CN115700648A - Power utilization scheduling system and power utilization scheduling method - Google Patents
Power utilization scheduling system and power utilization scheduling method Download PDFInfo
- Publication number
- CN115700648A CN115700648A CN202111211142.9A CN202111211142A CN115700648A CN 115700648 A CN115700648 A CN 115700648A CN 202111211142 A CN202111211142 A CN 202111211142A CN 115700648 A CN115700648 A CN 115700648A
- Authority
- CN
- China
- Prior art keywords
- parameter
- power
- data
- machines
- load
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
An electricity scheduling system and an electricity scheduling method are provided, wherein the electricity scheduling system comprises a plurality of machines, an intelligent machine upper box and a process planning device. The plurality of machines comprise a plurality of power load data and a plurality of temperature data. The intelligent machine upper box is connected with the machines and used for inputting the electric power load data and the temperature data into the neural network-like model so as to generate an electric power utilization prediction result. The process planning device is used for generating a power utilization schedule of a plurality of machines according to the power utilization prediction result. The implementation can effectively avoid the condition of power consumption overload when a plurality of machines carry out a plurality of processes simultaneously, and further control the power consumption and the power consumption expense of a factory.
Description
Technical Field
The present disclosure relates to a power scheduling system and a power scheduling method, and more particularly, to a power scheduling system and a power scheduling method for predicting power consumption.
Background
In a factory area containing many machines, the power consumption of the equipment of the machine is extremely high, and the power load exceeds the contract demand amount by carelessness. In the past, the power consumption of other equipment is periodically checked or passively closed by relying on manual monitoring, and the benefit is to be enhanced. Traditionally, the production schedule is only passively affected by power overload, and thus, the production quality of the equipment is also affected.
Disclosure of Invention
Some embodiments of the present disclosure relate to a power scheduling system, which includes a plurality of machines, a smart box, and a process planning device. The plurality of machines comprise a plurality of power load data and a plurality of temperature data. The intelligent machine upper box is connected with the machines and used for inputting the electric power load data and the temperature data into the neural network-like model so as to generate an electric power utilization prediction result. The process planning device is used for generating a power utilization schedule of a plurality of machines according to the power utilization prediction result.
In some embodiments, the method further comprises: the order device is used for transmitting a plurality of customer data and a plurality of shipment data to the process planning device, wherein the process planning device is further used for generating the power utilization schedule of the machines according to the power utilization prediction result, the customer data and the shipment data.
In some embodiments, the neural model includes two hidden layers and an output layer.
In some embodiments, the plurality of power load data includes an average load parameter and a peak load parameter, and the plurality of temperature data includes an average temperature parameter, a maximum temperature parameter and a minimum temperature parameter.
In some embodiments, the neural-like model is used to generate a prediction model to generate the power consumption prediction result through the prediction model, and the prediction model is [ predicted power consumption = first parameter × the average load parameter-second parameter × the highest temperature parameter × the peak load parameter-third parameter × the average temperature parameter + fourth parameter × the lowest temperature parameter × the average load parameter + fifth parameter × (the peak load parameter) 1/2 X the average load amount parameter]。
Some embodiments of the present disclosure relate to a power scheduling method, including the following steps. And transmitting a plurality of power load data and a plurality of temperature data of the machines to the intelligent machine upper box by the machines. And inputting the plurality of power load data and the plurality of temperature data into the neural network-like model by the intelligent onboard box so as to generate a power utilization prediction result. The process planning device generates a power schedule for a plurality of machines according to the power prediction result.
In some embodiments, the method further comprises: transmitting a plurality of customer data and a plurality of shipment data from the ordering device to the process planning device; and generating the power utilization schedule of the machines by the process planning device according to the power utilization prediction result, the customer data and the shipment data.
In some embodiments, the method further comprises: generating a predictive model from the neural-like model to generate the electricity usage forecast via the predictive model.
In some embodiments, the prediction model is [ predicted power consumption = first parameter × average load quantity parameter-second parameter × highest temperature parameter × peak load quantity parameter-third parameter × average temperature parameter + fourth parameter × lowest temperature parameter × the average load quantity parameter + fifth parameter × (peak load quantity parameter) 1/2 X average amount of load parameter]。
In some embodiments, the first parameter is 7.21 ≦ 8.81, the second parameter is 18.33 ≦ 22.40, the third parameter is 1.44 ≦ 1.76, the fourth parameter is 1.10 ≦ 1.34, and the fifth parameter is 2.22 ≦ 2.72.
Drawings
The foregoing and other objects, features, advantages and embodiments of the disclosure will be apparent from the following more particular description of the embodiments, as illustrated in the accompanying drawings in which:
fig. 1 is a schematic diagram of a power scheduling system according to some embodiments of the disclosure;
FIG. 2 is a flowchart of a power scheduling method according to some embodiments of the disclosure;
FIG. 3 is a diagram illustrating a neural network-like model according to some embodiments of the present disclosure; and
fig. 4 is a schematic diagram of power usage scheduling according to some embodiments of the present disclosure.
[ notation ] to show
100 power consumption scheduling system
110A,110B and 110C machine
130 intelligent machine upper box
150 process planning device
170 ordering device
200 power consumption scheduling method
S210, S230, S250 step
300-class neural network model
I is a vector
H1, H2 hidden layer
OP output layer
B11, B2 vector
L1, L2: vector
F11, F12, F2 function
S power utilization prediction result
400 power usage scheduling
Detailed Description
The term "coupled," as used herein, may also refer to "electrically coupled," and the term "connected" may also refer to "electrically connected. "coupled" and "connected" may also mean that two or more elements co-operate or interact with each other.
Refer to fig. 1. Fig. 1 is a schematic diagram of a power scheduling system 100 according to some embodiments of the disclosure.
Referring to fig. 1, the power scheduling system 100 includes a plurality of machines 110A to 110C, an intelligent equipment box 130, a process planning apparatus 150, and an order apparatus 170. In the connection relationship, the smart machine top box 130 is connected to the plurality of tools 110A to 110C, the process planning device 150 is connected to the machine top box, and the ordering device 170 is connected to the process planning device 150.
The power scheduling system 100 shown in fig. 1 is for illustration only, and the embodiments are not limited thereto. For example, in some other embodiments, the process planning apparatus 150 is connected to a plurality of smart top boxes, which are connected to a plurality of tools, respectively. Various configurations of the power usage scheduling system 100 are within the scope of the present disclosure.
Taking a dyeing and finishing factory as an example, the machines 110A to 110C in fig. 1 may be, for example, a loom, a dyeing machine, a setting machine, a dewatering machine, a spreading machine, a cloth inspecting machine, a cloth slitting machine, an automatic dyeing auxiliary metering system, an air conditioner compressor, a cloth rolling machine, a waste water washing processing device, a steam boiler, a single-needle flat sewing machine, a factory temperature control device, and the like.
The detailed operation of the power utilization scheduling system 100 will be described with reference to fig. 2.
Fig. 2 is a flowchart of a power scheduling method 200 according to some embodiments of the disclosure. The power scheduling method 200 can be applied to the power scheduling system 100 shown in fig. 1. Please refer to fig. 1-2 together.
In step S210, a plurality of power load data and a plurality of temperature data of the plurality of machines are transmitted to the smart top box. In some embodiments, in step S210, the machines 110A to 110C shown in fig. 1 transmit the respective power load data and the temperature data to the smart top box 130.
In some embodiments, the plurality of power load data includes an average load parameter and a peak load parameter, and the plurality of temperature data includes an average temperature parameter, a maximum temperature parameter and a minimum temperature parameter.
In step S230, a plurality of power load data and a plurality of temperature data are input into the neural network model to generate a power consumption prediction result. In some embodiments, step S230 is performed by the smart phone top box 130 as shown in fig. 1.
Please refer to fig. 3. Fig. 3 is a diagram illustrating a neural network-like model 300 according to some embodiments of the disclosure. As shown in fig. 3, the neural network-like model 300 includes two hidden layers H1 and H2 and an output layer OP.
Specifically, the input layer includes a vector I composed of a plurality of power load data and a plurality of temperature data. The vector B11 is generated according to the vector I, and the vector B11 is calculated by the function F11 of the hidden layer H1 to generate the vector L1. After the vector L1 is input to the hidden layer H2, the vector L2 is generated after calculation by the function F12 of the hidden layer H2. Then, a vector B2 is generated according to the vectors L1 and L2, and the vector B2 generates the electrical prediction result S after passing through the function F2 of the output layer OP.
In some embodiments, the transfer functions of the functions F11 and F12 are tangent doubly-curved transfer functions, and the function F2 is a linear transfer function. In some embodiments, the number of nodes of the hidden layer H1 is 12, and the number of nodes of the hidden layer H2 is 12. In some embodiments, the network training method of the neural network-like model 300 is an LM algorithm (levenberg-marquardt algorithm) combined with a belie (Bayesian) structure of the BasDavid Mackay, and the maximum number of cycles of network training is 6000.
In some embodiments, the output layer OP of the neural network-like model 300 generates a prediction model, where the prediction model is predicted power consumption = first parameter × the average load parameter-second parameter × the highest temperature parameter × the peak load parameter-third parameter × the average temperature parameter + fourth parameter × the lowest temperature parameter × the average load parameter + fifth parameter × (the peak load parameter) 1/2 X the average load amount parameter.
In some embodiments, the first parameter, the second parameter, the third parameter, the fourth parameter and the fifth parameter are generated by the neural network model 300.
In some embodiments, the electricity consumption prediction result S in fig. 3 is generated according to a prediction model to predict the electricity consumption in each time interval.
In some embodiments, the first parameter is 7.21 ≦ 8.81, the second parameter is 18.33 ≦ 22.40, the third parameter is 1.44 ≦ 1.76, the fourth parameter is 1.10 ≦ 1.34, and the fifth parameter is 2.22 ≦ 2.72. In a preferred embodiment, the first parameter is 8.0136, the second parameter is 20.363, the third parameter is 1.6, the fourth parameter is 1.22, and the fifth parameter is 2.471.
Please refer back to fig. 2. In step S250, a power schedule of a plurality of machines is generated according to the power prediction result. In some embodiments, step S250 is performed by the process planning apparatus 150 as shown in fig. 1.
In some embodiments, step S250 further includes transmitting the customer data and the shipment data from the ordering apparatus 170 of FIG. 1 to the process planning apparatus 150. The process planning device 150 generates a power schedule for the machines 110A-110C according to the power forecast, the customer data, and the shipment data.
Please refer to fig. 4. Fig. 4 is a schematic diagram of a power schedule 400 according to some embodiments of the present disclosure. As illustrated in fig. 4, the power schedule 400 includes the operating times for processes 1-3 for the machines 110A,110B, and 110C of fig. 1 at 00. The power utilization schedule 400 shown in fig. 4 is for illustration purposes only, and the embodiments of the present invention are not limited thereto.
In some embodiments, the process planning apparatus 150 may provide the optimized power schedule 400 to a manufacturer for reference, thereby reducing the time required to modify the power schedule 400. In the power schedule 400, the process planning apparatus 150 can classify the processes 1 to 3 according to the amount of power consumption. For example, the process planning apparatus 150 may classify the processes 1 to 3 into three colors of red, yellow and green according to their power consumption levels. Thus, the process personnel can adjust the sequence of processes 1 to 3 according to the classification of the power schedule 400. Under the condition of considering the waiting time and the delivery time of the manufacturing process, the manufacturing personnel can properly adjust the sequence or the overlapping time sequence of the manufacturing processes 1 to 3 so as to avoid the situation of high power utilization load and thereby improve the reliability of the power system or reduce the related power fee. In some embodiments, the process planning apparatus 150 may also record and analyze the adjusted power schedule 400 to provide more accurate recommendations at the next time.
In some embodiments, the power scheduling system 100 and the power scheduling method 200 are applicable to a dyeing and finishing factory. However, the embodiments of the present disclosure are not limited thereto.
In summary, the present disclosure provides a power consumption scheduling system and a power consumption scheduling method, wherein power capacity data and temperature data of a plurality of machines are collected and integrated through an intelligent machine top box, power consumption prediction results of the plurality of machines are analyzed and predicted through a neural network model, and then the power consumption prediction results, customer data and shipment data are integrated by a process planning device to generate a power consumption schedule of the plurality of machines. After referring to the power utilization schedule, the process personnel can more appropriately adjust the operation sequence or the time sequence of a plurality of processes on a plurality of machines. Therefore, the condition of power consumption overload when a plurality of machines carry out a plurality of processes at the same time can be effectively avoided, and the power consumption expense of a factory are further controlled.
Various functional elements have been disclosed herein. It will be apparent to one of ordinary skill in the art that functional elements may be implemented using circuits (whether dedicated circuits or general circuits that operate under the control of one or more processors and coded instructions).
Although the present disclosure has been described with reference to particular embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present disclosure, and therefore the scope of the present disclosure should be limited only by the terms of the appended claims.
Claims (10)
1. A power usage scheduling system, comprising:
a plurality of machines, including a plurality of power load data and a plurality of temperature data;
the intelligent machine upper box is connected with the plurality of machines and used for inputting the plurality of power load data and the plurality of temperature data into a neural network-like model so as to generate a power utilization prediction result; and
and the process planning device is used for generating the power utilization schedule of the plurality of machines according to the power utilization prediction result.
2. The power consumption scheduling system of claim 1, further comprising:
an ordering device for transmitting a plurality of customer data and a plurality of shipment data to the process planning device,
the process planning device is further configured to generate the power utilization schedule of the machines according to the power utilization prediction result, the customer data and the shipment data.
3. The power usage scheduling system of claim 1, wherein the neural-like model includes two hidden layers and an output layer.
4. The power consumption scheduling system of claim 1, wherein the plurality of power load data comprises an average load parameter and a peak load parameter, and wherein the plurality of temperature data comprises an average temperature parameter, a maximum temperature parameter, and a minimum temperature parameter.
5. The power consumption scheduling system of claim 4, wherein the neural model is configured to generate a prediction model to generate the power consumption prediction result via the prediction model, and the prediction model is [ predicted power consumption = first parameter x the average load amount parameter-second parameter x the highest temperature parameter x the peak load amount parameter-third parameter x the average temperature parameter + fourth parameter x the lowest temperature parameter x the average load amount parameter + fifth parameter x (the peak load amount parameter) 1/2 X the average load amount parameter]。
6. A method for scheduling power usage, comprising:
transmitting a plurality of power load data and a plurality of temperature data of a plurality of machines to an intelligent machine upper box by the plurality of machines;
inputting the plurality of power load data and the plurality of temperature data into a neural network-like model by the smart onboard box to generate a power utilization prediction result; and
and generating the power utilization schedule of the plurality of machines by a process planning device according to the power utilization prediction result.
7. The electricity scheduling method of claim 6, further comprising:
transmitting a plurality of customer data and a plurality of shipment data to the process planning device by the ordering device; and
generating, by the process planning device, the power utilization schedule for the machines according to the power utilization prediction result, the customer data, and the shipment data.
8. The power usage scheduling method of claim 6, further comprising:
generating a predictive model from the neural-like model to generate the electricity usage forecast via the predictive model.
9. The power usage scheduling method of claim 8, wherein the prediction model is [ predicted power usage = first parameter x average load parameter-second parameter x maximum temperature parameter x peak load parameter-third parameter x average temperature parameter + fourth parameter x minimum temperature parameter x the average load parameter + fifth parameter x (peak load parameter) 1/2 X average amount of load parameter]。
10. The power usage scheduling method of claim 9, wherein the first parameter is 7.21 ≦ 8.81, the second parameter is 18.33 ≦ 22.40, the third parameter is 1.76, the fourth parameter is 1.34, the fifth parameter is 2.22 ≦ 2.72.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW110127766A TWI831033B (en) | 2021-07-28 | 2021-07-28 | Electricity usage scheduling system and electricity usage scheduling method |
| TW110127766 | 2021-07-28 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115700648A true CN115700648A (en) | 2023-02-07 |
Family
ID=85121060
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111211142.9A Pending CN115700648A (en) | 2021-07-28 | 2021-10-18 | Power utilization scheduling system and power utilization scheduling method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115700648A (en) |
| TW (1) | TWI831033B (en) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101383023B (en) * | 2008-10-22 | 2011-04-06 | 西安交通大学 | Neural network short-term electric load prediction based on sample dynamic organization and temperature compensation |
| CN101782258B (en) * | 2009-01-19 | 2012-08-15 | 中华电信股份有限公司 | Energy-saving method for air conditioner |
| TWI468952B (en) * | 2011-11-15 | 2015-01-11 | Univ Kun Shan | Short-term load forecasting method for smart grid |
| TWI584113B (en) * | 2012-05-03 | 2017-05-21 | 東海大學 | Smart energy-saving control system |
| US9911163B2 (en) * | 2013-03-15 | 2018-03-06 | Rockwell Automation Technologies, Inc. | Systems and methods for determining energy information using an organizational model of an industrial automation system |
| CN111047094A (en) * | 2019-12-12 | 2020-04-21 | 国网浙江省电力有限公司 | Meter reading data anomaly analysis method based on deep learning algorithm |
| CN112215426A (en) * | 2020-10-16 | 2021-01-12 | 国网山东省电力公司信息通信公司 | Short-term power load prediction method |
-
2021
- 2021-07-28 TW TW110127766A patent/TWI831033B/en active
- 2021-10-18 CN CN202111211142.9A patent/CN115700648A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| TW202305722A (en) | 2023-02-01 |
| TWI831033B (en) | 2024-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Optimization strategy based on deep reinforcement learning for home energy management | |
| US11334036B2 (en) | Power grid aware machine learning device | |
| US11747776B2 (en) | Adaptive training and deployment of single device and clustered device fault detection models for connected equipment | |
| Xu et al. | Multi-energy scheduling of an industrial integrated energy system by reinforcement learning-based differential evolution | |
| Wang et al. | Stochastic optimization for energy management in power systems with multiple microgrids | |
| CN104424512A (en) | Operation plan decision method and operation plan decision system | |
| CN104049600B (en) | With the system and method for the energy information renewal the value of the confidence related to automated system | |
| Mohagheghi et al. | Intelligent demand response scheme for energy management of industrial systems | |
| CN104049595B (en) | The system and method for energy information is determined with the tissue model of industrial automation system | |
| CN110135064A (en) | A kind of generator rear bearing temperature fault prediction technique, system and controller | |
| Nazemi et al. | A mixed-integer distributionally robust chance-constrained model for optimal topology control in power grids with uncertain renewables | |
| Mostafa et al. | A review on energy management systems | |
| CN114527714A (en) | Workshop dynamic scheduling method based on digital twin and disturbance monitoring | |
| Perroy et al. | Provision of frequency containment reserve through large industrial end-users pooling | |
| Nezhad et al. | Joint peak clipping and load scheduling based on user behavior monitoring in an IoT platform | |
| Li et al. | Multiple degradation-driven preventive maintenance policy for serial-parallel multi-station manufacturing systems | |
| Rao et al. | Demand response for renewable generation in an IOT based intelligent smart energy management system | |
| Zhuang et al. | Data-driven reserve allocation with frequency security constraint considering inverter air conditioners | |
| Lin et al. | Real-time charging scheduling of automated guided vehicles in cyber-physical smart factories using feature-based reinforcement learning | |
| CN115700648A (en) | Power utilization scheduling system and power utilization scheduling method | |
| Kumar et al. | Optimal load scheduling for industrial load-Analysis for a generalized industrial load model | |
| Heider et al. | Smart Grid Power Management Interface for Use of short-term Flexibility | |
| CN115864459A (en) | Network-building type energy storage capacity configuration method and device combined with robust optimization | |
| CN111191967B (en) | Energy supply data processing method, system, energy supply control device and storage medium | |
| CN113131487A (en) | Transformer area identification method and device based on voltage regulation pattern, storage medium and electronic equipment |
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 |