherein the tabu space comprises a tabu iteration number;
step S735: continuing to construct a second neighborhood of the first heat supply mode information, performing iterative optimization, and deleting a random adjustment mode for adjusting and obtaining the first heat supply mode information from the tabu space when the iteration number reaches the tabu iteration number;
step S736: stopping optimizing when the iterative optimization reaches the preset iterative times, and obtaining optimized heat supply mode information by the heat supply mode information corresponding to the maximum adaptability value in the iterative optimization process;
step S737: and carrying out heat supply combined control according to the optimized heat supply mode information.
Specifically, the heating mode information to be optimized is adjusted according to a plurality of random adjustment modes. Optionally, according to different adjustment amplitudes, the operation mode of the heating unit and the operation parameters of the heating unit are adjusted to adjust the information of the heating mode to be optimized. And taking the heat supply mode information to be optimized as a reference, and obtaining a first heat supply mode after random adjustment, wherein the first heat supply mode is used as the first neighborhood. The first neighborhood is an adjusting range of the heat supply mode information to be optimized, and the adjusting range comprises a first heat supply adjustment mode. And further, evaluating the plurality of first adjustment heat supply modes to obtain an evaluation result of the first adjustment heat supply mode on the heat supply quality of the regional load, and obtaining the adaptability according to the heat supply quality. Therefore, the plurality of first adjustment fitness is obtained by evaluating the fitness of the plurality of first adjustment heating modes one by one. And carrying out fitness screening from the plurality of first adjustment fitness degrees to obtain the fitness degree with the largest numerical value, and taking the fitness degree as the first fitness degree, so that the quality of heat supply can be optimized from the whole angle by indicating that heat supply is carried out according to the first adjustment heat supply mode corresponding to the first fitness degree. The first heating mode is a heating mode in which the most suitable target heat supply network system supplies heat in the first neighborhood.
Specifically, a random adjustment mode corresponding to the first heat supply mode is added into a tabu space which is not allowed to be selected, so that repeated selection of the adjustment mode is avoided, and the obtained result is not diversified. The tabu iteration times are the iteration times which are forbidden to be used by the adjustment mode, and when the iteration times exceed a certain number, the influence of the adjustment mode on the adjustment result is reduced. The number of tabu iterations is set by the staff and is not limited here.
Specifically, the second neighborhood is an adjustment space corresponding to the first heat supply mode, iteration optimization is performed on the first heat supply mode in the second neighborhood, and after the iteration times reach the tabu iteration times, the random adjustment mode of the first heat supply mode is deleted from the tabu space, so that the effectiveness and reliability of iteration are ensured. Iteration cannot be performed all the time, an iteration result of overfitting is avoided, and when iteration optimization reaches the preset iteration times, the heat supply mode corresponding to the maximum adaptation value is used as the optimized heat supply mode information, so that the aim of determining the optimal heat supply mode can be fulfilled.
Further, the step S732 of obtaining the fitness of the plurality of first adjustment heating modes and obtaining the plurality of first adjustment fitness further includes:
Step S7321: calculating the real-time maximum load of the first adjustment heating modes to obtain a plurality of pieces of real-time maximum load information, wherein the real-time maximum load information corresponds to the first adjustment heating modes one by one;
step S7322: obtaining a plurality of heating costs according to the real-time heating material consumption and the real-time heating material price of the plurality of first adjustment heating modes;
step S7323: and weighting and calculating the plurality of real-time maximum load information and the plurality of heating costs according to the preset weight ratio to obtain the plurality of first adjustment fitness.
Specifically, the real-time maximum load which can be achieved by the plurality of first adjustment heat supply modes is calculated, and the load quantity when the machine is in full-load operation is used as the plurality of real-time maximum load information according to the machine set operation modes and the machine set operation parameters corresponding to the plurality of first adjustment heat supply modes. The real-time heating material consumption is the heating material consumption in unit time when the heating unit is operated. The real-time heating material price is the price of the material when heating. The plurality of heating costs are costs consumed by the target heat supply network system when heating according to the plurality of first regulated heating modes. The preset weight ratio is the ratio of the preset load supply condition and the preset cost when the heating mode evaluation is carried out. And carrying out weighted calculation on the plurality of real-time maximum load information and the plurality of heating costs according to the preset weight ratio, and obtaining the plurality of first adjustment fitness according to a calculation result.
Further, step S700 in the embodiment of the present application further includes:
step S740: acquiring an emergency supply protection instruction, and calling a heating area screening module according to the emergency supply protection instruction;
step S750: inputting the plurality of secondary predicted load demands into the heating area screening module for load compression to obtain a plurality of secondary predicted compression load demands;
step S760: and carrying out heat supply combined control on the target heat supply network system according to the first-level demand load information and the plurality of second-level predicted compression load demands.
Specifically, the emergency supply-keeping instruction is an instruction issued under the condition that the heat supply resource is short, to ensure the heat supply of the supply-keeping area, and to compress and cut the heat supply of the non-supply-keeping area. The heat supply area screening module is a functional module for analyzing the plurality of secondary predicted load demands according to heat supply demand attributes in the secondary heat supply area so as to reduce loads. And compressing the plurality of secondary predicted load demands according to the heating area screening module to obtain the plurality of secondary predicted compression load demands. When emergency supply is carried out, the load of the secondary heat supply area can be directly compressed, so that the efficiency of heat supply load adjustment control is improved.
Further, step S760 in the embodiment of the present application further includes:
step S761: determining a plurality of load demands to be supported according to the plurality of second-level predicted load demands and the plurality of second-level predicted compression load demands;
step S762: collecting distributed heat supply source configuration information of the secondary heat supply area for heat supply analysis, wherein the distributed heat supply source configuration information comprises a heat supply source type and a heat supply source specification;
step S763: traversing the plurality of load demands to be supported based on the heat supply analysis result to calculate missing data, judging whether the calculation result is larger than a preset threshold value, and if so, carrying out forward marking on the heat supply analysis result;
step S764: judging whether the calculated result is smaller than a preset threshold value, and if so, carrying out negative marking on the heating capacity analysis result;
step S765: and (3) carrying out distributed heat supply source scheduling by using a K-clustering method and combining positive marks and negative marks.
Specifically, the plurality of load requirements to be supported are obtained by calculating the difference between the plurality of secondary predicted load requirements and the plurality of secondary predicted compression load requirements, that is, when the heat load of the secondary heat supply area is required to reach the full load requirement, the heat supply requirement is also required to be provided. By calculating the plurality of load demands to be supported, the compressed load quantity of the secondary heat supply area when the heat supply of the heat supply network system is insufficient can be determined, and meanwhile, a basis is provided for subsequent distributed heat supply source allocation.
Specifically, the heat supply source type is obtained by collecting the configuration condition of the distributed heat supply source in the secondary heat supply area, for example: heat pumps, photovoltaic panels, etc., and heat source specifications such as rated heating capacity, hot water flow, rated outlet water temperature, maximum outlet water temperature, etc. The heat supply quantity condition, namely the supplementary heat load, of the secondary heat supply area can be supplemented by acquiring the heat supply source type and the heat supply source specification. And then, matching the heat supply analysis result of the secondary heat supply area with a plurality of load demands to be supported in a one-to-one correspondence manner, namely subtracting the load demands to be supported from the heat supply analysis result, so as to obtain whether the demands can be met when the distributed heat supply source in the secondary heat supply area is used for heat supply supplement, and whether the demands are exceeded or not, and the outward support can be carried out.
Specifically, the preset threshold is a load range, in which the calculation result of missing data is in a normal fluctuation state, and when the calculation result is greater than the preset threshold, it is indicated that the heat supply quantity of the distributed heat supply source in the area can provide support for other areas at this time, and forward marking is performed on the other areas. When the calculation result is smaller than the preset threshold value, the fact that the heat supply quantity of the distributed heat supply source in the area cannot meet the compressed load demand is indicated, and other areas are required to provide distributed heat supply source support, so that negative marking is carried out on the distributed heat supply source support.
Specifically, by using a K-clustering method and combining the positive mark and the negative mark, matching and clustering the areas with similar supporting quantity and demand quantity, and performing directional distributed heat supply source scheduling according to the matching and clustering result, thereby meeting the heat supply requirement of the secondary heat supply area. Preferably, the K value is set to be 1, one mark is randomly selected from the positive marks, so that the positive marks are used as central data, the negative marks are clustered, the absolute value difference value of the positive mark data is used as a clustering scale, the negative mark closest to the positive mark is determined, the negative mark heat supply analysis result which is most matched with the heat supply analysis result corresponding to the positive mark is obtained, and therefore distributed heat supply source scheduling is performed. Through directional scheduling, the operability of scheduling and the accuracy of operation are improved, and the efficiency of heat supply combined control is improved.
Referring to fig. 4, the present application provides a heat supply combined control system based on load prediction of a heat supply network system, and the system and method embodiments in the embodiments of the present application are based on the same inventive concept. Wherein the system comprises:
the heat supply area obtaining module 11 is used for dividing a heat supply coverage area of the target heat supply network system into grids according to heat supply branches to obtain a plurality of heat supply areas;
The grading module 12 is configured to obtain heat supply demand attribute proportion conditions of the plurality of heat supply areas, and grade according to the heat supply demand attribute proportion conditions, so as to obtain a primary heat supply area and a secondary heat supply area;
a primary demand load obtaining module 13, where the primary demand load obtaining module 13 is configured to obtain primary demand load information of the primary heating area, where the primary heating area is a supply-protecting area, that is, an area where the demand load must be satisfied;
the historical load information obtaining module 14 is configured to obtain a plurality of historical load information sets of the secondary heating area through the data calling module, perform feature analysis on the plurality of historical load information sets, and generate a plurality of target feature sets;
the real-time target characteristic value obtaining module 15, wherein the real-time target characteristic value obtaining module 15 is configured to obtain real-time characteristic values of the secondary heating area according to the multiple target characteristic sets, so as to obtain multiple real-time secondary load characteristic value sets;
the load demand obtaining module 16 is configured to traverse the plurality of real-time secondary load feature value sets and input the plurality of real-time secondary load feature value sets into a load prediction model, thereby obtaining a plurality of secondary predicted load demands;
And the heat supply combined control module 17 is used for performing heat supply combined control on the target heat supply network system according to the primary demand load information and the plurality of secondary predicted load demands.
Further, the system further comprises:
a history fluctuation information obtaining unit, configured to analyze fluctuation conditions of the plurality of history load information sets to obtain a plurality of history fluctuation information, where the plurality of history fluctuation information includes a plurality of history fluctuation amplitudes and a plurality of history fluctuation association features;
an evaluation value set construction unit for constructing a fluctuation-level evaluation value set;
the association coefficient value obtaining unit is used for carrying out characteristic association coefficient calculation according to the fluctuation grade evaluation value set and the plurality of historical fluctuation amplitudes to obtain a plurality of characteristic association coefficient values;
and the association characteristic screening unit is used for screening the association characteristics of the secondary heat supply areas according to the plurality of characteristic association coefficient values so as to generate the plurality of target characteristic sets.
Further, the system further comprises:
The system comprises a supply protection instruction acquisition unit, a heat supply area screening module and a heat supply area control unit, wherein the supply protection instruction acquisition unit is used for acquiring an emergency supply protection instruction and calling the heat supply area screening module according to the emergency supply protection instruction;
the load compression unit is used for inputting the plurality of secondary predicted load demands into the heating area screening module for load compression, so as to obtain a plurality of secondary predicted compression load demands;
and the heat supply network heat supply combined control unit is used for performing heat supply combined control on the target heat supply network system according to the primary demand load information and the plurality of secondary predicted compression load demands.
Further, the system further comprises:
the total predicted load information obtaining unit is used for calculating the total predicted load requirement of the target heat supply network system according to the primary demand load information and the plurality of secondary predicted load requirements to obtain total predicted load information;
the system comprises a preset heat supply mode information obtaining unit, a target heat supply network system and a target heat supply network system, wherein the preset heat supply mode information obtaining unit is used for obtaining real-time heat source supply conditions of the target heat supply network system and obtaining preset heat supply mode information, and the preset heat supply mode information comprises a heat supply unit operation mode and heat supply unit operation parameters;
And the mode information constraint unit is used for constraining preset heat supply mode information by utilizing the total predicted load information, judging whether the preset heat supply mode information can meet the requirement, if so, heating according to the preset heat supply mode information, and if not, taking the preset heat supply mode as heat supply mode information to be optimized.
Further, the system further comprises:
the first neighborhood construction unit is used for adjusting the heat supply mode information to be optimized by adopting a plurality of random adjustment modes, and constructing a first neighborhood of the heat supply mode information to be optimized, wherein the first neighborhood comprises a plurality of first adjustment heat supply modes, and the plurality of random adjustment modes are used for adjusting the operation modes of the heat supply unit and the operation parameters of the heat supply unit;
a first adjustment fitness obtaining unit, configured to obtain fitness of the plurality of first adjustment heating modes, and obtain a plurality of first adjustment fitness;
and a first heating mode information setting unit for obtaining a maximum value among the plurality of first adjustment fitness as a first fitness and regarding a corresponding first adjustment heating mode as first heating mode information.
Further, the system further comprises:
the tabu space adding unit is used for adding a random adjustment mode for adjusting and obtaining the first heat supply mode information into a tabu space, and the tabu space comprises a tabu iteration number;
the iterative optimization unit is used for continuously constructing a second neighborhood of the first heat supply mode information, performing iterative optimization, and deleting a random adjustment mode for adjusting and obtaining the first heat supply mode information from the tabu space when the iteration number reaches the tabu iteration number;
the optimized heat supply mode information obtaining unit is used for stopping optimizing after the iterative optimizing reaches the preset iterative times, and obtaining optimized heat supply mode information by the heat supply mode information corresponding to the maximum adaptation value in the iterative optimizing process;
and the optimized heat supply combined control unit is used for performing heat supply combined control according to the optimized heat supply mode information.
Further, the system further comprises:
the real-time maximum load information obtaining unit is used for calculating the real-time maximum loads of the first adjustment heating modes to obtain a plurality of pieces of real-time maximum load information, wherein the real-time maximum load information corresponds to the first adjustment heating modes one by one;
The heat supply cost obtaining unit is used for obtaining a plurality of heat supply costs according to the real-time heat supply material consumption and the real-time heat supply material prices of the plurality of first adjustment heat supply modes;
the first adjustment fitness obtaining units are used for carrying out weighted calculation on the real-time maximum load information and the heat supply cost according to the preset weight occupation ratio to obtain the first adjustment fitness;
further, the system further comprises:
the load demand to be supported determining unit is used for determining a plurality of load demands to be supported according to the plurality of secondary predicted load demands and the plurality of secondary predicted compression load demands;
the heat supply analysis unit is used for collecting distributed heat supply source configuration information of the secondary heat supply area to perform heat supply analysis, wherein the distributed heat supply source configuration information comprises a heat supply source type and a heat supply source specification;
the calculation result judging unit is used for carrying out missing data calculation by traversing the plurality of load demands to be supported based on the heat supply analysis result, judging whether the calculation result is larger than a preset threshold value, and if so, carrying out forward marking on the heat supply analysis result;
The negative marking unit is used for judging whether the calculated result is smaller than a preset threshold value, and if so, carrying out negative marking on the heating capacity analysis result;
and the heat supply source scheduling unit is used for performing distributed heat supply source scheduling by combining positive marks and negative marks by using a K-clustering method.
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. The heat supply combined control method based on the load prediction of the heat supply network system is characterized by being applied to an intelligent combined control system, wherein the intelligent combined control system is in communication connection with a data calling module, and the method comprises the following steps of:
grid division is carried out on the heat supply coverage area of the target heat supply network system according to the heat supply branches, so that a plurality of heat supply areas are obtained;
Acquiring the heat supply demand attribute proportion conditions of the plurality of heat supply areas, and grading according to the heat supply demand attribute proportion conditions to acquire a primary heat supply area and a secondary heat supply area;
acquiring primary demand load information of the primary heating area, wherein the primary heating area is a supply protection area, namely an area which needs to be met by the demand load;
acquiring a plurality of historical load information sets of a secondary heating area through the data calling module, and performing feature analysis on the historical load information sets to generate a plurality of target feature sets;
acquiring real-time characteristic values of the secondary heating area according to the target characteristic sets to obtain a plurality of real-time secondary load characteristic value sets;
traversing the real-time secondary load characteristic value sets to input the load prediction model to obtain a plurality of secondary prediction load demands;
and carrying out heat supply combined control on the target heat supply network system according to the primary demand load information and the plurality of secondary predicted load demands.
2. A combined heat and power control method based on load prediction of a heat supply network system as claimed in claim 1, comprising:
analyzing the fluctuation conditions of the plurality of historical load information sets to obtain a plurality of historical fluctuation information, wherein the plurality of historical fluctuation information comprises a plurality of historical fluctuation amplitudes and a plurality of historical fluctuation association features;
Constructing a fluctuation grade evaluation value set;
calculating characteristic association coefficients according to the fluctuation level evaluation value set and the plurality of historical fluctuation amplitudes to obtain a plurality of characteristic association coefficient values;
and screening the associated features of the secondary heating areas according to the feature associated coefficient values, so as to generate the target feature sets.
3. A combined heat and power control method based on load prediction of a heat supply network system as claimed in claim 1, comprising:
acquiring an emergency supply protection instruction, and calling a heating area screening module according to the emergency supply protection instruction;
inputting the plurality of secondary predicted load demands into the heating area screening module for load compression to obtain a plurality of secondary predicted compression load demands;
and carrying out heat supply combined control on the target heat supply network system according to the first-level demand load information and the plurality of second-level predicted compression load demands.
4. A combined heat and power control method based on load prediction of a heat supply network system as claimed in claim 1, comprising:
calculating the total predicted load demand of the target heat supply network system according to the primary demand load information and the plurality of secondary predicted load demands to obtain total predicted load information;
Acquiring real-time heat source supply conditions of a target heat supply network system, and acquiring preset heat supply mode information, wherein the preset heat supply mode information comprises a heat supply unit operation mode and heat supply unit operation parameters;
and constraining the preset heat supply mode information by using the total predicted load information, judging whether the preset heat supply mode information can meet the requirement, if so, carrying out heat supply according to the preset heat supply mode information, and if not, taking the preset heat supply mode as the heat supply mode information to be optimized.
5. A heat supply combined control method based on heat supply network system load prediction as claimed in claim 4, comprising:
adjusting the heat supply mode information to be optimized by adopting a plurality of random adjustment modes, and constructing a first neighborhood of the heat supply mode information to be optimized, wherein the first neighborhood comprises a plurality of first heat supply adjustment modes, and the plurality of random adjustment modes are used for adjusting the operation modes of the heat supply unit and the operation parameters of the heat supply unit;
acquiring the fitness of the plurality of first adjustment heating modes, and acquiring the fitness of the plurality of first adjustment heating modes;
and obtaining the maximum value of the first adjustment fitness as the first fitness, and taking the corresponding first adjustment heat supply mode as first heat supply mode information.
6. A heat supply combined control method based on heat supply network system load prediction as claimed in claim 5, comprising:
adding a random adjustment mode for adjusting and obtaining the first heat supply mode information into a tabu space, wherein the tabu space comprises a tabu iteration number;
continuing to construct a second neighborhood of the first heat supply mode information, performing iterative optimization, and deleting a random adjustment mode for adjusting and obtaining the first heat supply mode information from the tabu space when the iteration number reaches the tabu iteration number;
stopping optimizing when the iterative optimization reaches the preset iterative times, and obtaining optimized heat supply mode information by the heat supply mode information corresponding to the maximum adaptability value in the iterative optimization process;
and carrying out heat supply combined control according to the optimized heat supply mode information.
7. The method for combined heat and power control based on load prediction of a heat supply network system according to claim 6, wherein said obtaining the fitness of the plurality of first adjusted heat supply modes to obtain the fitness of the plurality of first adjusted heat supply modes comprises:
calculating the real-time maximum load of the first adjustment heating modes to obtain a plurality of pieces of real-time maximum load information, wherein the real-time maximum load information corresponds to the first adjustment heating modes one by one;
Obtaining a plurality of heating costs according to the real-time heating material consumption and the real-time heating material price of the plurality of first adjustment heating modes;
and weighting and calculating the plurality of real-time maximum load information and the plurality of heating costs according to the preset weight ratio to obtain the plurality of first adjustment fitness.
8. A combined heat and power control method based on load prediction of a heat supply network system according to claim 3, comprising:
determining a plurality of load demands to be supported according to the plurality of second-level predicted load demands and the plurality of second-level predicted compression load demands;
collecting distributed heat supply source configuration information of the secondary heat supply area for heat supply analysis, wherein the distributed heat supply source configuration information comprises a heat supply source type and a heat supply source specification;
traversing the plurality of load demands to be supported based on the heat supply analysis result to calculate missing data, judging whether the calculation result is larger than a preset threshold value, and if so, carrying out forward marking on the heat supply analysis result;
judging whether the calculated result is smaller than a preset threshold value, and if so, carrying out negative marking on the heating capacity analysis result;
And (3) carrying out distributed heat supply source scheduling by using a K-clustering method and combining positive marks and negative marks.
9. A heat supply combined control system based on heat supply network system load prediction, comprising:
the heat supply area obtaining module is used for dividing a heat supply coverage area of the target heat supply network system into grids according to heat supply branches to obtain a plurality of heat supply areas;
the grading module is used for acquiring the heat supply demand attribute proportion conditions of the plurality of heat supply areas and grading according to the heat supply demand attribute proportion conditions to acquire a primary heat supply area and a secondary heat supply area;
the primary demand load acquisition module is used for acquiring primary demand load information of the primary heating area, wherein the primary heating area is a supply protection area, namely an area which needs to be met by the demand load;
the historical load information acquisition module is used for acquiring a plurality of historical load information sets of the secondary heating area through the data calling module, carrying out feature analysis on the plurality of historical load information sets and generating a plurality of target feature sets;
The real-time target characteristic value acquisition module is used for acquiring real-time characteristic values of the secondary heating area according to the target characteristic sets to obtain a plurality of real-time secondary load characteristic value sets;
the load demand obtaining module is used for traversing the real-time secondary load characteristic value sets to be input into a load prediction model to obtain a plurality of secondary predicted load demands;
and the heat supply combined control module is used for carrying out heat supply combined control on the target heat supply network system according to the primary demand load information and the plurality of secondary predicted load demands.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310211587.XA CN116255665A (en) | 2023-03-07 | 2023-03-07 | Heat supply combined control method and system based on load prediction of heat supply network system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310211587.XA CN116255665A (en) | 2023-03-07 | 2023-03-07 | Heat supply combined control method and system based on load prediction of heat supply network system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116255665A true CN116255665A (en) | 2023-06-13 |
Family
ID=86684112
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310211587.XA Pending CN116255665A (en) | 2023-03-07 | 2023-03-07 | Heat supply combined control method and system based on load prediction of heat supply network system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116255665A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116993227A (en) * | 2023-09-22 | 2023-11-03 | 北明天时能源科技(北京)有限公司 | Heat supply analysis and evaluation method, system and storage medium based on artificial intelligence |
-
2023
- 2023-03-07 CN CN202310211587.XA patent/CN116255665A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116993227A (en) * | 2023-09-22 | 2023-11-03 | 北明天时能源科技(北京)有限公司 | Heat supply analysis and evaluation method, system and storage medium based on artificial intelligence |
| CN116993227B (en) * | 2023-09-22 | 2023-12-15 | 北明天时能源科技(北京)有限公司 | Heat supply analysis and evaluation method, system and storage medium based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116646933B (en) | Big data-based power load scheduling method and system | |
| Milligan | Modelling utility‐scale wind power plants. Part 2: Capacity credit | |
| CN110717688A (en) | Water, wind and light short-term combined optimization scheduling method considering new energy output uncertainty | |
| CN112671831B (en) | Multistage application system for digital intelligent heat supply platform of large group company | |
| CN107423836B (en) | Short-term load prediction method based on body sensing temperature | |
| CN110011358B (en) | Distribution network load state adjustment controller | |
| CN113326654A (en) | Method and device for constructing gas load prediction model | |
| CN116255665A (en) | Heat supply combined control method and system based on load prediction of heat supply network system | |
| CN114372360A (en) | Method, terminal and storage medium for power load prediction | |
| CN115907822A (en) | Load characteristic index relevance mining method considering region and economic influence | |
| CN116362584A (en) | Economic analysis method based on user side energy storage capacity configuration | |
| CN112633762A (en) | Building energy efficiency obtaining method and equipment | |
| CN115115193A (en) | Low-carbon analysis and optimization planning method for industrial park | |
| CN116706905B (en) | Multi-energy prediction and scheduling method, equipment and storage medium based on power system | |
| CN116526584B (en) | Green power traceability-based virtual power plant quick response regulation and control method | |
| CN114943471A (en) | Low-carbon index system of power system and comprehensive evaluation method | |
| CN112330017A (en) | Power load prediction method, power load prediction device, electronic device, and storage medium | |
| Ghaemi et al. | Sizing optimization of district energy systems considering meteorological, demand, and electricity emission factor uncertainties | |
| CN117252707B (en) | Power grid project investment optimization method and device | |
| Puech et al. | Controlling microgrids without external data: A benchmark of stochastic programming methods | |
| Rama et al. | A predictive analysis of residential electrical load demand in Mauritius | |
| CN117134364B (en) | Feed processing enterprise load management method based on staged strategy gradient algorithm | |
| CN117595517B (en) | Intelligent cluster control method and system based on distributed photovoltaic | |
| CN115983576A (en) | Self-adaptive multi-element energy load characteristic identification method | |
| CN118171788A (en) | Collaborative optimization method for schedulable flexible resources and power grid planning layout |
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 |