CN112862189A - Method, device, apparatus, storage medium, and program product for predicting heat source load - Google Patents
Method, device, apparatus, storage medium, and program product for predicting heat source load Download PDFInfo
- Publication number
- CN112862189A CN112862189A CN202110166111.XA CN202110166111A CN112862189A CN 112862189 A CN112862189 A CN 112862189A CN 202110166111 A CN202110166111 A CN 202110166111A CN 112862189 A CN112862189 A CN 112862189A
- Authority
- CN
- China
- Prior art keywords
- heat source
- model
- heat
- data
- real
- 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 83
- 238000003860 storage Methods 0.000 title claims abstract description 19
- 230000003068 static effect Effects 0.000 claims abstract description 77
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims description 82
- 238000010438 heat treatment Methods 0.000 claims description 81
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 43
- 230000003238 somatosensory effect Effects 0.000 claims description 33
- 238000013461 design Methods 0.000 claims description 31
- 238000005070 sampling Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 239000008400 supply water Substances 0.000 claims description 10
- 230000002688 persistence Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract description 19
- 230000000694 effects Effects 0.000 abstract description 8
- 238000004422 calculation algorithm Methods 0.000 description 21
- 238000010586 diagram Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 238000005457 optimization Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000002440 industrial waste Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2477—Temporal data queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a heat source load prediction method, a heat source load prediction device, equipment, a storage medium and a program product, and relates to the technical field of artificial intelligence and cloud computing. One embodiment of the method comprises: acquiring future weather data; acquiring real-time data and static parameter data of a heat source of a heat supply system; and processing future weather data, real-time data and static parameter data by using a pre-trained heat source model, and predicting to obtain a future load prediction result of the heat source. The implementation mode can remarkably improve the load prediction effect of the heat source in the heat supply scene by means of strong artificial intelligence prediction capability.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to the field of artificial intelligence and cloud computing technologies, and in particular, to a method, an apparatus, a device, a storage medium, and a program product for predicting a heat source load.
Background
With the industrial upgrading of the industrial internet of things and the transformation of the structure of the traditional manufacturing industry, the rapid transformation from the traditional industrial industry to the intelligent mode is urgently needed. At present, various heat supply companies and enterprises are actively exploring different degrees of intelligent heat supply. However, the existing intelligent heat supply platform is more concentrated on unification and supervision on a data level, heat supply scheduling under complex actual scenes cannot be deeply explored and adapted, and the load prediction effect on a heat source of a heat supply system is poor.
Disclosure of Invention
The application provides a heat source load prediction method, device, equipment, storage medium and program product.
According to a first aspect of the present application, there is provided a heat source load prediction method including: acquiring future weather data; acquiring real-time data and static parameter data of a heat source of a heat supply system; and processing future weather data, real-time data and static parameter data by using a pre-trained heat source model, and predicting to obtain a future load prediction result of the heat source.
According to a second aspect of the present application, there is provided a heat source load prediction apparatus including: a first acquisition unit configured to acquire future weather data; a second obtaining unit configured to obtain real-time data and static parameter data of a heat source of the heating system; and the prediction unit is configured to process the future weather data, the real-time data and the static parameter data by utilizing a pre-trained heat source model, and predict the future load prediction result of the heat source.
According to a third aspect of the present application, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described in any one of the implementations of the first aspect.
According to a fourth aspect of the present application, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method as described in any one of the implementations of the first aspect.
According to a fifth aspect of the application, a computer program product is provided, comprising a computer program which, when executed by a processor, implements a method as described according to any of the implementations of the first aspect.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
FIG. 1 is a flow diagram of one embodiment of a heating system scheduling method according to the present application;
FIG. 2 is a flow chart of yet another embodiment of a heating system scheduling method according to the present application;
FIG. 3 is a heating system dispatch platform architecture diagram;
FIG. 4 is a flow diagram of one embodiment of a heat source load prediction method according to the present application;
FIG. 5 is a flow chart of yet another embodiment of a heat source load prediction method according to the present application;
FIG. 6 is a flow diagram of one embodiment of a heat source model training method according to the present application;
FIG. 7 is a diagram of an application scenario of a heat source model training method;
FIG. 8 is a diagram of an application scenario of a heat source load prediction method;
FIG. 9 is a schematic diagram of an embodiment of a heating system scheduling apparatus according to the present application;
fig. 10 is a block diagram of an electronic device for implementing a heating system scheduling method according to an embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 shows a flow 100 of an embodiment of a heating system scheduling method according to the present application. The heat supply system scheduling method comprises the following steps:
In this embodiment, the executing body of the heat supply system scheduling method may obtain the first real-time data of the heat supply system currently reported by the gateway.
In general, a heating system may be a system in which a plant provides steam or hot water to a heat user and recovers return water thereof, and pipelines in the plant are connected. The heating system may include, but is not limited to, heat sources, heat exchange stations, and user terminals. The gateway can interact with the heating system and is used for collecting and reporting real-time data of the heating system. Here, the real-time data currently reported by the gateway is the first real-time data. The real-time data may be data that changes over time. Taking the heat source of the heating system as an example, the real-time data may include, but is not limited to, real-time water supply temperature, real-time water supply and return pressure, real-time flow rate, and the like.
In some optional implementations of this embodiment, the heating system scheduling method may be executed in the cloud. The cloud may include an edge module. The edge module can interact with the gateway for data reporting. For example, the gateway may collect real-time data of a heating system and periodically report to the cloud via the edge module. Generally, real-time data can be reported through the internet of things core suite. In a specific embodiment, the gateway can be connected to the internet of things core suite by configuring a Broker. The Internet of things core suite can support mass equipment data uploading, and therefore the Internet of things core suite is very suitable for the edge equipment scene. The rule engine suite under the core suite of the Internet of things can filter, convert and clean data. In addition, the cloud can also include a data module. The data module may interact with the edge module to provide a TSDB (Time Series Database). The reported real-time data can be filtered by combining with a rule engine and written into a TSDB of a data module. The TSDB is very suitable for mass storage and throughput query of real-time data, and simultaneously provides a visual operation interface, so that all data can be displayed on a panel, and monitoring is facilitated.
And 102, acquiring static parameter data of the heating system.
In this embodiment, the executing entity may obtain static parameter data of the heating system. The value of the static parameter data is usually a fixed value and does not change with time. Taking the heat source of the heating system as an example, the static parameter data may include, but is not limited to, a heat source identifier, a heating area, a heat consumption index, a heat source design temperature difference, and the like.
In some optional implementations of this embodiment, the data module may also provide a relational database (e.g., MySQL). The static parameter data is stored in a relational database. The execution agent may read the static parameter data from a relational database.
And 103, processing the first real-time data and the static parameter data by using a pre-trained prediction model, and predicting to obtain a load prediction result of the heating system.
In this embodiment, the executing entity may process the first real-time data and the static parameter data by using a pre-trained prediction model, and predict a load prediction result of the heating system.
Generally, the prediction model can be trained by using computing power of the cloud end, and the problems of insufficient computing resources and cost are not needed to be worried about. The predictive models may include, but are not limited to, at least one of: the system comprises a heat source model, a heat exchange station model, a user end model, a flow-valve opening model and a valve opening-flow reverse model. And the load prediction result obtained by prediction of the prediction model can be used for scheduling and adjusting the heating system. Taking the heat source model as an example, the predicted load prediction result may include the future required heat and the future water supply temperature.
In some optional implementations of the present embodiments, the prediction model may be persisted to a data module after training is complete. And, an index pointer is generated for the prediction model, and the prediction model can be called or tracked through the index pointer. If the prediction model is optimized and updated, the new prediction model is persisted to the data module. At the same time, a new index pointer is generated for the new prediction model. The cloud may also include an API (Application Programming Interface) module. The API module may be used to provide load prediction services. For example, the API module may call a corresponding prediction model according to the index pointer to predict the load prediction result of the heating system. The prediction model is black-boxed to the API module at the time of load prediction, and does not need to care about the specific model used for prediction. If exact positioning is required, it can be obtained by the model management module.
In some optional implementation manners of the embodiment, the first real-time data and the static parameter data are input to the persistent prediction model, so as to obtain a first load prediction result of the heating system. And meanwhile, inputting the first real-time data and the static parameter data into a currently used prediction model to obtain a second load prediction result of the heating system. If the second load prediction result is better than the first load prediction result, the prediction effect of the persisted prediction model is poorer than that of the model in current use. To improve the prediction effect, a load prediction result may be generated based on the first load prediction result and the second load prediction result. For example, the second load prediction result is determined as the load prediction result. Or combining the first load prediction result and the second load prediction result to generate a load prediction result. The generation of the load prediction result may be customized depending on the policy and is not limited herein.
And 104, transmitting the load prediction result to the gateway so that the gateway schedules the heating system based on the load prediction result.
In this embodiment, the execution subject may issue the load prediction result to the gateway. The gateway can dispatch the heat supply system based on the load prediction result, control the heat load, the water supply temperature, the water supply and return pressure and the like, and finally achieve the purposes of heat supply balance, reasonable heat supply, beneficial monitoring and cost saving.
In some optional implementation manners of this embodiment, the edge module may also be used for issuing data. For example, the load prediction result may be transmitted to the edge module by the data module, and sent to the gateway through the ipk (itsy package) of the edge module. The edge module interacts directly with the gateway, often requiring certain hardware requirements.
The method for scheduling the heat supply system comprises the steps of firstly obtaining first real-time data and static parameter data of the heat supply system; then, processing the first real-time data and the static parameter data by using a pre-trained prediction model, and predicting to obtain a load prediction result of the heating system; and finally, transmitting the load prediction result to the gateway. And the gateway schedules the heating system based on the load prediction result. The prediction model is obtained by training by utilizing the computing power of the cloud. The heat supply system scheduling method fusing the computing capability of the cloud and the prediction capability of artificial intelligence is provided, and end-cloud integrated intelligent scheduling of a heat supply system is achieved. The computing power of the cloud is fused, and the problems of insufficient computing resources and cost are not needed to be worried about. The prediction capability of the artificial intelligence is fused, and the result of algorithm realization and the prediction capability of the artificial intelligence are not needed to be worried about. Meanwhile, with the help of strong artificial intelligence prediction capability, the load prediction effect in a heat supply scene can be obviously improved. All elements of the heating system from a heat source to a heat consumer and a gateway including equipment are incorporated in a light weight mode, and the light weight is light and not heavy. And the deployment and operation of cross-platform are supported, and good compatibility is ensured.
It should be noted that the heat supply system scheduling method provided by the embodiment of the application can be applied to smart heat supply and smart energy industry scenes, is particularly applicable to heat supply scenes with relatively complete infrastructure, and can quickly realize the transformation of the landing and the direction of the traditional project. The problem of lag of current heating structure in the energy industry is solved, and traditional regulation strategy relies on PID (Proportional Integral Derivative) control, is very easily to produce and vibrates and inaccurate, needs to rely on more manpower manual regulation and leads to more resource input and human consumption. The problems that the heat supply effect is not ideal, the result data is lack of unified analysis and monitoring, and more dimensionalities of weather, room temperature and body sensing temperature and the personalized requirements of users cannot be met due to excessive dependence on manual experience due to the fact that a single adjusting strategy of an existing heat supply system is adopted are solved.
With continued reference to fig. 2, a flow 200 of yet another embodiment of a heating system scheduling method according to the present application is shown. The heat supply system scheduling method comprises the following steps:
In this embodiment, the execution subject of the heating system scheduling method may obtain historical real-time data of the heating system from the TSDB. The TSDB can store real-time data of a heating system of the cloud end which are periodically reported by the gateway.
In this embodiment, the executing entity may obtain the static parameter data of the heating system from the relational database. Wherein the relational database may be used for storing static parameter data of the heating system.
In this embodiment, the execution subject may perform integration processing on the historical real-time data and the static parameter data to obtain a first training sample set. Wherein the integration process may include, but is not limited to, filtering, converting, washing, and the like.
And step 204, training to obtain a prediction model based on the first training sample set.
In this embodiment, the executing entity may train to obtain the prediction model based on the first training sample set. Typically, supervised training is performed based on a first set of training samples, and a predictive model may be derived.
In practice, the heat supply system scheduling method provided by the embodiment of the application has perfect artificial intelligence prediction capability, and provides, but is not limited to, heat source model training and load prediction, heat exchange station model training and load prediction, user-side model training and load prediction, flow-valve opening model training, valve opening-flow reverse model training and the like.
In this embodiment, the execution subject may perform persistence processing on the prediction model and generate an index pointer of the prediction model. Where index pointers may be used for prediction invocation and model tracking.
In some optional implementation manners of this embodiment, the cloud end mainly includes an algorithm module, a data module, and an edge module. The algorithm module can be used for reading data in the time sequence database and the relation database and training the model. The data module interacts with the algorithm module and the edge module and can be used for logic processing and data adaptation. The edge module interacts with the data module and the gateway and can be used for reporting data. For example, the gateway may collect real-time data of a heating system and periodically report to the cloud via the edge module. The reported real-time data can be filtered by combining with a rule engine and written into a TSDB of a data module. The data module may read historical real-time data from the TSDB and static parameter data from the relational database. Meanwhile, the data module can integrate historical real-time data and static parameter data to obtain a first training sample set. The first training sample set can be transmitted to the algorithm module for model training, and the trained prediction model is returned to the data module. The data module may persist the predictive model.
In some optional implementations of this embodiment, the data module may interact with the algorithm module periodically or non-periodically, the former provides customized model training parameters, and the latter reads the TSDB real-time historical data according to the customized parameters and trains the model based on the multidimensional feature.
And step 206, acquiring first real-time data of the heating system currently reported by the gateway.
And step 207, acquiring static parameter data of the heating system.
And 208, processing the first real-time data and the static parameter data by using a pre-trained prediction model, and predicting to obtain a load prediction result of the heating system.
And 209, transmitting the load prediction result to the gateway so that the gateway schedules the heating system based on the load prediction result.
In the present embodiment, the specific operations of step 206-.
And step 210, after the scheduling of the heat supply system is completed, acquiring second real-time data of the heat supply system currently reported by the gateway.
In this embodiment, after the scheduling of the heating system is completed, the executing body may further obtain second real-time data of the heating system currently reported by the gateway. The second real-time data may be data that is updated and fed back by the gateway in real time after the scheduling of the heating system is completed. And the second real-time data is also written into the TSDB of the data module.
In this embodiment, the executing entity may generate a second training sample set based on the second real-time data and the static parameter data. The generation manner of the second training sample set may refer to the generation manner of the first training sample set in step 203, which is not described herein again.
In this embodiment, the execution subject may perform iterative optimization on the prediction model based on the second training sample set to obtain a new prediction model.
In some optional implementation manners of this embodiment, the algorithm module may be further configured to read data in the time sequence database and the relational database, and optimize the model. For example, the second set of training samples may be passed to the algorithm module for model optimization, resulting in a new predictive model being returned to the data module. The data module also persists the new prediction model and generates an index pointer for the new prediction model.
As can be seen from fig. 2, compared with the corresponding embodiment of fig. 1, the heating system scheduling method in this embodiment adds the training and optimization steps of the prediction model. Therefore, the scheme described in this embodiment provides a heating system scheduling method combining computing power of a cloud and prediction power of artificial intelligence, the cloud computing and the artificial intelligence are combined, a prediction model is trained through the computing power provided by the cloud, the trained prediction model is sent to a data module, a predicted load prediction result is sent to a gateway through an edge module to complete adjustment, the gateway updates and feeds back acquired data to the cloud in real time to serve as a training set iterative optimization algorithm model, so that real heating load prediction is realized, and the purpose of intelligent scheduling is achieved.
For ease of understanding, fig. 3 shows a heating system dispatch platform architecture diagram. The heat supply system scheduling method is applied to a heat supply system scheduling platform. The heat supply system scheduling platform is deployed at the cloud end and can comprise an algorithm module, a data module, an edge module, an API (application programming interface) module, a storage module, a calculation module and the like. The algorithm module is mainly used for reading data in the time sequence database and the relation database and training and optimizing the model. The algorithm module supports training of various model libraries and multi-dimensional multi-eigenvalue artificial intelligence models, and the models can be continuously self-optimized and self-trained along with the improvement of historical real-time data. The data module is a central module of the heat supply dispatching system. The data module interacts with the algorithm module, the API module, and the edge module, and may be used for various logic processes and data adaptation. The edge module interacts with the data module and the gateway and can be used for issuing and reporting data. The API module faces enterprise users and resident users, can be used for providing load forecasting service, data display service, platform monitoring service and the like, and supports expansion and customization. The storage module may be used to provide a timing database and a relational database. The computation module can be used to provide the underlying foundation including the kubernets-based container orchestration engine CCE, among others.
Compared with the existing intelligent heating system platform, the heating system dispatching platform in fig. 3 has the following differences: firstly, a heat supply system scheduling platform is constructed on the basis of strong cloud computing capability and artificial intelligence capability of a cloud end, and computing resources and artificial intelligence enabling are provided by the aid of the cloud computing capability and the artificial intelligence capability. Secondly, the heating system scheduling platform not only integrates the source, the station and the household of the heating system together, but also brings the edge module including the gateway, the valve, the flowmeter, the temperature collecting device and the like into the intelligent scheduling platform for the first time, thereby really realizing artificial intelligence and intellectualization of all links of the heating system, and being intelligent and intelligent heating in the real sense. And thirdly, the heat supply system dispatching platform logically separates the algorithm module from the data module, and the algorithm module and the data module are independently deployed for decoupling, so that expansion and model optimization upgrading under more scenes can be supported, and the applicability of the platform under more general and complex scenes is improved. The end-cloud integrated heat supply system scheduling method has high robustness and expansibility, decoupled sub-modules can be dynamically expanded, enhanced and optimized according to actual complex scenes, and the method can be applied to more common and complex heat supply scenes.
With further reference to FIG. 4, a flow 400 of one embodiment of a heat source load prediction method according to the present application is illustrated. The heat source load prediction method comprises the following steps:
in step 401, future weather data is obtained.
In the present embodiment, the execution subject of the heat source load prediction method may acquire future weather data. Wherein the future weather data may be weather data for a future period of time (e.g., a day, a week, etc.). In general, weather data may include outdoor temperature, sensible temperature, air humidity, wind power, and the like.
In this embodiment, the execution subject may obtain real-time data and static parameter data of a heat source of the heating system.
Generally, the heat source of the heating system may be, for example, a thermal power plant, a central boiler house, a low-temperature nuclear heating plant, a heat pump, geothermal heat, industrial waste heat, solar energy, or the like. The gateway can interact with the heat supply system and is used for collecting and reporting real-time data of a heat source of the heat supply system. The real-time data of the heat source may be data that varies over time, including but not limited to real-time supply water temperature, real-time supply and return water pressure, and real-time flow rate, among others. The value of the static parameter data of the heat source is usually a fixed value and does not change with time, and includes but is not limited to heat source identification, heat supply area, heat consumption index, heat source design temperature difference and the like.
And 403, processing future weather data, real-time data and static parameter data by using a pre-trained heat source model, and predicting to obtain a future load prediction result of the heat source.
In this embodiment, the executing agent may process future weather data, real-time data, and static parameter data by using a pre-trained heat source model, and predict a future load prediction result of the heat source.
In general, the heat source model can be trained by using computing power of the cloud, and the problems of insufficient computing resources and cost are not needed to be worried about. The heat source model can intelligently control the water supply temperature and the required heat for a future period of time to provide a prediction function. The future load prediction of the heat source may include a future required heat and a future supply water temperature.
In some optional implementations of the present embodiments, the data module may be persisted after the training of the heat source model is completed. And, an index pointer is generated for the heat source model, and the heat source model can be called or tracked through the index pointer. And if the heat source model is optimized and updated, the new heat source model is durably added to the data module. At the same time, a new index pointer is generated for the new heat source model. The execution main body can call the corresponding heat source model according to the index pointer to process future weather data, real-time data and static parameter data, and a future load prediction result of the heat source is obtained through prediction. And the trained heat source model is persisted to a data module, and the heat source model is read from the data module for load prediction without being transmitted outside. And the index pointer of the mobile heat source model is optimized in the data module, so that the heat source model which is as optimal as possible can be called every time the load is predicted. The module provides the function of index pointer automatic optimization of the heat source model. Usually, one-key prediction can be realized and the prediction result is issued, so that the complexity of the system in use is greatly reduced, and the outside does not need to care about too many training details. Of course, load prediction also supports a specified heat source model, which is rarely used in practical applications.
In some optional implementations of this embodiment, the future load prediction result of the heat source may be transmitted to the edge module by the data module, and sent to the gateway by the edge module. The gateway schedules the heat source based on future load prediction results for the heat source. The future load prediction result of the heat source comprises the future required heat and the future water supply temperature, the data of the prediction result is simple, and the analysis difficulty of the gateway cannot be increased.
According to the heat source load prediction method provided by the embodiment of the application, future weather data, real-time data of a heat source and static parameter data are obtained at first; and then, processing future weather data, real-time data and static parameter data by using a pre-trained heat source model, and predicting to obtain a future load prediction result of the heat source. The prediction capability of the artificial intelligence is fused, and the result of algorithm realization and the prediction capability of the artificial intelligence are not needed to be worried about. Meanwhile, with the help of strong artificial intelligence prediction capability, the load prediction effect of a heat source in a heat supply scene can be obviously improved.
With continued reference to FIG. 5, a flow 500 of yet another embodiment of a heat source load prediction method according to the present application is illustrated. The heat source model comprises a heat prediction model and a water supply temperature model, and the heat source load prediction method comprises the following steps:
In this embodiment, the specific operations of steps 501-502 have been described in detail in step 401-402 in the embodiment shown in fig. 4, and are not described herein again.
In this embodiment, the executing body of the heat source load prediction method may input the future weather data to the heat prediction model to obtain a fitting value of the heat exchange station of the heating system. Wherein the heat prediction model may be used to predict the future required heat.
Generally, the heat source model includes a somatosensory model and a non-somatosensory model. Where the heat source model is a somatosensory model, the future weather data may include a future outdoor temperature and a future somatosensory temperature. In the case where the heat source model is a non-somatosensory model, the future weather data may include future outdoor temperatures.
And 504, generating a future design temperature difference of the heat source based on the fitting value, the real-time data and the static parameter data of the heat exchange station.
In this embodiment, the execution body may generate a future design temperature difference of the heat source based on the fitting value, the real-time data and the static parameter data of the heat exchange station.
Usually, the fitting value, the real-time data and the static parameter data of the heat exchange station are calculated by using a regression function in the algorithm, and then the future design temperature difference of the heat source can be generated. In a specific embodiment, the executing body may first generate a heat rate fitting value based on the fitting value of the heat exchange station and the heat supply area; and then generating a future design temperature difference based on the heat consumption fitting value and the real-time flow. Wherein the heating area belongs to static parameter data. Real-time traffic pertains to real-time data. And calculating the fitting value and the heat supply area of the heat exchange station by using a regression function in the algorithm to generate a heat consumption fitting value. And calculating the heat consumption fitting value and the real-time flow by using a regression function in the algorithm to generate the future design temperature difference.
And 505, inputting the future weather data and the future design temperature difference into the water supply temperature model to obtain a future water supply temperature prediction result of the heat source.
In this embodiment, the execution subject may input the future weather data and the future design temperature difference into the water supply temperature model to obtain the future water supply temperature prediction result of the heat source. Wherein the supply water temperature prediction model may be used to predict a future supply water temperature.
As can be seen from fig. 5, compared with the embodiment corresponding to fig. 4, the heat source load prediction method in the present embodiment highlights the prediction step of the heat source model. Therefore, according to the scheme described in the embodiment, the future required heat is predicted by using the heat prediction model, and then the future water supply temperature is predicted by using the water supply temperature model, so that the prediction function of intelligently controlling the regional water supply temperature and the required heat in a future period of time is provided.
With further reference to FIG. 6, a flow 600 of one embodiment of a heat source model training method according to the present application is illustrated. The heat source model training method comprises the following steps:
In this embodiment, the execution subject of the heat source model training method may obtain the static parameter data, the training start-stop time, and the sampling frequency of the heat source of the heating system from the relational database. Wherein the relational database may be used for storing static parameter data of heat sources of the heating system. The heat source model may be a somatosensory model or a non-somatosensory model. If the heat source model is a non-somatosensory model, the static parameter data may include, but is not limited to, at least one of: heat source identification, heat supply area, heat consumption index and heat source design temperature difference. If the heat source model is a somatosensory model, the heat source static parameter data can further comprise a somatosensory temperature. The training start-stop time includes a training start time and an end time of the heat source model. In a scenario requiring manual intervention training, these two parameters may be specified manually. In the scenario of model auto-training and preference, these two parameters can be dynamically specified during auto-training. In practical applications, dynamically specified scenarios are most common. The sampling frequency can also be specified manually or dynamically, with a default value of 1 minute.
In this embodiment, the execution subject may obtain historical real-time data of the heat source of the heating system from the TSDB based on the training start-stop time and the sampling frequency. The TSDB can store real-time data of a heat source of a heat supply system of the cloud periodically reported by the gateway. The historical real-time data of heat sources may include, but is not limited to, at least one of: historical real-time water supply temperature, historical real-time water supply and return pressure, historical real-time flow and the like.
In this embodiment, the execution subject may extract feature values from the static parameter data of the heat source and the historical real-time data of the heat source to obtain a training sample set. Typically, the characteristic values required for training, including but not limited to water supply temperature, body sensing temperature, outdoor temperature, initial energy consumption index, and design temperature difference, are extracted.
And step 604, training to obtain a heat source model based on the training sample set.
In this embodiment, the executing entity may train to obtain the heat source model based on the training sample set. Typically, supervised training is performed based on a training sample set, and a heat source model may be derived.
In some optional implementations of the present embodiment, the heat source model may include a heat prediction model and a supply water temperature model. When the heat source model is a somatosensory model, the heat prediction model is a model trained by taking outdoor temperature and the somatosensory temperature as input and taking an initial heat consumption index as output. The water supply temperature model is trained by taking outdoor temperature, somatosensory temperature and design temperature difference as inputs and water supply temperature as an output. And under the condition that the heat source model is a non-somatosensory model, the heat prediction model is a model trained by taking outdoor temperature as input and taking an initial heat consumption index as output. The water supply temperature model is trained by taking outdoor temperature and design temperature difference as input and water supply temperature as output.
In this embodiment, the execution subject may perform persistence processing on the heat source model and generate an index pointer of the heat source model. Where index pointers may be used for prediction invocation and model tracking.
In some optional implementations of the present embodiment, after the training of the heat source model is completed, a persistence process may be performed. And, an index pointer is generated for the heat source model, and the heat source model can be called or tracked through the index pointer. And if the heat source model is optimized and updated, the new heat source model can be persisted. At the same time, a new index pointer is generated for the new prediction model.
And for the non-somatosensory model, model fitting and prediction are mainly carried out on relevant data such as outdoor temperature, water supply and return pressure and the like. For somatosensory models, the somatosensory temperature can also be combined. In addition, dimensional characteristics such as air humidity and wind power can be considered, so that the applicability and the accuracy of the heat source load prediction model in a more general scene can be guaranteed.
The heat source model training method provided by the embodiment of the application comprises the steps of firstly obtaining static parameter data, training start-stop time and sampling frequency of a heat source of a heat supply system from a relational database; then, acquiring historical real-time data of a heat source of the heating system from a time sequence database based on the training start-stop time and the sampling frequency; then extracting characteristic values from the static parameter data of the heat source and the historical real-time data of the heat source to obtain a training sample set; and finally, training to obtain a heat source model based on the training sample set. Thereby, a heat source model capable of load prediction is obtained.
For ease of understanding, fig. 7 shows an application scenario diagram of the heat source model training method. Here, the heat source model in fig. 7 is a somatosensory model. Firstly, acquiring real-time data get _ region _ data of a heat source from a TSDB, and acquiring data such as an initial heat consumption index region _ qn, a body sensing temperature region _ Ta, an outdoor temperature region _ Tw, a water supply temperature region _ Tg, a design temperature difference region _ Tdelta and the like. And then extracting a training sample set df _ region _ data based on the data, performing load prediction-fitting of a region _ load _ modeling _ fit by using the training sample set df _ region _ data, and training to obtain a heat prediction model heatDemandModel and a water supply temperature model SupplytetramperatureModel. The heat prediction model heatDemandModel is trained based on the outdoor temperature region _ Tw and the sensible temperature region _ Ta. The water supply temperature model supplied temperature model is obtained by taking an outdoor temperature region _ Tw, a body sensing temperature region _ Ta and a design temperature difference region _ Tdelta as inputs and taking a water supply temperature region _ Tg as an output.
For ease of understanding, fig. 8 shows an application scenario diagram of the heat source load prediction method. Here, the heat source model in fig. 8 is a somatosensory model. Firstly, inputting the future sensible temperature future _ Ta and the future outdoor temperature future _ Tw into a heat prediction model heatDemandModel to obtain a fitting value future _ qn of the heat exchange station. And then, calculating the fitting value future _ qn, the heat supply area region _ area and the real-time flow rate region _ flow of the heat exchange station by using a regression function in the algorithm to generate the future design temperature difference future _ Tdelta. And finally, inputting the future sensible temperature future _ Ta, the future outdoor temperature future _ Tw and the future design temperature difference future _ Tdelta into the water supply temperature model supplied with water, so as to obtain the future water supply temperature future _ Tg.
With further reference to fig. 9, as an implementation of the methods shown in the above figures, the present application provides an embodiment of a heat source load prediction apparatus, which corresponds to the method embodiment shown in fig. 4, and which is particularly applicable to various electronic devices.
As shown in fig. 9, the heat source load prediction apparatus 900 of the present embodiment may include: a first acquisition unit 901, a second acquisition unit 902, and a prediction unit 903. Wherein, the first obtaining unit 901 is configured to obtain future weather data; a second obtaining unit 902 configured to obtain real-time data and static parameter data of a heat source of the heating system; and the prediction unit 903 is configured to process the future weather data, the real-time data and the static parameter data by using a pre-trained heat source model, and predict a future load prediction result of the heat source.
In the present embodiment, the heat source load prediction apparatus 900: the detailed processing of the first obtaining unit 901, the second obtaining unit 902 and the predicting unit 903 and the technical effects thereof can refer to the related descriptions of step 401 and step 403 in the corresponding embodiment of fig. 4, which are not repeated herein.
In some optional implementations of this embodiment, the heat source model includes a heat prediction model and a supply water temperature model; and the prediction unit 903 includes: a first prediction subunit configured to input future weather data to the heat prediction model, resulting in a fitted value of a heat exchange station of the heating system; a generating subunit configured to generate a future design temperature difference of the heat source based on the fitted values, the real-time data, and the static parameter data of the heat exchange station; and the second prediction subunit is configured to input the future weather data and the future design temperature difference into the water supply temperature model to obtain a future water supply temperature prediction result of the heat source.
In some optional implementations of this embodiment, the static parameter data includes a heating area, and the real-time data includes a real-time flow rate; and the generating subunit is further configured to: generating a heat consumption fitting value based on the fitting value and the heat supply area of the heat exchange station; and generating a future design temperature difference based on the heat consumption fitting value and the real-time flow.
In some optional implementations of the present embodiment, the heat source load prediction apparatus 900 further includes: a third obtaining unit configured to obtain static parameter data, training start-stop time, and sampling frequency of a heat source of the heating system from the relational database; a fourth obtaining unit configured to obtain historical real-time data of a heat source of the heating system from the time sequence database based on the training start-stop time and the sampling frequency; the extraction unit is configured to extract characteristic values from the static parameter data of the heat source and the historical real-time data of the heat source to obtain a training sample set; and the training unit is configured to train to obtain the heat source model based on the training sample set.
In some optional implementations of the present embodiment, the heat source load prediction apparatus 900 further includes: and the processing unit is configured to perform persistence processing on the heat source model and generate an index pointer of the heat source model, wherein the index pointer is used for prediction calling and model tracking.
In some optional implementations of this embodiment, the heat source model is a somatosensory model or a non-somatosensory model, and if the heat source model is a non-somatosensory model, the static parameter data includes at least one of: heat source identification, heat supply area, heat consumption index and heat source design temperature difference; and if the heat source model is a somatosensory model, the heat source static parameter data further comprises a somatosensory temperature.
In some optional implementations of this embodiment, the historical real-time data of the heat source includes at least one of: historical real-time water supply temperature, historical real-time water supply and return pressure and historical real-time flow.
There is also provided, in accordance with an embodiment of the present application, an electronic device, a readable storage medium, and a computer program product.
FIG. 10 shows a schematic block diagram of an example electronic device 1000 that may be used to implement embodiments of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 10, the apparatus 1000 includes a computing unit 1001 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)1002 or a computer program loaded from a storage unit 1008 into a Random Access Memory (RAM) 1003. In the RAM 1003, various programs and data necessary for the operation of the device 1000 can also be stored. The calculation unit 1001, the ROM 1002, and the RAM 1003 are connected to each other by a bus 1004. An input/output (I/O) interface 1005 is also connected to bus 1004.
A number of components in device 1000 are connected to I/O interface 1005, including: an input unit 1006 such as a keyboard, a mouse, and the like; an output unit 1007 such as various types of displays, speakers, and the like; a storage unit 1008 such as a magnetic disk, an optical disk, or the like; and a communication unit 1009 such as a network card, a modem, a wireless communication transceiver, or the like. The communication unit 1009 allows the device 1000 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present application may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this application, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (17)
1. A heat source load prediction method, comprising:
acquiring future weather data;
acquiring real-time data and static parameter data of a heat source of a heat supply system;
and processing the future weather data, the real-time data and the static parameter data by utilizing a pre-trained heat source model, and predicting to obtain a future load prediction result of the heat source.
2. The method of claim 1, wherein the heat source model comprises a heat prediction model and a supply water temperature model; and
the processing the future weather data, the real-time data and the static parameter data by using a pre-trained heat source model to predict the future load prediction result of the heat source comprises the following steps:
inputting the future weather data into the heat prediction model to obtain a fitting value of a heat exchange station of the heat supply system;
generating a future design temperature difference of the heat source based on the fitting value of the heat exchange station, the real-time data and the static parameter data;
and inputting the future weather data and the future design temperature difference into the water supply temperature model to obtain a future water supply temperature prediction result of the heat source.
3. The method of claim 2, wherein the static parameter data comprises a heating area, and the real-time data comprises a real-time flow rate; and
generating a future design temperature difference of the heat source based on the fit values of the heat exchange station, the real-time data and the static parameter data, comprising:
generating the heat consumption fitting value based on the fitting value of the heat exchange station and the heat supply area;
generating the future design temperature difference based on the heat rate fit value and the real-time flow.
4. The method of claim 1, wherein the method further comprises:
obtaining static parameter data, training start-stop time and sampling frequency of a heat source of the heat supply system from a relational database;
acquiring historical real-time data of a heat source of the heating system from a time sequence database based on the training start-stop time and the sampling frequency;
extracting characteristic values from the static parameter data of the heat source and the historical real-time data of the heat source to obtain a training sample set;
and training to obtain the heat source model based on the training sample set.
5. The method of claim 4, wherein after the training the heat source model based on the training sample set, further comprising:
the method comprises the steps of conducting persistence processing on the heat source model, and generating an index pointer of the heat source model, wherein the index pointer is used for forecasting calling and model tracing.
6. The method of claim 4, wherein the heat source model is a somatosensory model or a non-somatosensory model, and if the heat source model is a non-somatosensory model, the static parameter data comprises at least one of: heat source identification, heat supply area, heat consumption index and heat source design temperature difference; and if the heat source model is a somatosensory model, the heat source static parameter data further comprises a somatosensory temperature.
7. The method of claim 4, wherein the historical real-time data of the heat source comprises at least one of: historical real-time water supply temperature, historical real-time water supply and return pressure and historical real-time flow.
8. A heat source load prediction apparatus comprising:
a first acquisition unit configured to acquire future weather data;
a second obtaining unit configured to obtain real-time data and static parameter data of a heat source of the heating system;
and the prediction unit is configured to process the future weather data, the real-time data and the static parameter data by utilizing a pre-trained heat source model, and predict the future load prediction result of the heat source.
9. The apparatus of claim 8, wherein the heat source model comprises a heat prediction model and a supply water temperature model; and
the prediction unit includes:
a first prediction subunit configured to input the future weather data to the heat prediction model, resulting in fitted values for heat exchange stations of the heating system;
a generating subunit configured to generate a future design temperature difference for the heat source based on the fit values of the heat exchange station, the real-time data, and the static parameter data;
a second prediction subunit configured to input the future weather data and the future design temperature difference to the supply water temperature model to obtain a future supply water temperature prediction of the heat source.
10. The apparatus of claim 9, wherein the static parameter data comprises a heating area, and the real-time data comprises a real-time flow rate; and
the generating subunit is further configured to:
generating the heat consumption fitting value based on the fitting value of the heat exchange station and the heat supply area;
generating the future design temperature difference based on the heat rate fit value and the real-time flow.
11. The apparatus of claim 8, wherein the apparatus further comprises:
a third obtaining unit configured to obtain static parameter data, training start-stop time, and sampling frequency of a heat source of the heating system from a relational database;
a fourth obtaining unit configured to obtain historical real-time data of a heat source of the heating system from a time series database based on the training start-stop time and the sampling frequency;
the extraction unit is configured to extract characteristic values from the static parameter data of the heat source and the historical real-time data of the heat source to obtain a training sample set;
a training unit configured to train the heat source model based on the training sample set.
12. The apparatus of claim 11, wherein the apparatus further comprises:
the processing unit is configured to perform persistence processing on the heat source model and generate an index pointer of the heat source model, wherein the index pointer is used for prediction calling and model tracking.
13. The apparatus of claim 11, wherein the heat source model is a somatosensory model or a non-somatosensory model, and wherein the static parameter data comprises at least one of: heat source identification, heat supply area, heat consumption index and heat source design temperature difference; and if the heat source model is a somatosensory model, the heat source static parameter data further comprises a somatosensory temperature.
14. The method of claim 11, wherein the historical real-time data of the heat source comprises at least one of: historical real-time water supply temperature, historical real-time water supply and return pressure and historical real-time flow.
15. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
16. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-7.
17. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110166111.XA CN112862189B (en) | 2021-02-03 | 2021-02-03 | Heat source load prediction method, heat source load prediction device, heat source load prediction apparatus, heat source load prediction device, heat source load prediction program product, and heat source load prediction program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110166111.XA CN112862189B (en) | 2021-02-03 | 2021-02-03 | Heat source load prediction method, heat source load prediction device, heat source load prediction apparatus, heat source load prediction device, heat source load prediction program product, and heat source load prediction program product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112862189A true CN112862189A (en) | 2021-05-28 |
| CN112862189B CN112862189B (en) | 2023-11-10 |
Family
ID=75988808
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110166111.XA Active CN112862189B (en) | 2021-02-03 | 2021-02-03 | Heat source load prediction method, heat source load prediction device, heat source load prediction apparatus, heat source load prediction device, heat source load prediction program product, and heat source load prediction program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112862189B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114222477A (en) * | 2021-12-13 | 2022-03-22 | 中国联合网络通信集团有限公司 | Energy-saving control method and device for data center, storage medium and program product |
| CN117249471A (en) * | 2023-11-20 | 2023-12-19 | 哈尔滨哈东新春锅炉有限公司 | Boiler load adjusting method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203274046U (en) * | 2013-05-14 | 2013-11-06 | 沈阳汇博自动化仪表有限公司 | Heat exchanging station intelligent controller and water/water heat exchanging control system |
| CN106447529A (en) * | 2016-08-30 | 2017-02-22 | 上海交通大学 | Distributed energy system modeling and running optimization method considering hot water pipe network |
| CN108240679A (en) * | 2018-02-22 | 2018-07-03 | 烟台科创捷能机电工程有限公司 | A kind of heat supply method based on building heating load prediction, device and system |
| CN109681957A (en) * | 2018-08-30 | 2019-04-26 | 中节能唯绿（北京）科技股份有限公司 | A kind of heat exchange station heat load prediction method |
| US10402733B1 (en) * | 2015-06-17 | 2019-09-03 | EMC IP Holding Company LLC | Adaptive ensemble workload prediction model based on machine learning algorithms |
| CN110701672A (en) * | 2019-10-28 | 2020-01-17 | 沈阳瑞科斯节能科技有限公司 | Heat supply management system |
-
2021
- 2021-02-03 CN CN202110166111.XA patent/CN112862189B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203274046U (en) * | 2013-05-14 | 2013-11-06 | 沈阳汇博自动化仪表有限公司 | Heat exchanging station intelligent controller and water/water heat exchanging control system |
| US10402733B1 (en) * | 2015-06-17 | 2019-09-03 | EMC IP Holding Company LLC | Adaptive ensemble workload prediction model based on machine learning algorithms |
| CN106447529A (en) * | 2016-08-30 | 2017-02-22 | 上海交通大学 | Distributed energy system modeling and running optimization method considering hot water pipe network |
| CN108240679A (en) * | 2018-02-22 | 2018-07-03 | 烟台科创捷能机电工程有限公司 | A kind of heat supply method based on building heating load prediction, device and system |
| CN109681957A (en) * | 2018-08-30 | 2019-04-26 | 中节能唯绿（北京）科技股份有限公司 | A kind of heat exchange station heat load prediction method |
| CN110701672A (en) * | 2019-10-28 | 2020-01-17 | 沈阳瑞科斯节能科技有限公司 | Heat supply management system |
Non-Patent Citations (4)
| Title |
|---|
| YAN DING 等: "Model input selection for building heating load prediction: A case study for an office building in Tianjin", ENERGY AND BUILDINGS * |
| 朱雷;: "多维控制策略在供热生产实时监控系统中的应用", 区域供热, no. 03 * |
| 李琦;武旭丹;: "基于ADHDP的热源供热优化控制", 信息与控制, no. 05 * |
| 白鹤;杨亚龙;范文强;: "大数据分析在供热运行监测和节能领域的应用", 区域供热, no. 03 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114222477A (en) * | 2021-12-13 | 2022-03-22 | 中国联合网络通信集团有限公司 | Energy-saving control method and device for data center, storage medium and program product |
| CN117249471A (en) * | 2023-11-20 | 2023-12-19 | 哈尔滨哈东新春锅炉有限公司 | Boiler load adjusting method and system |
| CN117249471B (en) * | 2023-11-20 | 2024-01-16 | 哈尔滨哈东新春锅炉有限公司 | Boiler load adjusting method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112862189B (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11204591B2 (en) | Modeling and calculating normalized aggregate power of renewable energy source stations | |
| JP5985861B2 (en) | Energy utilization analysis system and method | |
| US9727828B2 (en) | Method for evaluating operational and financial performance for dispatchers using after the fact analysis | |
| KR101648272B1 (en) | Method for forecasting household water demand and detecting water leakage based on complex event processing and machine learning | |
| JP7161268B2 (en) | Quantifying the combined impact of interdependent and uncertain resources within the power grid | |
| WO2013040853A1 (en) | Cloud computing-based system and method for management and control of water pump | |
| CN112862189A (en) | Method, device, apparatus, storage medium, and program product for predicting heat source load | |
| CN112836370B (en) | Heating system scheduling method, apparatus, device, storage medium and program product | |
| Huang et al. | Distributed machine learning on smart-gateway network toward real-time smart-grid energy management with behavior cognition | |
| CN105868073A (en) | Data center energy saving strategy implementation method based on time series analysis | |
| Yang et al. | Increasing the energy efficiency of a data center based on machine learning | |
| CN110867956A (en) | Topology automatic identification system and method based on intelligent platform area | |
| CN111625583B (en) | Business data processing method and device, computer equipment and storage medium | |
| CN117236571B (en) | Planning method and system based on Internet of things | |
| Urazayev et al. | Distributed Energy Management System with the Use of Digital Twin | |
| CN115579935A (en) | Power generation system control method, device, system, electronic device and storage medium | |
| WO2019055329A1 (en) | A method of learning robust regression models from limited training data | |
| CN116993240A (en) | Logistics system control method, device, equipment and storage medium | |
| CN110443460B (en) | Artificial intelligent analysis method and device for heat exchange quantity of heat exchange station based on weather and community heat loss | |
| Ramesh et al. | Big Data and IoT System for Utility Power Planning using Commercial Cloud Database | |
| CN105631606A (en) | Energy data management system and energy data management method based on energy metering network diagram | |
| Rohith et al. | GUI energy demand forecast using LSTM deep learning model in python platform | |
| Plamanescu et al. | High-reporting rate smart metering framework using fiware technology | |
| Roux | Load management of electric water heaters in a smart grid through forecasting and intelligent centralised control | |
| Bu et al. | Distributed unit commitment scheduling in the future smart grid with intermittent renewable energy resources and stochastic power demands |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |