CN109377060B - BP neural network electric heating equipment adjusting capacity evaluation method based on similarity - Google Patents
BP neural network electric heating equipment adjusting capacity evaluation method based on similarity Download PDFInfo
- Publication number
- CN109377060B CN109377060B CN201811266385.0A CN201811266385A CN109377060B CN 109377060 B CN109377060 B CN 109377060B CN 201811266385 A CN201811266385 A CN 201811266385A CN 109377060 B CN109377060 B CN 109377060B
- Authority
- CN
- China
- Prior art keywords
- electric heating
- temperature
- heating equipment
- time
- similarity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- 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
Abstract
The invention relates to a BP neural network electric heating equipment regulating capacity evaluation method based on similarity, which is characterized by comprising the following steps of: firstly, defining the regulation capacity index of electric heating load, then calculating the similarity between historical data and the forecast time, and evaluating the temperature interval [ T ] meeting the human body comfort levelmin,Tmax]The adjustment capability of the electric heating load determines the basic principle of the evaluation of the adjustment capability of the electric heating load by utilizing the measured parameters, and provides the step of evaluating the adjustment capability of the electric heating equipment and a system framework which can be realized by a computer. The invention can provide an accurate and practical method for evaluating the adjusting capacity of the electric heating equipment, and improves the accuracy and the practicability of evaluating the adjusting capacity of the electric heating equipment.
Description
Technical Field
The invention belongs to electric heating, and relates to a BP neural network electric heating equipment regulation capacity evaluation method based on similarity.
Background
Renewable energy sources such as wind energy, solar energy and the like are used for generating power and are incorporated into a power grid in a large scale, and the phenomena of difficulty, serious wind and light abandonment and the like are brought to the safe and economic operation of the power grid. Under the condition, the safe and economic operation of the power grid is often difficult to meet only through power generation side means such as primary frequency modulation of the generator, automatic power generation control, economic dispatching and the like, and auxiliary load regulation and control means are needed. With the great promotion of the country to adopt the electric heating mode, the time-shifting load with the characteristics of energy storage, high response speed, high controllability and the like is adopted in the electric heating mode, and when the installed capacity is considerable, the adjustment capacity of a power grid is improved by the energy storage load of the electric heating mode. Therefore, whether the regulation capacity of the electric heating in a certain period of time in the future can be accurately predicted is the basis for participating in the regulation capacity of the power grid. At present, most of work is to macroscopically evaluate the adjusting capacity of the electric heating equipment on the basis of the existing thermodynamic model, and the adjusting capacity of the electric heating equipment cannot be accurately evaluated due to the influence of various uncertain factors. Under the background, the invention provides a BP neural network electric heating equipment regulation capacity evaluation method based on similarity.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method overcomes the defects of the prior art, provides an accurate BP neural network electric heating equipment adjusting capacity assessment method based on similarity, can obtain an analog simulation result close to the actual result, and improves the accuracy of electric heating equipment adjusting capacity assessment.
The technical scheme for solving the technical problem is as follows: a BP neural network electric heating equipment adjusting capacity assessment method based on similarity is characterized in that: firstly, defining the regulation capacity index of the electric heating equipment, then calculating the similarity between historical data and the moment to be predicted, and evaluating the temperature interval [ T ] meeting the human body comfort levelmin,Tmax]The regulation capability of the electric heating equipment comprises the following contents:
1) defining the regulation capacity index of the electric heating load;
p is the power of the electric heating equipment, and the unit is kW;
t is the time that the electric heating equipment can be turned on or off in the comfort interval of the user, and the unit h is the time;
w is the regulation capacity index of the electric heating equipment, and the unit kWh;
2) calculating the similarity between the historical data and the time to be predicted;
the calculation is as formula (1):
in formula (1): the feature vector at historical i time is Xi=[xi1,xi2,xi3,…,xim],i=1,2,3,…,ximM is the number of the characteristic quantities, and the characteristic vector text of the moment to be predicted is Xj;
3) Electrical heating load regulation capability assessment
Determining influence factors of similar selection;
determining the type, position and area S of a building using electric heating, and determining a user comfort interval [ Tmin,Tmax]Providing heating data of history n days including outdoor temperature, indoor temperature and solar irradiance;
determining historical feature vector XikAnd the current time characteristic vector Xjk;
Selecting the indoor temperature T at a certain momentroomAsInitial temperature T at evaluation time of electric heating load regulation capacityoGiving the outdoor temperature change T in the future period according to the weather forecastoutAnd solar irradiance alpha, and extracting characteristic quantity x of time to be predicted and historical data1For the current time indoor temperature Troom、x2For the outdoor average temperature T in a future periodout,average、x3Is TminOr Tmax、x4Alpha, x as solar irradiance5Tendency of outdoor temperature change, x6Forming a historical characteristic vector X for the power of the equipment PikAnd the current time feature vector Xjk;
The outdoor temperature variation trend x5Setting of (1): outdoor temperature rise x5Is 1, outdoor temperature drop x5Is-1, the outdoor temperature is not changed x5Is 0;
thirdly, similar selection is carried out;
substituting the related data obtained in the first step and the second step in the step 3) into a similarity calculation formula (1), calculating the similarity between the historical time and the time to be predicted, and selecting the temperature rise and temperature reduction process data with large similarity;
establishing a BP neural network prediction model;
taking the data obtained from the third step of the step 3) as a training sample of the BP neural network, taking the characteristic quantity for similar selection as an input vector of the BP neural network, and enabling the electric heating equipment to be in a temperature comfort degree interval [ T ]min,Tmax]The time t capable of being opened or closed is used as an output vector of the BP neural network, a BP neural network prediction model is established, and the response time t of the electric heating equipment is obtained;
evaluating the electric heating load regulation capacity;
according to the response time t of the electric heating equipment obtained in the step 3), evaluating the adjusting capacity of the electric heating equipment according to the formula (2); when the electric heating equipment is in a closed state, the electric heating equipment can be started, and the indoor temperature is controlled from T within T timeroomUp to TmaxFor the up-regulation capability W of electric heating equipmentup(ii) a When the electric heating equipment is in an open state, the electric heating equipment is startedThe time-lapse electric heating equipment can be turned off, and the indoor temperature is controlled from T within T timeroomDown to TminFor the down-regulation of electric heating Wdown;
The invention has the beneficial effects that: the target object is winter heating in northern areas, the factors influencing the adjusting capacity of electric heating equipment are analyzed according to historical data, the similarity between the historical data and the time to be predicted is calculated, the time with similar history is selected as a training sample of a BP neural network, and the temperature interval [ T ] meeting the human body comfort level is evaluatedmin,Tmax]The regulating capacity of the electric heating equipment can comprehensively consider factors influencing the regulating capacity of the electric heating equipment, and the electric heating equipment regulating capacity regulating device has the advantages of being scientific and reasonable, strong in applicability, good in effect and the like.
Drawings
FIG. 1 is a flow chart of a BP neural network electric heating equipment regulation capability evaluation method based on similarity according to the present invention;
FIG. 2 is a graph of the trend of the up-regulation ability and the down-regulation ability as a function of the indoor temperature evaluated by the evaluation method of the present invention;
FIG. 3 is a graph comparing the electric heating plant turndown capability assessment of the present invention with the electric heating plant turndown capability assessment of the thermodynamic model (ETP);
FIG. 4 is a graph comparing the electric heating plant turndown capability assessment of the present invention with the electric heating plant turndown capability assessment of the thermodynamic model (ETP);
fig. 5 is a schematic structural diagram of a modeling system of embodiment 1.
In the figure: the system comprises a cloud computing service unit 1, a centralized controller 2, an electric heating system 3, a wireless current voltmeter 4, a temperature controller 5, a control signal transmitter 6, a control signal encoder 7 and a comprehensive scheduling control unit 8.
Detailed Description
The present invention will be further described with reference to the following examples.
Referring to fig. 1-5, embodiment 1, this embodiment is used for 10.15m for a certain cell2And evaluating the adjusting capacity of the electric heating equipment in the household user room. The electric heating power P is 0.9kW (reduced to 0.089 kW/m)2) Setting the indoor temperature adjustment range [ T ]max,Tmin]Is [20 ℃,23℃ ]]4320 groups of indoor temperature, outdoor temperature and solar irradiance data from 16 days in 2018, 2 months and 18 days in 2018 are selected as historical data (sampling interval is 1min), and the adjusting capacity of the electric heating equipment at 20 moments in 19 days in 2018, 2 months and 19 days is evaluated.
The method specifically comprises the following steps:
1) defining an adjusting capacity index of the electric heating load;
p is the power of the electric heating equipment, and the unit kW is 0.9kW in this embodiment;
t is the time that the electric heating equipment can be turned on or off in the comfort interval of the user, and the unit h is the time;
w is the regulation capacity index of the electric heating equipment, and the unit kWh;
2) calculating the similarity between the historical data and the time to be predicted;
the calculation is as formula (1):
in formula (1): the feature vector at historical i time is Xi=[xi1,xi2,xi3,…,xim],i=1,2,3,…,ximM is the number of the characteristic quantities, and the characteristic vector text of the moment to be predicted is Xj(ii) a Calculating to obtain 160 groups of temperature rise process data and 350 groups of temperature reduction process data;
3) electrical heating load regulation capability assessment
Determining influence factors of similar selection;
determining the kind, position and area S of a building adopting electric heating to 10.15m2Determining a user comfort interval [ Tmin=20℃,Tmax=23℃]Giving includes outdoor temperature, indoor temperatureHeating data for 3 days of history of solar irradiance (16/2/2018-18/2/2018);
(ii) determining a historical feature vector XikAnd the current time feature vector Xjk;
Selecting the indoor temperature T at a certain momentroomInitial temperature T as evaluation time of electric heating load regulation capacityoGiving the outdoor temperature change T in the future period according to the weather forecastoutAnd solar irradiance alpha, and extracting characteristic quantity x of time to be predicted and historical data1For the current time indoor temperature Troom、x2For the outdoor average temperature T in a future periodout,average、x3Is TminOr Tmax、x4Alpha, x as solar irradiance5Tendency of outdoor temperature change, x6Forming a historical characteristic vector X for the power of the equipment PikAnd the current time feature vector Xjk;
The outdoor temperature variation trend x5Setting (2): outdoor temperature rise x5Is 1, outdoor temperature drop x5Is-1, the outdoor temperature is not changed x5Is 0;
thirdly, similar selection is carried out;
substituting the related data obtained in the first step and the second step in the step 3) into a similarity calculation formula (1), calculating the similarity between the historical time and the time to be predicted, and selecting 160 groups of temperature rise process data and 350 groups of temperature reduction process data with high similarity;
establishing a BP neural network prediction model;
taking the data obtained in the third step of the step (3) as a training sample of the BP neural network, taking the characteristic quantity for similar selection as an input vector of the BP neural network, and taking the electric heating equipment in a temperature comfort degree interval (T)min=20℃,Tmax=23℃]The time t capable of being opened or closed is used as an output vector of the BP neural network, the iteration number of the BP neural network is 100, the learning rate is 0.1, the training target is 0.00004, the network is a double hidden layer, the number of nodes is 6 and 2 respectively, a BP neural network prediction model is established, and the response time t of the electric heating equipment is obtained;
evaluating the electric heating load regulation capacity;
according to the response time t of the electric heating equipment obtained in the step 3), evaluating the adjusting capacity of the electric heating equipment according to the formula (2); when the electric heating equipment is in a closed state, the electric heating equipment can be started, and the indoor temperature is controlled from T within T timeroomUp to TmaxFor the up-regulation capability W of electric heating equipmentup(ii) a When the electric heating equipment is in an open state, the electric heating equipment can be closed, and the indoor temperature is controlled from T within T timeroomDown to TminFor the down-regulation of electric heating Wdown;
Comparing the evaluation of the adjustment capability of the electric heating equipment performed in example 1 with the evaluation of the adjustment capability of the electric heating equipment performed by the conventional thermodynamic model (ETP), the comparative results are shown in fig. 3 and 4, and the evaluation process of the adjustment capability of the electric heating equipment performed by the conventional thermodynamic model (ETP) is as follows:
the traditional thermodynamic model can represent the change of indoor temperature by formula (3), and relevant parameters are shown in table 1;
TABLE 1 ETP model parameter values
The error criteria, i.e., the relative Mean Absolute Percent Error (MAPE) and the maximum absolute error (ME), were determined using equations (4) and (5), as shown in Table 2.
ME=max|ti-ti'|(5)
In the formula: t is tiAnd ti' real value and predicted value at the ith moment are respectively; n is the number of predicted times, and n is 20. T isroomIs the indoor temperature, DEG C. C. R, P is equivalent thermal capacitance (J/deg.C), equivalent thermal resistance (deg.C/W), and equipment electric power (W); t isoIs the outdoor ambient temperature, DEG C. t is simulation time; Δ t is the simulation step length, min; k is the electric heating on-off state, and K is 1 when electric heating is opened, and K is 0 when electric heating is closed.
TABLE 2 error analysis and comparison table for two methods
Comparing the average absolute percent error (MAPE) and the maximum absolute error (ME) of the up-regulation capability of the electric heating equipment and the average absolute percent error (MAPE) and the maximum absolute error (ME) of the down-regulation capability of the electric heating equipment in fig. 3, fig. 4 and table 2, it can be seen that the method of the present invention has higher evaluation accuracy than the conventional thermodynamic model (ETP).
The embodiment also illustrates the feasibility and the effectiveness of the BP neural network electric heating equipment regulation capability evaluation method based on the similarity.
The modeling system that this embodiment adopted includes cloud computing service unit 1 and comprehensive dispatch control unit 8, still includes the data acquisition unit, the data acquisition unit with cloud computing service unit 1 radio signal connects for with the data transmission of the voltage, electric current, the temperature of gathering to cloud computing service unit 1, comprehensive dispatch control unit 8 is equallyd divide respectively with data acquisition unit and cloud computing service unit 1 signal connection for receive the calculation result of cloud computing service unit 1 output, and according to calculation result output control signal, control data acquisition unit's temperature controller 5.
The structure of the data acquisition unit is as follows: it includes centralized control ware 2, wireless voltmeter 4, temperature controller 5, control signal encoder 7 and control signal transmitter 6, centralized control ware 2 equally divide respectively with wireless voltmeter 4 temperature controller 5, cloud calculate service unit 1's data calculation part with 6 wireless signal of control signal transmitter connects, control signal encoder 7 equally divide respectively with synthesize dispatch control unit 8 and 6 signal connection of control signal transmitter.
The application software of the embodiment is the prior art.
The embodiment is manufactured by adopting the prior art, and the centralized controller 2, the wireless current voltmeter 4, the temperature controller 5, the control signal encoder 7 and the control signal emitter 6 are all commercial products in the prior art.
The working process of the embodiment is as follows: the temperature controller 5 and the radio current voltmeter 4 transmit the measured temperature, voltage and current data to the centralized controller 2 in the heating room through the zigbee-bee wireless transmission technology, the centralized controller 2 is in signal connection with the cloud computing service unit 1 through the ethernet to transmit the data, the cloud computing service unit 1 stores the data, then the BP neural network electric heating equipment regulation capacity evaluation method based on the similarity is constructed according to the modeling method of the invention, the constructed BP neural network electric heating equipment regulation capacity evaluation method based on the similarity is applied to calculate the received measured data, then the calculation result is transmitted to the comprehensive scheduling control unit 8, the comprehensive scheduling control unit 8 sends out a control command, the control signal is coded by the control signal coder 7, and then the control signal transmitter 6 sends the control signal to the centralized controller 2, the switch of the electric heater is controlled by the action of the integrated controller 2 on the temperature controller 5.
Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art can make modifications and equivalents to the embodiments of the present invention without departing from the spirit and scope of the present invention, which is set forth in the claims of the present application.
Claims (1)
1. A BP neural network electric heating equipment adjusting capacity assessment method based on similarity is characterized in that: firstly, defining the regulation capacity index of the electric heating load, then calculating the similarity between historical data and the moment to be predicted, and evaluating the temperature interval [ T ] meeting the human body comfort levelmin,Tmax]The regulation capacity of the electric heating load comprises the following contents:
1) defining the regulation capacity index of the electric heating load;
p is the power of the electric heating equipment, and the unit is kW;
t is the time that the electric heating equipment can be turned on or off in the comfort interval of the user, and is a unit h;
w is the regulation capacity index of the electric heating equipment, and the unit kWh;
2) calculating the similarity between the historical data and the time to be predicted;
the calculation is as formula (1):
in formula (1): x is the number ofikIs a characteristic quantity, x, corresponding to a time i in the history datajkThe characteristic quantity corresponding to the moment j to be predicted, and m is the number of the characteristic quantities;
3) electrical heating load regulation capability assessment
Determining influence factors of similar selection;
determining the kind, position and area S of a building adopting electric heating, and determining a user comfort interval [ Tmin,Tmax]Providing heating data of history n days including outdoor temperature, indoor temperature and solar irradiance;
determining historical feature vector XikAnd a feature vector X of a time to be predictedjk;
Selecting the indoor temperature T at a certain momentroomInitial temperature T as evaluation time of electric heating load regulation capacityoGiving the outdoor temperature change T in the future period according to the weather forecastoutAnd solar irradiance α, titaniumTaking characteristic quantities of a moment to be predicted and historical data;
historical feature vector Xik=[xi1,xi2,xi3,xi4,xi5,xi](ii) a Wherein x isi1For the current time indoor temperature Troom;xi2Is the average outdoor temperature T in the process of temperature riseout,average;xi3For the temperature control limit, the temperature control upper limit T is taken in the temperature rise processmaxTaking the lower limit T of temperature control in the process of temperature reductionmin;xi4Is solar irradiance α; x is the number ofi5Is the outdoor temperature variation trend; x is the number ofi6Is the device power size P; the number m of the characteristic quantities is 6; the outdoor temperature variation tendency xi5Setting of (1): temperature rise outside the room, xi5Is 1; decrease of outdoor temperature, xi5Is-1; constant outdoor temperature, xi5Is 0;
feature vector X of time to be predictedjk=[xj1,xj2,xj3,xj4,xj5,xj6](ii) a Wherein x isj1For the current time indoor temperature Troom;xj2For the outdoor temperature T at the moment to be predictedout;xj3For the temperature control limit, the temperature control upper limit T is taken in the temperature rise processmaxTaking the lower limit T of temperature control in the process of temperature reductionmjn;xj4Is solar irradiance α; x is the number ofj5Is the outdoor temperature variation trend; x is the number ofj6Is the device power size P; the number m of the characteristic quantities is 6; the outdoor temperature variation trend xj5Setting of (1): temperature rise outside the room, xj5Is 1; decrease of outdoor temperature, xj5Is-1; constant outdoor temperature, xj5Is 0;
thirdly, similar selection is carried out;
substituting the related data obtained in the first step and the second step in the step 3) into a similarity calculation formula (1), calculating the similarity between the historical time and the time to be predicted, and selecting the temperature rise and temperature reduction process data with large similarity;
establishing a BP neural network prediction model;
using the data obtained from the third step of step 3) as a training sample of the BP neural network, and performing similar selection on the characteristicsThe quantity is used as the input vector of BP neural network, and the electric heating equipment is in the temperature comfort degree interval [ Tmin,Tmax]The time t capable of being opened or closed is used as an output vector of the BP neural network, a BP neural network prediction model is established, and the response time t of the electric heating equipment is obtained;
evaluating the electric heating load regulation capacity;
according to the response time t of the electric heating equipment obtained in the step 3), evaluating the adjusting capacity of the electric heating equipment according to the formula (2); when the electric heating equipment is in a closed state, the electric heating equipment can be started, and the indoor temperature is controlled from T within T timeroomUp to TmaxFor the up-regulation capability W of electric heating equipmentup(ii) a When the electric heating equipment is in an open state, the electric heating equipment can be closed, and the indoor temperature is controlled from T within T timeroomDown to TminFor the down-regulation of electric heating Wdown;
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811266385.0A CN109377060B (en) | 2018-10-29 | 2018-10-29 | BP neural network electric heating equipment adjusting capacity evaluation method based on similarity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811266385.0A CN109377060B (en) | 2018-10-29 | 2018-10-29 | BP neural network electric heating equipment adjusting capacity evaluation method based on similarity |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109377060A CN109377060A (en) | 2019-02-22 |
CN109377060B true CN109377060B (en) | 2022-05-24 |
Family
ID=65390303
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811266385.0A Active CN109377060B (en) | 2018-10-29 | 2018-10-29 | BP neural network electric heating equipment adjusting capacity evaluation method based on similarity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109377060B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110007613B (en) * | 2019-04-10 | 2022-04-29 | 北方工业大学 | Warming prediction method and system for heat storage type electric heater and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105631558A (en) * | 2016-03-22 | 2016-06-01 | 国家电网公司 | BP neural network photovoltaic power generation system power prediction method based on similar day |
CN106874581A (en) * | 2016-12-30 | 2017-06-20 | 浙江大学 | A kind of energy consumption of air conditioning system in buildings Forecasting Methodology based on BP neural network model |
CN107528385A (en) * | 2017-06-29 | 2017-12-29 | 国网辽宁省电力有限公司 | A kind of source net lotus control method for coordinating and system based on new energy consumption |
CN108229754A (en) * | 2018-01-31 | 2018-06-29 | 杭州电子科技大学 | Short-term load forecasting method based on similar day segmentation and LM-BP networks |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4525806B2 (en) * | 2008-07-15 | 2010-08-18 | セイコーエプソン株式会社 | Power reception control device, power reception device, and electronic device |
-
2018
- 2018-10-29 CN CN201811266385.0A patent/CN109377060B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105631558A (en) * | 2016-03-22 | 2016-06-01 | 国家电网公司 | BP neural network photovoltaic power generation system power prediction method based on similar day |
CN106874581A (en) * | 2016-12-30 | 2017-06-20 | 浙江大学 | A kind of energy consumption of air conditioning system in buildings Forecasting Methodology based on BP neural network model |
CN107528385A (en) * | 2017-06-29 | 2017-12-29 | 国网辽宁省电力有限公司 | A kind of source net lotus control method for coordinating and system based on new energy consumption |
CN108229754A (en) * | 2018-01-31 | 2018-06-29 | 杭州电子科技大学 | Short-term load forecasting method based on similar day segmentation and LM-BP networks |
Non-Patent Citations (3)
Title |
---|
Electrical energy storage systems in electricity generation:energy policies,innovative technologies,and regulatory regimes;Grigorios L等;《renewable and sustainable energy reviews》;20160430;第56卷;1044-1067页 * |
基于温度预报的户用电采暖负荷可调节能力评估;黄亚峰等;《电网技术》;20180805;第42卷(第5期);2487-2493页 * |
蓄能供热采暖系统负荷预测研究;李腾等;《自动化仪表》;20140720;第35卷(第7期);77-79页 * |
Also Published As
Publication number | Publication date |
---|---|
CN109377060A (en) | 2019-02-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109270842B (en) | Bayesian network-based regional heat supply model prediction control system and method | |
CN111222674A (en) | Short-term photovoltaic power generation capacity prediction method based on long-term and short-term memory neural network | |
Yu et al. | The forecast of the electrical energy generated by photovoltaic systems using neural network method | |
CN106765959A (en) | Heat-air conditioner energy-saving control method based on genetic algorithm and depth B P neural network algorithms | |
CN109492792A (en) | A method of it is predicted based on particle group optimizing wavelet neural network powerline ice-covering | |
CN109284576B (en) | Distributed electric heating load scheduling method based on measured data and modeling system thereof | |
CN115907191B (en) | Self-adaptive building photovoltaic epidermis model prediction control method | |
CN111191854A (en) | Photovoltaic power generation prediction model and method based on linear regression and neural network | |
CN106845663A (en) | A kind of method that heat load prediction is carried out based on numerical weather forecast | |
CN108062025B (en) | Electricity and heat cooperative scheduling system and method based on non-uniform characteristic of terminal heat load | |
Laopaiboon et al. | Hour-ahead solar forecasting program using back propagation artificial neural network | |
CN109377060B (en) | BP neural network electric heating equipment adjusting capacity evaluation method based on similarity | |
CN109583645A (en) | A kind of public building short-term load forecasting method | |
CN111478349B (en) | Power three-phase balance strategy method based on power utilization equipment intelligent network regulation and control Internet of things | |
CN109523134A (en) | A kind of distributing electric heating load time-shift capability quantitative evaluating method and its modeling based on measured data | |
CN116436033A (en) | Temperature control load frequency response control method based on user satisfaction and reinforcement learning | |
CN113361744A (en) | Indoor temperature prediction method based on LSTM algorithm | |
Huang et al. | Model predictive control for energy-efficient buildings: An airport terminal building study | |
CN108303898B (en) | Intelligent scheduling method of novel solar-air energy coupling cold and heat cogeneration system | |
Wei et al. | Deep reinforcement learning for real-time energy management in smart home | |
CN106444388A (en) | Distributed PID type dynamic matrix control method for furnace pressure of coke furnace | |
CN113222231A (en) | Wisdom heating system based on internet of things | |
Özden et al. | Prediction and modelling of energy consumption on temperature control for greenhouses | |
Zhao et al. | Short-term load forecasting based on RBF neural network | |
Yang et al. | Overhead conductor thermal dynamics identification by using echo state networks |
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 |