KR20220090202A - System for performing optimal managing of complex equipments based thermal energy demanding forcasting - Google Patents

Abstract

The present invention relates to a complex facility optimal operation system based on thermal energy demand prediction, providing a user interface for providing an optimal complex facility operation service based on thermal energy demand forecasting, and controlling operation of field facilities according to an operation schedule performance, collecting information according to the operation of the on-site equipment, performing daily heat demand forecasting based on monthly heat demand forecasting, and performing production optimization to calculate the daily production target amount for each on-site equipment based on the daily heat demand forecasting amount And, it relates to an invention for performing optimization of thermal energy consumption by calculating an operation schedule for each on-site facility based on a target daily production amount.

Description

SYSTEM FOR PERFORMING OPTIMAL MANAGING OF COMPLEX EQUIPMENTS BASED THERMAL ENERGY DEMANDING FORCASTING

The present invention relates to a technology for a complex facility optimal operation system and method based on thermal energy demand prediction.

The most important goal of the energy efficiency project (MEG-EMS, Micro Energy Grid - Energy Management System) for businesses that consumes heat and electricity is the M&V, Measurement and Verification (M&V) management of the efficient operation of energy-consuming facilities. It is aimed at maximizing the efficiency of investment in heating and cooling and hot water supply facilities.

Basically, most of the heat data is managed as a monthly gas bill, so it is difficult to understand the real-time heat consumption situation, and it is almost impossible to flexibly control the facility in response to changes in site-specific conditions (temperature, visitors, load, etc.) to be.

In addition, after facility managers in the building set facility operation control values (set temperature, etc.) for each season, most of the results result in uniform facility operation for each season.

Accordingly, there is a need for a system capable of effectively managing energy while flexibly responding to changes in customers' various operating environments, for example, seasons, days of the week, temperature, holidays, and the like.

An object of the present invention is to provide an optimal operation system for a complex facility based on a thermal energy demand prediction that can maximize the investment efficiency of the facility.

The present inventor's optimal operation system for complex facilities based on thermal energy demand prediction,

a service provider providing a user interface for providing an optimal operation service for a complex facility based on a prediction of thermal energy demand;

a real-time processing unit configured to perform operation control for on-site equipment according to an operation schedule and collect information according to operation of the on-site equipment; and

The daily heat demand forecast is performed based on the monthly heat demand forecast to calculate the daily heat demand forecast, and after calculating the daily production capacity of a plurality of field facilities capable of producing heat, the daily production capacity of the plurality of field facilities and A production optimization process of calculating a daily production target amount for each of the plurality of on-site facilities based on the predicted daily heat demand, and a daily production capacity of each of the plurality of on-site facilities for the plurality of on-site facilities to produce heat of a daily production target amount for each facility and an optimal operation management unit for controlling a consumption optimization process of calculating an operation schedule applied to each of the plurality of field facilities based on the .

The present invention provides an effect of maximizing the efficiency of investment in heating/cooling/hot water supply facilities for businesses that consume a lot of heat and electric energy by controlling the high-efficiency facilities to be operated in a cost-effective time.

1 is a diagram illustrating a monthly gas consumption prediction graph according to an embodiment of the present invention.
2 is a diagram illustrating a concept of a day characteristic weight according to an embodiment of the present invention.
3 is a diagram illustrating a daily heat consumption prediction graph according to an embodiment of the present invention.
4 is a diagram illustrating a heat consumption prediction graph for each time period per year according to an embodiment of the present invention.
5 is a diagram illustrating an example of a production optimization process according to an embodiment of the present invention.
6 is a diagram illustrating an example of a consumption optimization process according to an embodiment of the present invention.
7 is a diagram schematically illustrating an environment in which the complex facility optimal operating system according to an embodiment of the present invention is used.
FIG. 8 is a diagram illustrating a detailed configuration of the optimal driving management unit shown in FIG. 7 .
9 is a diagram illustrating a detailed configuration of the heat demand prediction unit shown in FIG. 8 .
FIG. 10 is a diagram illustrating a detailed configuration of the driving scheduling unit shown in FIG. 8 .

Hereinafter, with reference to the accompanying drawings, the embodiments of the present invention will be described in detail so that those of ordinary skill in the art to which the present invention pertains can easily implement them. However, the present invention may be embodied in several different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part "includes" a certain element, it means that other elements may be further included, rather than excluding other elements, unless otherwise stated. In addition, terms such as “…unit”, “…group”, and “module” described in the specification mean a unit that processes at least one function or operation, which may be implemented as hardware or software or a combination of hardware and software. have.

Hereinafter, a description will be given of the complex facility optimal operation system 10 based on the prediction of thermal energy demand according to an embodiment of the present invention with reference to the drawings.

First, the optimal complex facility operating system 10 based on thermal energy demand prediction according to an embodiment of the present invention may be operated by dividing it into two parts: a heat demand prediction part and a demand forecast-based facility operation scheduling part.

First, the heat demand forecasting part will be described.

Heat demand forecasting is based on monthly heat consumption (kcal, N㎥) data, and the daily consumption is estimated by reflecting the temperature change weight for each site and the day-of-week characteristic weight. Apply to perform daily heat demand forecast for each site.

In addition, the daily heat demand forecast data is fixed for each site, flow energy characteristics, and daily flow coefficients for each time period are applied to predict the heat consumption for each time period.

To predict such heat demand, first, as in [Equation 1], a gas consumption baseline model Y is established.

[Equation 1]

는 월 냉방 계수이며,

은 월 난방 계수이고,

는 평일 계수이며,

는 휴일 계수이고, CDD(Cooling Degree Days)는 냉방도일이고, HDD(Heating Degree Days)는 난방도일이며,

은 월의 평일(weekdays)의 수이고,

는 월의 휴일(weekends)의 수이다. 여기서, 냉난방도일은 실내의 표준온도(18.3℃)와 1일 평균 외기 온도와의 차를 냉난방 기간 동안 합산한 것으로, 기온이 18.3℃보다 높을 경우 온도에서 18.3℃를 뺀 값을 CDD라고 하고 이하의 경우 18.3℃에서 기온을 뺀 값을 HDD로 한다. 이에 대해서는 이미 잘 알려져 있으므로 구체적인 설명은 생략한다.where Y is the predicted monthly gas consumption (Nm3),

is the monthly cooling coefficient,

is the monthly heating coefficient,

is the weekday coefficient,

is the holiday coefficient, CDD (Cooling Degree Days) is cooling degree days, HDD (Heating Degree Days) is heating degree days,

is the number of weekdays in the month,

is the number of weekends in the month. Here, the heating and cooling degree is the sum of the difference between the indoor standard temperature (18.3℃) and the daily average outdoor temperature during the heating/cooling period. In this case, the HDD is the value obtained by subtracting the temperature from 18.3℃. Since this is already well known, a detailed description thereof will be omitted.

As a result of verifying the above baseline model Y based on two-year monthly thermal energy consumption data of a specific general hospital, it was shown as shown in FIG. 1 , and a basic model almost similar to the actual monthly gas consumption can be created.

Next, in estimating the daily heat consumption, it is obtained by multiplying Equation 1 above by the temperature change weight and the day characteristic weight.

) 를 구할 수 있으며 [수학식 2]와 같이 표현할 수 있다.The temperature change weight is the value obtained by dividing the sum of the cooling rate (CDD) and heating index (HDD) for a specific day by the total sum of the cooling rate and heating index for the month.

) can be obtained and can be expressed as in [Equation 2].

[Equation 2]

Here, CDDa is the cooling index of a specific day a in a month, and HDDa is the heating index of a specific day a in a month. Therefore, the denominator represents the sum of the monthly heating and cooling indices.

)를 적용하여 추정되는 일일 소비 추정량(

)는 다음의 [수학식 3]과 같이 표현될 수 있다.These daily temperature change weights and day-of-week characteristic weights (

) to the estimated daily consumption (

) can be expressed as the following [Equation 3].

[Equation 3]

은 위의 수학식 1에 기반하여 산출되는 월별 소비량을 나타낸다.here,

represents the monthly consumption calculated based on Equation 1 above.

As such, the daily consumption estimate may be estimated by multiplying the monthly consumption by the daily temperature change weight and the day-of-week characteristic weight.

On the other hand, the day characteristic weight is a coefficient obtained by calculating the weight of the day of the week by month based on the daily electricity consumption for two years, assuming that the heat consumption pattern is similar to the electricity consumption pattern as a characteristic of each industry.

In the case of a specific general hospital that is a simulation target, as shown in FIG. 2, it is classified into Monday/Tuesday-Friday/Sat/Sun, and the usage on other days of the week is relatively indicated based on the usage on Monday, and each classification has 8 values. (2 years, 8 weeks per month).

In the embodiment of the present invention, the average of eight values in one category is adopted and the daily heat consumption is estimated by multiplying the relative weight of the day of the week by the monthly consumption together with the daily temperature weight.

Next, based on the daily consumption estimate calculated as in Equation 3, the daily demand forecasting model is developed by analyzing the variables of cooling degree day, heating degree day, day characteristics of Monday/holiday/Friday/Saturday, consumption a day before, and consumption a week ago [Mathematics] Equation 4].

[Equation 4]

는 일 냉방계수이고,

은 일 난방계수이며,

는 월요일 계수이고,

는 금요일 계수이며,

는 토요일 계수이고,

는 휴일(일요일, 공휴일) 계수이며,

는 하루 전 열 소비량 계수이고,

은 일주일 전 열 소비량 계수이며,

는 월/금/토/일 또는 공휴일로써 해당 요일일 경우만 1의 값을 가지고 그렇지 않은 경우에는 0의 값을 가지고,

는 하루 전 일일 수비 추정량 혹은 하루 전 일일 소비량(kcal)이며,

는 일주일 전 일일 소비 추정량 혹은 일주일 전 일일 소비량(kcal)이다.here,

is the working cooling coefficient,

is the daily heating coefficient,

is the Monday coefficient,

is the Friday coefficient,

is the Saturday coefficient,

is the holiday (Sunday, public holiday) coefficient,

is the coefficient of heat consumption a day before,

is the coefficient of heat consumption a week ago,

is Monday/Friday/Saturday/Sunday or a public holiday and has a value of 1 only if it is the day of the week, and has a value of 0 otherwise,

is the daily defense estimate of the day before or daily consumption (kcal) the day before,

is the estimated daily consumption a week ago or daily consumption in kcal a week ago.

을 제외한 변수에는 0이 들어가고 해당 요일 변수는 값 1을 갖는다. With respect to Equation 4, for example, if the week to be predicted is Monday

0 is entered in variables except for , and the corresponding day variable has a value of 1.

Then, the coefficient values obtained through the regression analysis are substituted into Equation (4).

As a result of regression analysis based on specific general hospital data for verification, the coefficients of determination had a confidence level of about 95%.

The regression analysis results of the specific general hospital can be shown in Table 1 as follows.

[Table 1]

When the coefficients obtained through the above table are applied to Equation 4, the daily consumption estimate obtained can be expressed as in Equation 5 below.

[Equation 5]

=688631.8397054*CDD + 230283.639946574*HDD + 643426.722692934*

+ 77832.4794508482*

+ (-943365.972701576)*

+ (-597161.056890592)*

+ 0.632561424613761*

+ 0.0242916407593964*

=688631.8397054*CDD + 230283.639946574*HDD + 643426.722692934*

+77832.4794508482*

+ (-943365.972701576)*

+ (-597161.056890592)*

+ 0.632561424613761*

+ 0.0242916407593964*

3 is a diagram showing the result of visualization of Equation 5.

)을 에너지를 고정적으로 사용하는 면적과 시간대별 에너지 소비량 가중치를 곱하여 시간대 별 열 소비 추정량(

)을 추정하는 모델을 [수학식 6]과 같이 만들었다. On the other hand, as the last stage of demand forecasting, the daily consumption estimator (

(

) was created as in [Equation 6].

[Equation 6]

는 시간대별 열 소비 추정량(kcal)이고,

는 일일 소비 추정량(kcal)이며,

는 고정 비율이고,

는 요일별 시간대 유동계수를 나타낸다.here,

is the estimate of heat consumption over time (kcal),

is the daily consumption estimate (kcal),

is a fixed ratio,

is the flow coefficient for each day of the week.

In Equation 6, the fixed ratio refers to the ratio of the area that uses energy in a fixed manner among the total area of the building, and the flow ratio refers to the remainder obtained by subtracting the fixed ratio from 1.

In the case of a specific general hospital, the sum of the outpatient area and the inpatient room area was assumed to be the total area, the fixed ratio was calculated as the area of the inpatient room to the total area, and the floating ratio was calculated as the outpatient area.

The ratio of the fixed and flow ratio was 28.6% : 71.4%.

와 마찬가지로 요일별 열 소비 패턴은 전기 소비패턴과 유사하다고 가정하여, 요일별(월/화~금/토/휴일 또는 일)로 하루(24시간) 전력 소비량 대비 요일별 시간대 전력 사용량 비율을 요일 별 시간대 유동 계수로 정의하였다. 그리고 1시간당 8개의 요일 별 시간대 유동계수 값의 평균을 수학식 6에서 사용하였다The flow coefficient for each day of the week is the day-of-week characteristic weight (

Similarly, assuming that the heat consumption pattern by day of the week is similar to the electricity consumption pattern, the ratio of power consumption per day (24 hours) to power consumption per day (Mon/Tuesday-Friday/Sat/Holiday or Sun) per day (Mon/Tuesday-Friday/Sat/Holiday or Sun) is calculated as the flow coefficient for each day of the week. was defined as And the average of the flow coefficient values for each day of the week for 8 hours per hour was used in Equation 6

The heat demand prediction results for each time period are two years of monthly heat energy consumption data of a general hospital.

Next, the demand forecast-based facility operation scheduling part will be described.

The demand forecast-based facility operation scheduling part is divided into a production optimization stage and a consumption optimization stage. In the production optimization stage, the daily production target for each facility is selected based on the seasonal efficiency of the facility, production fuel price, rate system, daily production capacity, etc. , in the consumption optimization stage, the operation schedule for each facility for each time zone is created for the daily production target in consideration of the preheating time required for each facility, the production unit price for each time period, and the operating cost.

As above, the factors to be considered in terms of heat production by facility (bold text in Table 2) and the order of policies to be given to each facility are as follows, based on the forecast amount of heat demand by time in terms of consumption as described above in [Table 2].

[Table 2]

For example, if a site has two types of heat demand, heating and cooling, first estimate the daily heat demand for each.

If there is a heat pump that uses electricity and an absorption type cold/hot water heater that uses gas, the equipment with high efficiency is selected after comparing the seasonal efficiencies of each facility.

*Next, after comparing the production fuel (late-night electricity/general electricity or LNG gas, etc.) of the relevant facility by unit price, calculate the daily heat production capacity considering the capacity and number of facilities, and select the high-efficiency facility calculated above. Set the daily production target for each facility as the first priority.

In order to optimize consumption by time of day, the operating time (including preheating time) for each facility that meets the daily production target is determined, and after considering the production unit price and operating cost for each time period, an optimal facility operation schedule policy is created for each time period.

In the case of a specific general hospital, since the power peak is in the afternoon (14-17) in the summer, it is recommended that operation be performed between 7 and 13:00. It can be created like 6.

Referring to FIG. 5 , as a result of forecasting the heating and cooling demand, a demand of 12,558,251 kcal was predicted as a daily heating demand forecast.

First, as facilities, there are a heat pump and a water heater, and the efficiency of the heat pump is 2.7, which is higher than that of the cold/hot water machine, 0.85, so the heat pump is selected as the first priority facility.

Next, in the case of the production fuel unit cost of each facility, the heat pump is 30.7 won/Mcal based on late-night electricity and the cold/hot water unit is 1133 won/Mcal based on the LNG gas.

After that, the daily production capacity for each facility is calculated. It is assumed that there are 8 heat pumps and the total capacity is 151 kWh, and that there is one 320RT class of hot and cold water heaters.

*First, the 1st priority facility, the cold/hot water unit, is 151kWh * 24h * 2.7 * 860(kcal//kWh) = 8,414,920 kcal of daily production capacity, and the 2nd priority facility, the cold/hot water machine, is 320RT * 24h * 0.85 * 3,024(kcal/RT) ) = 19,740,672 daily production capacity of kacl is calculated.

Next, since the daily heating demand forecast is 12,558,251 kcal, if the first-priority heat pump is operated at full capacity for 24 hours, a total of 8,414,920 kcal can be produced. Since the remaining amount produced by the heat pump from the total demand forecast amount is 4,143,323 kcal, only this amount becomes the daily production target amount produced by the cold/hot water machine, which is the second priority facility.

In this way, it is possible to optimally set a target daily production amount for each facility based on the efficiency and production capacity of each facility.

Next, referring to FIG. 6 , if the target daily production amount for each facility is calculated as shown in FIG. 5 , the operation time for each facility is first calculated in the consumption optimization step.

In the case of the heat pump, which is the first priority facility, since the daily production capacity is set as the daily production target amount, the daily operation time is 24 hours. can be That is, since the production capacity per hour of the cold/hot water machine is 320RT * 0.85 * 3024 = 822,528 kcal, in order to produce the daily target amount of 4,143,323 kcal, 4,143,323/822,528 = 5.04h of daily operation time is calculated.

Next, since a preheating time is required for each facility, the total daily operating time for each facility is calculated in consideration of the preheating time. In the case of the heat pump, which is the first priority facility, since it operates all day, there is no need for preheating time. Accordingly, the daily total operation time of the heat pump, which is the first priority facility, is 24 hours, and in the case of the cold/hot water machine, which is the second priority facility, 5.54 hours including 0.5 hours, which is the preheating time, is set as the total daily operation time.

Next, the production unit price for each time period is calculated for each facility.

In the case of the heat pump, which is the first priority facility, it is 623 won/kWh from 23:00 to 09:00, but it is 884 won/kWh from 10:00 to 22:00, which is the other time.

In addition, it can be seen that the production unit price for each time period of the cold/hot water machine, which is the second priority facility, is 843 won/N㎥ regardless of the time on the basis of LNG.

Next, it is necessary to calculate the operating cost for each time period compared to the operating time for each facility.

In the case of the heat pump, which is the first priority facility, by operating it in full for 24 hours, the previously calculated production unit price for each time period is used as it is. Should be. At this time, consideration should be given to the summer peak time of 14:00 to 17:00 and the hourly unit price. For example, the unit price per hour is 63.1 won from 23:00 to 09:00, 109.2 won from 9 to 10, 12:00 to 13:00 and 17:00 to 23:00, 10 to 12, 13 From 17:00 to 17:00 can be confirmed as 166.7 won.

Next, with respect to the daily production target for each facility, an operation schedule for each time zone is prepared for each facility in consideration of the previously calculated daily operation time, production unit price for each time period, and operation cost.

First, in the case of the heat pump, which is the first priority facility, since it is fully operated for 24 hours, its operation schedule can be set from 0 to 23:49.

Since the cold/hot water heater, which is the second priority facility, should be scheduled with an operating time of 5.54 hours, it is possible to schedule the operation from 07:00 to 12:30 based on the above considerations.

Next, with reference to the drawings for the complex facility optimal operation system based on the thermal energy demand prediction according to the embodiment of the present invention as described above in detail.

7 is a diagram schematically illustrating an environment in which the complex facility optimal operating system 10 according to an embodiment of the present invention is used.

As shown in FIG. 7 , the complex facility optimal operation system 10 according to an embodiment of the present invention includes a service providing unit 100 , a database 200 , a real-time processing unit 300 , and an optimal operation management unit 400 . do.

The service providing unit 100 is provided with a user interface for providing the optimal operation service of the complex facility based on the thermal energy demand prediction according to an embodiment of the present invention. The user may be provided with the optimal operation service of the complex facility to be managed through the service providing unit 100 .

The database 200 stores operation information for each facility and various data collected from the external server 700 . Such data may include electricity usage data, production unit price data by time period, weather information, and the like.

The real-time processing unit 300 controls the on-site equipment 500 controlled through the gateway 600 according to the optimal operation scheduling set by the optimal operation management unit 400 , for example, facilities such as a heat pump and a water heater.

In addition, the real-time processing unit 300 collects various information detected from the field facility 500 and stores it in the database 200 . Such information includes operation information, production information, and the like.

As described with reference to FIGS. 1 to 6 , the optimal operation management unit 400 performs daily heat demand prediction, and performs management for optimizing production and consumption for each facility based on the predicted daily heat demand amount. In particular, the optimal operation management unit 400 creates a schedule for optimal operation for each facility, and controls the real-time processing unit 300 according to the created operation schedule to control the operation of the field facility 500 .

FIG. 8 is a diagram illustrating a detailed configuration of the optimal driving management unit 400 illustrated in FIG. 7 .

As shown in FIG. 8 , the optimal driving management unit 400 includes a heat demand prediction unit 410 , a driving scheduling unit 420 , a verification and updating unit 430 , and a settlement unit 440 .

The heat demand prediction unit 410 predicts the monthly heat consumption based on the monthly heat consumption data stored in the database 200, and predicts the daily heat consumption by applying the temperature change weight and the day characteristic weight to the monthly heat consumption. After that, the heat consumption by time period is predicted by applying the energy consumption weight for each time period and the area in which energy is used in a fixed manner.

The operation scheduling unit 420 applies the daily heat demand prediction amount predicted by the heat demand prediction unit 410 and the efficiency and daily production capacity for each field facility 500 to calculate the daily production target amount for each facility; The consumption optimization process is performed by calculating the total daily operating hours for each facility, and creating an operating schedule for each facility for the daily production target amount by referring to the production unit price and operating cost for each time period.

The verification and update unit 430 prepares an initial operation schedule for each facility by the heat demand prediction unit 410 and the operation scheduling unit 420 and then uses the real-time processing unit 300 to perform real-time operation of the field facility 500 in real time. The operation schedule is updated according to the obtained information, and the operation of the field facility 500 is controlled according to the updated operation schedule.

The settlement unit 440 settles charges generated due to the operation of the field facility 500 according to the operation schedule created by the operation scheduling unit 420 .

FIG. 9 is a diagram illustrating a detailed configuration of the heat demand prediction unit 410 shown in FIG. 8 .

As shown in FIG. 9 , the heat demand prediction unit 410 includes a monthly heat consumption prediction unit 411 , a daily heat consumption prediction unit 413 , a time-based heat consumption prediction unit 415 , and a prediction control unit 417 . include

The monthly heat consumption prediction unit 411 calculates a monthly heat consumption predicted amount by predicting the monthly heat consumption based on [Equation 1] based on the monthly heat consumption data stored in the database 200 . For a detailed description thereof, refer to the above description.

The daily heat consumption prediction unit 413 applies the temperature change weight and the day characteristic weight calculated based on [Equation 2] to the monthly heat consumption prediction amount calculated by the monthly heat consumption prediction unit 411 [Equation 3] ] to estimate the daily heat consumption to calculate the daily heat consumption forecast. Also refer to the above description for a detailed description thereof.

The heat consumption prediction unit 415 for each time period is based on the predicted daily heat consumption calculated by the daily heat consumption prediction unit 413, and applies the energy consumption weight for each time area and the area that uses energy in a fixed manner. to calculate the heat consumption by time period.

The prediction control unit 417 controls the monthly heat consumption prediction unit 411 , the daily heat consumption prediction unit 413 , and the time-specific heat consumption prediction unit 415 to predict the heat consumption of the object. At this time, during the initial prediction, the prediction control unit 417 performs the heat consumption prediction based on the monthly heat consumption data stored in the database 200 and using various initial variables, but during the operation of the field facility 500 . By updating and applying various variables based on the data collected by the real-time processing unit 300 , the control is performed so that real-time heat consumption prediction by the operation of the field facility 500 is possible.

FIG. 10 is a diagram illustrating a detailed configuration of the driving scheduling unit 420 shown in FIG. 8 .

As shown in FIG. 10 , the operation scheduling unit 420 includes a production optimization unit 421 and a consumption optimization unit 423 .

The production optimization unit 421 calculates a daily production target amount for each production-optimized field facility 500 based on the daily heat demand prediction amount calculated by the heat demand prediction unit 410 .

The production optimization unit 421 includes an efficiency comparison unit 4211 , a production possible amount calculation unit 4213 , a target production amount calculation unit 4215 , and a production amount control unit 4217 .

The efficiency comparison unit 4211 compares the seasonal efficiencies of the field facilities 500 and then selects the facilities in the order of the facilities with high efficiency.

The production capacity calculation unit 4213 calculates the total amount that can be produced per day for each on-site facility 500 .

The production target amount calculation unit 4215 includes the daily heat demand prediction amount calculated by the heat demand prediction unit 410 , the order of facilities selected by the efficiency comparison unit 4211 , and the production capacity calculated by the production capacity calculation unit 4213 . Based on the total amount, the daily production target amount for each field facility 500 is calculated.

The production control unit 4217 controls the efficiency comparison unit 4211 , the production possible amount calculation unit 4213 , and the production target amount calculation unit 4215 to calculate a target daily production amount for each field facility 500 .

Next, the consumption optimization unit 423 creates an operation schedule for each field facility 500 that is optimized for consumption based on the daily target amount calculated by the production optimization unit 421 .

The consumption optimization unit 423 includes a driving time calculation unit 4231 , a driving cost calculation unit 4233 , a driving schedule creation unit 4235 , and a scheduling control unit 4237 .

The operating time calculation unit 4231 calculates the daily operating time based on the target daily production amount calculated by the production optimization unit 421 and the preheating time and production capacity for each on-site facility 500 .

The operating cost calculation unit 4233 calculates the operating cost for each time period based on the production unit price for each time period.

The operation schedule creation unit 4235 creates an operation schedule for each field facility 500 based on the daily operation time calculated by the operation time calculation unit 4231 and the operation cost calculated by the operation cost calculation unit 4233 . .

The scheduling control unit 4237 controls the operation time calculation unit 4231 , the operation cost calculation unit 4233 , and the operation schedule creation unit 4235 to create an operation schedule for each field facility 500 .

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto. is within the scope of the right.

Claims (5)

In the optimal operation system for complex facilities based on thermal energy demand prediction,
a service provider that provides a user interface for providing an optimal operation service for a complex facility based on a prediction of thermal energy demand;
a real-time processing unit configured to perform operation control of on-site equipment according to an operation schedule and collect information according to the operation of the on-site equipment;
Daily heat demand forecasting is performed based on the monthly heat demand forecast to calculate the daily heat demand forecast, and after calculating the daily production capacity of a plurality of field facilities capable of producing heat, the daily production capacity of the plurality of field facilities and A production optimization process of calculating a daily production target amount for each of the plurality of field facilities based on the daily heat demand forecast amount, and a daily production capacity of each of the plurality of field facilities for the plurality of field facilities to produce heat of a daily production target amount for each facility and an optimal operation management unit for controlling a consumption optimization process of calculating an operation schedule applied to each of the plurality of field facilities based on
The optimal operation management unit compares the efficiencies of the plurality of field facilities and, in the order of the high-efficiency facilities, produces the next high-efficiency facility when the total productionable amount of the high-efficiency facilities is insufficient for the daily heat demand forecast amount The optimal operation system for complex facilities based on thermal energy demand prediction, characterized in that the daily production target amount for each of the plurality of field facilities is calculated in the form of supplementing the shortfall in the daily heat demand forecast with a possible total amount.
According to claim 1,
The optimal operation management unit,
Predict monthly heat consumption based on monthly heat consumption data, predict daily heat consumption by applying temperature change weights and day-of-week characteristic weights to the monthly heat consumption. a heat demand prediction unit that predicts heat consumption by time period by applying;
A production optimization process of calculating the daily production target amount for each field facility by applying the daily heat demand consumption predicted by the heat demand prediction unit, the efficiency and the daily production capacity for each field facility, and the total daily operation time for each field facility Composite based on thermal energy demand forecasting, comprising: an operation scheduling unit that calculates and performs a consumption optimization process of creating an operation schedule for each on-site facility for the daily production target amount with reference to the production unit price and operation cost by time period Equipment optimal operating system.
3. The method of claim 2,
After the initial operation schedule for each field facility is created by the heat demand prediction unit and the operation scheduling unit, the operation schedule is updated according to the information obtained in real time during operation of the field facility through the real-time processing unit, and the operation schedule is updated a verification and update unit for controlling the operation of the on-site equipment according to the
Composite facility optimal operation system based on thermal energy demand prediction, characterized in that it further comprises a settlement unit that settles charges generated due to the operation of the on-site facility 500 according to the operation schedule created by the operation scheduling unit 420 .
3. The method of claim 2,
The heat demand prediction unit,
a monthly heat consumption prediction unit for predicting the monthly heat consumption based on the monthly heat consumption data and calculating the monthly heat consumption;
a daily heat consumption prediction unit calculating daily heat consumption by predicting daily heat consumption by applying a temperature change weight and a day characteristic weight to the monthly heat consumption calculated by the monthly heat consumption prediction unit;
Based on the daily heat consumption calculated by the daily heat consumption prediction unit, heat consumption by time period is calculated by predicting heat consumption by time period by applying the weight of energy consumption by time and area in which energy is fixedly used. predictor;
Optimal operation of complex facilities based on thermal energy demand prediction, characterized in that it comprises a prediction control unit for controlling the heat consumption prediction of the object by controlling the monthly heat consumption prediction unit, the daily heat consumption prediction unit, and the time period heat consumption prediction unit system.
3. The method of claim 2,
The driving scheduling unit,
a production optimization unit configured to perform a production optimization process of calculating a target daily production amount for each on-site facility based on the daily heat demand calculated by the heat demand prediction unit;
and a consumption optimization unit performing a consumption optimization process of creating an operation schedule for each on-site facility based on the target daily production amount calculated by the production optimization unit.

Images