A method for deducing adjustable potential of industrial equipment under time-of-use price incentive

Abstract

The application discloses a kind of adjustable potential deduction method of industrial equipment under the consideration of time-of-use price incentive, comprising the following steps: S1: establishing industrial equipment model and analysis;S2: clustering analysis to industrial user;S3: to the load regulation constraint analysis of electrical equipment;S4: analysis time-of-use input window and corresponding cost;S5: establish adjustable deduction model.The application adopts the above-mentioned adjustable potential deduction method of industrial equipment under the consideration of time-of-use price incentive, which helps to realize the automated query of demand-side resource adjustable capacity, improve the load management capability of new power system, and promote the construction of adjustable resource pool.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power system demand measurement, in particular to a method for deducing adjustable potential of industrial equipment under consideration of time-of-use price incentive. BACKGROUND

[0002] The interaction ability of the current power grid for adjustable load needs to rely on data for analysis. Most of the existing analysis methods adopt a combination of mathematical and physical models, but due to the difference in the behavior of the corresponding demand side resource users, their interaction ability is often different. The traditional mathematical model analysis method is difficult to accurately depict the adjustable interaction behavior of the demand side resource compared with the data-driven analysis method, so it is necessary to explore and research the analysis method combined with data-driven. SUMMARY

[0003] The purpose of the present application is to provide a method for deducing the adjustable potential of industrial equipment under consideration of time-of-use price incentive, which helps to realize the automatic query of the adjustable ability of demand side resources, improves the load management ability of the new power system, and promotes the construction of adjustable resource pool.

[0004] To achieve the above purpose, the present application provides a method for deducing the adjustable potential of industrial equipment under consideration of time-of-use price incentive, comprising the following steps:

[0005] S1: establishing an industrial equipment model and analyzing;

[0006] S2: clustering analysis of industrial users;

[0007] S3: analysis of load regulation constraints of electrical equipment;

[0008] S4: analysis of time-of-use input window and corresponding cost;

[0009] S5: establishing an adjustable deduction model.

[0010] Preferably, in step S1, the industrial equipment is divided into main production equipment and auxiliary production equipment, wherein the main production equipment is continuous type impact equipment load and indirect type impact equipment load, and models are established and analyzed respectively;

[0011] Among them, the continuous type impact equipment takes electric arc furnace type equipment as an example, analyzes its working characteristics and working process, and models it, and the expression is:

[0012] (1)

[0013] In the formula, P eaf (t) is the power of electric arc furnace type equipment, t eafon is the power-on time of electric arc furnace type equipment, t eafoff is the power-off time of electric arc furnace type equipment, Peeaf the rated power of the electric arc furnace type equipment, Δt up the time required for the electric arc furnace type equipment to reach the rated power from being powered on, Δt down the time for the electric arc furnace type equipment to reach 0 power from being powered off, ρ(t) is the random power fluctuation of the equipment in steady state operation;

[0014] Taking the motor type equipment as an example, the working characteristics and working process of the indirect type impact equipment are analyzed, and the expression is:

[0015] (2)

[0016] In the formula, P rm (t) is the power of the motor, t rmoff is the motor off time, t rmon is the motor on time, P erm is the rated power of the motor, Δt rm is the time required for the motor to reach the rated power from starting to work;

[0017] For auxiliary production equipment, the working characteristics and working process are analyzed, and the expression is:

[0018] (3)

[0019] In the formula, P s (t) is the power of the auxiliary production equipment at time t, P sn is the rated power of the auxiliary production equipment, t on , t off are the on and off times of the auxiliary production equipment, t1 and t2 are the power drop and climb times of the auxiliary production equipment, k1 and k2 are the power drop and climb speeds of the auxiliary production equipment, P s1 is the adjusted power.

[0020] Preferably, in step S2, the K-means algorithm is used for secondary clustering of the three types of electricity, the clustering center is three, and the median is selected as the representative of industrial electricity for analysis. The main production equipment electricity proportion in the first and second electricity stages is about 80%, the auxiliary production equipment electricity proportion is about 10%, and the remaining 10% is other electricity such as employee life. In the third electricity stage, the main production equipment is all closed for maintenance, the auxiliary production equipment is ventilated by the fan for safety operation, and the factory electricity is mainly life electricity.

[0021] Preferably, in step S3, the industrial user participates in the different directions of upward or downward adjustment of the power grid, and the economic cost model is divided into downward adjustment cost and upward adjustment cost, and the variables are defined as follows:

[0022] The cost model for down-regulation is shown as follows:

[0023] (4)

[0024] where L is the down-regulation loss, R is the product sale price, O is the product production cost, and Q is the unit production power consumption. d p f p

[0025] The cost model for up-regulation is shown as follows:

[0026] (5)

[0027] where L is the up-regulation loss, P is the net electricity price, P is the self-provided power plant power generation cost. u e c

[0028] Preferably, in step S3, the device regulation power constraints are established from the following five aspects according to the order and flow of the production devices, and the constraint equations are shown as follows:

[0029] The power consumption device m working time constraint is

[0030] (6)

[0031] where M is all devices, T is the device working time, b is the total time period required to complete the production task, t is the minimum working time, t is the maximum working time, and μ is the state coefficient of the device m at k time. m，b m,min m,max m,k

[0032] The device m non-interruptibility constraint is

[0033] (7)

[0034] where K is all scheduling time periods.

[0035] The preceding device constraint is

[0036] (8)

[0037] The device strong correlation constraint is

[0038] (9)

[0039] The device synchronization constraint is

[0040] ​​​​​​​​​​​ (10)

[0041] μ m,k is the state coefficient of the device m at time k, is the state coefficient of the main production device at time t.

[0042] Preferably, in step S4, the enhanced regulation cost is fitted with the load regulation to obtain the time-division input window and the corresponding cost, and a sliding window of the corresponding regulation period is introduced. Equation (11) is the sliding window input of the low valley period,

[0043] (11)

[0044] wherein W1 is the input window corresponding to the period; y 1 is the power consumption of the device in the low valley period, corresponding to all load data within 15 days; y 2 is the cost of upward regulation within 15 days corresponding to the load.

[0045] Preferably, in step S5, based on the industrial device model analysis and the device regulation constraint, an industrial user adjustable potential deduction model is established, as shown below:

[0046] The forget gate determines the selection of the previous state, and the formula is as follows:

[0047] (12)

[0048] The cell determines the input proportion of the previous state and the input proportion of the current state, and determines the output,

[0049] (13)

[0050] The output gate determines the proportion, which is defined as follows:

[0051] (14)

[0052] The output is determined by the cell output and the output gate determined proportion output result,

[0053] (15)

[0054] wherein f t is the output value of the forget gate at time t, C t is the cell output at time t, σ is the Sigmoid function, W f is the weight of the forget gate, h t-1 is the power consumption signal of the device in a short time at time t-1, b f is the transformation bias, C t-1 is the short-time power consumption information of the power consumption device in the cell at time t-1； i t a variable for determining the new information retention degree at time t; new input device power consumption information in the unit core at time t.

[0055] Therefore, the application adopts the above-mentioned industrial equipment adjustable potential deduction method considering the time-of-use price incentive to obtain the industrial enterprise adjustable potential result in the time-of-use period, clearly defines the customer side adjustable capacity, realizes the accurate analysis of the interactive capacity based on data driving, and improves the perception capacity of the power grid end.

[0056] The technical solutions of the application will be further described in detail below with reference to the drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 is a adjustable potential deduction process schematic diagram according to the embodiment of the application. DETAILED DESCRIPTION

[0058] The technical solutions of the application will be further described in detail below with reference to the drawings and examples.

[0059] Unless otherwise defined, the technical terms or scientific terms used in the present application shall have the usual meanings understood by those skilled in the art to which the present application belongs.

[0060] It is apparent for those skilled in the art that the present application is not limited to the details of the above-mentioned exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, the embodiments should be regarded as exemplary and non-limiting, and the scope of the present application is defined by the appended claims rather than the above description, and therefore all changes falling within the meaning and scope of the equivalent elements of the claims should be included in the present application, and any reference signs in the claims should not be regarded as limiting the involved claims.

[0061] In addition, it should be understood that although the present specification is described in terms of embodiments, each embodiment does not contain only one independent technical solution, and the description manner of the specification is only for clarity, and those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be properly combined to form other embodiments which can be understood by those skilled in the art. These other embodiments are also covered by the protection scope of the present application.

[0062] It should also be understood that the above-described specific embodiments are merely intended for explaining the present application, and the protection scope of the present application is not limited thereto, and any person skilled in the art can make equivalent replacements or changes to the technical solutions and the inventive concept of the present application within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application.

[0063] Techniques, methods, and apparatus known to those of ordinary skill in the relevant art can not be discussed in detail herein, but should be considered as part of the specification.

[0064] The disclosures of the prior art documents cited in the specification of the present application are all incorporated herein by reference, and thus are part of the disclosure of the present application.

[0065] Embodiment one

[0066] As shown in the figure, the present application provides a method for deriving the adjustable potential of industrial equipment under time-of-use price incentives, which derives the adjustable capacity of industrial users, introduces a deep learning model for calculation, and the model takes into account the time-of-use price signal and the power generation of the factory self-provided power plant. After the model calculation result meets the load constraint condition of the industrial equipment, the potential derivation result is output. Finally, the model result is the adjustable potential result of the industrial enterprise under the time-of-use period, which clearly defines the adjustable capacity of the customer side, realizes the accurate analysis of the interactive capacity based on data driving, and improves the perception ability of the power grid end.

[0067] First, the industrial equipment model is established and analyzed. The industrial equipment is divided into main production equipment and auxiliary production equipment, wherein the main production equipment is continuous impact equipment load and indirect impact equipment load, and models are established and analyzed respectively. The continuous impact equipment takes electric arc furnace type equipment as an example, analyzes its working characteristics and working process, and models it, and the expression is:

[0068] (1)

[0069] In the formula, P eaf (t) is the power of electric arc furnace type equipment, t eafon is the power-on time of electric arc furnace type equipment, t eafoff is the power-off time of electric arc furnace type equipment, P eeaf is the rated power of electric arc furnace type equipment, Δt up is the time required for electric arc furnace type equipment to reach rated power from power-on, Δt down is the time required for electric arc furnace type equipment to reach power 0 from power-off, and ρ(t) is the random power fluctuation of the equipment in steady-state operation.

[0070] The working characteristics and working process of the indirect impact equipment, such as the motor type equipment, are analyzed, and the motor type equipment is modeled, and the expression is:

[0071] (2)

[0072] In the formula, P rm (t) is the motor power, t rmoff is the motor closing time, t rmon is the motor opening time, P erm is the rated power of the motor, and Δt rm is the time required for the motor to start working to reach the rated power.

[0073] The auxiliary production equipment is the equipment that assists the main production equipment to work, and the work of the auxiliary production equipment is to complete the tasks of material handling, exhaust, etc. The load of the auxiliary production equipment accounts for about 10% of the power consumption of the factory. The auxiliary production equipment is modeled, and the expression is:

[0074] (3)

[0075] In the formula, P s (t) is the power of the auxiliary production equipment at time t, P sn is the rated power of the auxiliary production equipment, t on and t off are the opening and closing times of the auxiliary production equipment, t1 and t2 are the power drop and climb time of the auxiliary production equipment, k1 and k2 are the power drop and climb speed of the auxiliary production equipment, and P s1 is the adjusted power.

[0076] Secondly, the industrial user clustering analysis is performed. The industrial electricity data is classified according to the average load value. Due to the difference in order quantity and maintenance requirements, the factory electricity stage can be roughly divided into three stages, namely, order quantity guarantee stage, order balance production stage, and equipment maintenance stage. If the order is normal, the factory electricity stage is divided into order quantity guarantee stage and order balance production stage; if the order is urgent, the factory will process with full power, and the electricity of the order quantity guarantee stage will continue to produce. Therefore, the order quantity guarantee stage is defined as a class of electricity stage, the order balance production stage is defined as a class of electricity stage, and the equipment maintenance stage is defined as a class of electricity stage.

[0077] The K-means algorithm is used to cluster the three types of electricity consumption, and the cluster center is set to three. The median is selected as the representative of industrial electricity consumption for analysis. The first type of electricity consumption phase must ensure the stable production of various industrial products to achieve the specified production capacity. The second type of electricity consumption phase is used to produce surplus industrial products. This phase has a large adjustment potential and can implement intelligent adjustment of factory electricity consumption to reduce the pressure on the power grid while ensuring factory production capacity. The main production equipment electricity consumption ratio in the first and second types of electricity consumption phases is about 80%, the auxiliary production equipment electricity consumption ratio is about 10%, and the remaining 10% is employee life and other electricity consumption. In the third type of electricity consumption phase, the main production equipment is completely closed for maintenance, and the auxiliary production equipment is operated safely with fan ventilation. The factory electricity consumption is mainly for life electricity consumption.

[0078] Third, the load regulation constraint analysis of electricity consumption equipment. The economic cost model is divided into downward adjustment cost and upward adjustment cost according to the different directions of industrial users participating in the upward or downward adjustment of the power grid. The variables are defined as follows:

[0079] The downward adjustment cost model is shown below:

[0080] (4)

[0081] In the formula, L d is the downward adjustment loss, R p is the product sales price, O f is the product production cost, and Q p is the unit output power consumption.

[0082] The cost model of upward adjustment is shown below:

[0083] (5)

[0084] In the formula, L u is the upward adjustment loss, P e is the net electricity price, and P c is the self-provided power plant generation cost.

[0085] There is a mutual dependence relationship between industrial equipment. The main production equipment and auxiliary production equipment follow strict order and process. Therefore, the constraint equation for the transfer of production tasks in the factory is established. According to the order and process between production equipment, the equipment regulation power constraints are established from the following five aspects, and the constraint equation is shown below:

[0086] The working time constraint of electricity consumption equipment m is

[0087] (6)

[0088] In the formula, M is the total equipment, T m,bis the working time of the device, b is the total time period required to complete the production task, t m,min is the minimum working time, t m,max is the maximum working time;

[0089] The device m non-interruptibility constraint is

[0090] (7)

[0091] Where K is the total scheduling period;

[0092] The front-end device constraint is

[0093] (8)

[0094] The device strong association constraint is

[0095] (9)

[0096] The device synchronization constraint is

[0097] (10)

[0098] μ m,k is the state coefficient of device m at time k. When the device is running, , is 1, otherwise 0. Let the main production device state coefficient be , the auxiliary production device state coefficient be , and be set, which can ensure that when the main production device regulates the load, the auxiliary production device adjusts along with the regulation direction of the main production device.

[0099] Fourth, analyze the time period input window and the corresponding cost. The fitting of the enhanced regulation cost and the load regulation obtains the time period input window and the corresponding cost, and then introduces the sliding window of the corresponding regulation period. Equation (11) is the low valley period sliding window input, whose length is the data point length within 15 days in the corresponding period, corresponding to the period of sufficient production into the warehouse. By inputting the data in the form of a sliding window, the regulation cost and the device power consumption can be unified, which is convenient for the TCN to extract the time sequence features for model training.

[0100] (11)

[0101] In the formula, W1 is the corresponding period input window; y 1 is the device power consumption in the low valley period, corresponding to all load data within 15 days; y 2 is the upward regulation cost within 15 days corresponding to the load.

[0102] Peak and off-peak hours are treated the same. Replace the basic electricity price with the time-of-use electricity price, calculate the upward and downward regulation costs of the corresponding period, and input them into the model. The regulation range under the time-of-use electricity price can be obtained.

[0103] Fifth, establish an adjustable inference model. Based on the analysis of industrial equipment models and equipment regulation constraints, an industrial user adjustable potential inference model is established. The industrial user equipment electricity data is used as the driving force, and the time-of-use electricity price factor is added to evaluate the equipment regulation potential of industrial users in different time periods. As follows:

[0104] The forget gate decides the selection of the previous state, and the formula is as follows:

[0105] (12)

[0106] The cell decides the input proportion of the previous state and the input proportion of the current state, and decides the output,

[0107] (13)

[0108] i t Direct control The proportion of the cell entering the unit, i t is expressed as:

[0109] (14)

[0110] The proportion of the current input saved to the cell is decided, is expressed as:

[0111] (15)

[0112] The output gate decides the proportion, which is defined as,

[0113] (16)

[0114] The output is determined by the cell output and the output gate decision proportion output result,

[0115] (17)

[0116] In the formula, f t is the output value of the forget gate at time t, Ct is the output of the cell at time t, σ is the Sigmoid function, W f is the weight of the forget gate, h t-1 is the electricity signal of the equipment in a short time at time t-1, b f is the transformation bias, C t-1 is the short-time electricity information of the electricity equipment in the cell at time t-1, i tA variable for determining the new information retention degree at time t, The device power information newly input in the unit core at time t.

[0117] Finally, the industrial device power consumption data is calculated by the model, and the regulation cost under the time-of-use price incentive is combined. The model can automatically learn the relationship between the cost and the load transfer according to the height of the regulation cost, and obtain the optimization result of the potential, so as to achieve the purpose of analyzing the time-of-use regulation potential of the industrial user, and obtain the analysis result of the adjustable potential of the industrial user under the time-of-use period. At the same time, the present application will evaluate the adjustable potential on the basis of load aggregation. The user who meets the industrial regulation demand can evaluate the adjustable potential under the time-of-use period.

[0118] Therefore, the industrial device adjustable potential deduction method considering the time-of-use price incentive has the advantages of helping to realize the automatic query of the adjustable capacity of the demand side resource, improving the load management capability of the new power system, and promoting the construction of the adjustable resource pool.

[0119] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application and not to limit them, although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that: it can still modify or equivalently replace the technical solutions of the present application, and these modifications or equivalent replacements cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present application.

Claims

1. A method for extrapolating the adjustability potential of industrial equipment considering time-of-use electricity pricing incentives, characterized in that: Includes the following steps: S1: Establish and analyze industrial equipment models; S2: Cluster analysis of industrial users; S3: Constraint analysis of load regulation for electrical equipment. In step S3, industrial users participate in different directions of upward or downward regulation of the power grid. The economic cost model is divided into downward regulation cost and upward regulation cost, and the variables are defined as follows: The downward adjustment cost model is shown below: （1）； In the formula, L d To adjust the loss downwards, R p For the product price, O f Q represents the product manufacturing cost. p Electricity consumption per unit of output; The upward adjustment cost model is shown below: （2）； In the formula, L u To adjust the loss upwards, P e For net electricity price, P c Cost of generating electricity from a self-owned power plant; Based on the sequential and process-oriented nature of the production equipment, power control constraints for equipment will be established from the following five aspects, as shown in the following constraint formulas: The operating time constraint for electrical equipment m is as follows: （3）； In the formula, M represents all devices, and T m，b Let b be the equipment operating time, b be the total time required to complete the production task, and t be the total operating time. m,min To minimize the working time, t m,max For the longest working time, μ m,k Let m be the state coefficient of device m at time k; The uninterruptibility constraint of device m is （4）； Where K represents the total scheduling period; Pre-processor constraints are （5）； Strong device correlation constraint is （6）； Equipment synchronization constraints are （7）； μ m,k Let m be the state coefficient of device m at time k. The state coefficients of the main production equipment at time t; S4: Analyze the time-segmented input window and corresponding cost. In step S4, the time-segmented input window and corresponding cost are obtained by fitting the enhanced control cost and load control. Then, a sliding window for the corresponding control period is introduced. Equation (8) is the sliding window input for the off-peak period. （8）； In the formula, W1 is the input window for the corresponding time period; y 1 This represents the power consumption of equipment during off-peak hours, corresponding to all load data over a 15-day period; y 2 The cost of adjusting upwards within 15 days corresponding to the load; S5: Establish an adjustable simulation model. In step S5, based on the industrial equipment model analysis and equipment control constraints, an adjustable potential simulation model for industrial users is established, as shown below: The forget gate determines whether to discard a previous state, using the following formula: （9）； The unit determines the input ratio of the previous state to the current state, and thus determines the output. （10）； The output gate determines the ratio, as defined below. （11）； The output is proportional to the unit output and the output gate. （12）； In the formula, f t Let C be the output value of the forget gate at time t. t Let W be the cell output at time t, σ be the Sigmoid function, and W be the output of the cell at time t. f h represents the weight of the forget gate. t-1 b represents the power consumption signal of the device during a short period of time at time t-1. f To transform paranoia, C t-1 For short-term power consumption information of electrical equipment in the unit at time t-1 ； i t Let t be the variable that determines the degree to which new information is retained. The newly input device power consumption information in the unit core at time t.

2. The method for extrapolating the adjustability potential of industrial equipment considering time-of-use electricity pricing incentives as described in claim 1, characterized in that: In step S1, industrial equipment is divided into main production equipment and auxiliary production equipment. The main production equipment is divided into continuous impact equipment load and indirect impact equipment load, and models are established for analysis respectively. Taking electric arc furnaces as an example, the working characteristics and workflow of continuous impact equipment are analyzed, and a model is created, with the expression as follows: （13）； In the formula, P eaf (t) represents the power of electric arc furnace equipment, t eafon For electric arc furnace equipment, t eafoff For electric arc furnace equipment, P is the time of power failure. eeaf For electric arc furnace equipment, Δt up Δt is the time required for electric arc furnace equipment to reach its rated power after being powered on. down Let ρ(t) be the time it takes for an electric arc furnace to reach zero power after a power outage, and let ρ(t) be the random power fluctuation of the equipment during steady-state operation. For auxiliary production equipment, analyze its working characteristics and workflow, and model it. The expression is: （14）； In the formula, P s (t) represents the power of the auxiliary production equipment at time t, P sn To support the rated power of production equipment, t on t off t1 and t2 represent the start-up and shut-down times of the auxiliary production equipment, respectively; t1 and t2 represent the power decrease and ramp-up times of the auxiliary production equipment, respectively; k1 and k2 represent the ramp-up speeds of the auxiliary production equipment's power decrease and increase, respectively; P s1 To adjust the power.

3. The method for extrapolating the adjustability potential of industrial equipment considering time-of-use electricity pricing incentives as described in claim 1, characterized in that: In step S2, the K-means algorithm is used to perform secondary clustering on the three types of electricity consumption, with the cluster center set to three. The median is then selected as the representative of industrial electricity consumption for analysis. In the first and second types of electricity consumption, the main production equipment accounts for about 80% of the electricity consumption, the auxiliary production equipment accounts for about 10%, and the remaining 10% is other electricity consumption. In the third type of electricity consumption, all the main production equipment is shut down for maintenance, and the auxiliary production equipment is ventilated safely. The factory's electricity consumption is mainly for residential use.

Images