Optimized scheduling method and system in demand response and electronic equipment

Abstract

The invention relates to the technical field of electric power, and provides an optimal scheduling method and system in demand response, and electronic equipment, and the method comprises the steps: obtaining historical data, inputting the historical data into a pre-constructed load prediction model, and obtaining the total load power in a to-be-scheduled time period; determining constraint conditions of schedulable load power in the total load power; the total load power serves as the input, under the constraint of the constraint condition, the value of the schedulable load power when the target function obtains the minimum value is determined, and the output of the target function is the cost in the demand response process; and determining an optimal scheduling scheme based on the numerical value of the schedulable load power and a pre-constructed schedulable load power model. The task issuing method and device are used for overcoming the defect that in the prior art, demand response is prone to causing the polarization phenomenon of poor response completion degree or resource waste, and the supply and demand balance of a power system is affected, and task issuing can be achieved more reasonably and accurately.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to an optimization scheduling method and system, and electronic equipment in demand response. Background Art

[0002] Renewable energy has gradually become the mainstream source of energy in the power system. However, the power generation of new energy is intermittent, random, and volatile, which can easily lead to imbalances in supply and demand over time. In addition, the power generation of new energy may not match the electricity consumption season, resulting in difficulties in seasonal power balance.

[0003] Demand Response (DR) refers to the short-term behavior of electricity users changing their inherent habitual electricity consumption patterns to respond to electricity supply by reducing or shifting the electricity load during a certain period of time after receiving a direct compensation notice of induced load reduction or a signal of electricity price increase from the power supplier when the wholesale electricity market price rises or the system reliability is threatened, thereby ensuring the stability of the power grid and suppressing the increase in electricity prices.

[0004] However, the issuance of demand response tasks in related technologies is highly subjective and cannot be accurately implemented, which can easily lead to polarization phenomena such as poor response completion or waste of resources, affecting the supply and demand balance of the power system. Summary of the invention

[0005] The present invention provides an optimization scheduling method and system, and electronic equipment in demand response, which are used to solve the defect that demand response in the prior art easily causes polarization phenomenon of poor response completion or waste of resources, affecting the supply and demand balance of the power system. The solution of the present application can realize task issuance more reasonably and accurately.

[0006] The present invention provides an optimization scheduling method in demand response, comprising:

[0007] Obtain historical data, input the historical data into a pre-built load forecasting model, and obtain the total load power in the time period to be scheduled, where the historical data is the load power data before the time period to be scheduled;

[0008] Determine the constraints of dispatchable load power in the total load power;

[0009] Taking the total load power as input, under the constraints of the constraints, determine the value of the dispatchable load power when the objective function achieves the minimum value. The objective function is pre-constructed, and the output of the objective function is the cost in the demand response process;

[0010] Based on the numerical value of the dispatchable load power and the pre-built dispatchable load power model, an optimal dispatching plan is determined.

[0011] According to the optimal dispatching method in demand response provided by the present invention, the method for constructing a load forecasting model includes:

[0012] Build an extreme learning machine model;

[0013] The load power data before the scheduling period is used as the training set data, and the extreme learning machine model is trained based on the training set data to obtain the load forecasting model.

[0014] According to the optimal dispatching method in demand response provided by the present invention, the method for constructing a load forecasting model further includes:

[0015] Based on the goose optimization algorithm, the total load power in the scheduling time period predicted by the extreme learning machine model is optimized.

[0016] According to the optimization scheduling method in demand response provided by the present invention, the dispatchable load power includes interruptible load power;

[0017] The dispatchable load power model includes the interruptible load power model, which is expressed by the following formula:

[0018]

[0019] in is the load at time t, is the minimum load, is the maximum load, is the start time of the operation, is the end time of the operation, For the running time, is the minimum runtime.

[0020] According to the optimization dispatching method in demand response provided by the present invention, the dispatchable load power includes transferable load power;

[0021] The dispatchable load power model includes the transferable load power model, which is expressed by the following formula:

[0022]

[0023] in is the load at time t, is the minimum load, is the maximum load, is the start time of the operation, is the end time of the operation, Q a The required power consumption.

[0024] According to the optimal dispatching method in demand response provided by the present invention, determining the constraint conditions of the dispatchable load power in the total load power includes determining the constraint conditions of the interruptible load model by the following formula:

[0025]

[0026] Among them, p il (m,t) represents the load of the mth interruptible device at time t, c il (m) represents the proportion of the mth interruptible load to the total load, p lood (t) represents the total load at time t, p il (m,t-1) represents the load of the mth interruptible device at time t-1, η represents the maximum interruptible ratio at consecutive moments, c il (t) represents the total compensation cost of interruptible load, f m is the compensation price for different levels of interruptible load, and n represents the number of levels of interruptible load.

[0027] According to the optimal dispatching method in demand response provided by the present invention, determining the constraint conditions of the dispatchable load power in the total load power includes determining the constraint conditions of the transferable load model by the following formula:

[0028]

[0029] Where ushiftl(n,t) represents the state of the nth outgoing load at time t, ushiftq(n,t) represents the state of the nth incoming load at time t, and p shiftl (n,t) represents the transfer amount of the nth transferable load at time t, δ(n) represents the proportion of the nth transferable load to the total load, and p shiftq (n,t) represents the transfer amount of the nth transferable load at time t, and σ(n) represents the proportion of the nth transferable load to the total load.

[0030] According to the optimization scheduling method in demand response provided by the present invention, the method for constructing the objective function includes:

[0031] Determine the costs incurred by purchasing electricity and the costs incurred by dispatchable loads;

[0032] The objective function is the sum of the cost of purchasing electricity and the cost of dispatchable load.

[0033] The present invention also provides an optimization scheduling system in demand response, comprising:

[0034] A data acquisition module is used to acquire historical data, input the historical data into a pre-built load forecasting model, and obtain the total load power in the time period to be scheduled. The historical data is the load power data before the time period to be scheduled.

[0035] A first determination module is used to determine the constraint conditions of the dispatchable load power in the total load power;

[0036] The second determination module is used to take the total load power as input and, under the constraints of the constraints, determine the value of the dispatchable load power when the objective function obtains the minimum value, the objective function is pre-constructed, and the output of the objective function is the cost in the demand response process;

[0037] The third determination module is used to determine the optimal scheduling solution based on the numerical value of the dispatchable load power and the pre-built dispatchable load power model.

[0038] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, an optimization scheduling method in any of the above-mentioned demand responses is implemented.

[0039] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the optimization scheduling method in any of the above-mentioned demand responses is implemented.

[0040] The present invention also provides a computer program product, including a computer program, which implements any of the above-mentioned optimization scheduling methods in demand response when executed by a processor.

[0041] In the optimization scheduling method provided by the present invention, the total load power in a future period of time can be predicted based on the load prediction model. Since the input of the load prediction model is historical data, the total load power in the future can be predicted more accurately. Then, the constraints of the dispatchable load power are determined. In this way, when scheduling within the constraints, the phenomenon of poor response completion and waste of resources can be avoided. In addition, under the constraints of the constraints, the data of the dispatchable load power can be determined based on the objective function. Since the output of the objective function is the cost of demand response, the cost can be controlled to the lowest on the basis of satisfying the constraints. Finally, the optimization scheduling scheme can be determined based on the pre-constructed dispatchable load power model. In this way, the optimization scheduling scheme obtained can minimize the cost of optimization scheduling while avoiding the phenomenon of poor response completion and waste of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 It is a flowchart of an optimization scheduling method provided by an embodiment of the present invention;

[0044] Figure 2 It is a flow chart of a load forecasting model and a goose optimization algorithm provided by an embodiment of the present invention;

[0045] Figure 3 is a schematic diagram of the structure of an optimization scheduling system provided by an embodiment of the present invention;

[0046] Figure 4 It is a schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] Figure 1 It is a flowchart of an optimization scheduling method provided by an embodiment of the present invention;

[0049] like Figure 1 As shown, this embodiment provides an optimization scheduling method in demand response, including:

[0050] Step 101, obtaining historical data, inputting the historical data into a pre-built load forecasting model, and obtaining the total load power in the time period to be scheduled, where the historical data is the load power data before the time period to be scheduled;

[0051] Step 102, determining the constraint conditions of the dispatchable load power in the total load power;

[0052] Step 103, taking the total load power as input, under the constraints of the constraints, determining the value of the dispatchable load power when the objective function obtains the minimum value, the objective function is pre-constructed, and the output of the objective function is the cost in the demand response process;

[0053] Step 104: Determine an optimal scheduling solution based on the value of the dispatchable load power and a pre-built dispatchable load power model.

[0054] In implementation, the optimized scheduling scheme in this embodiment can be a macro-control result, that is, the load power in different time periods is scheduled according to actual demand, and the incoming load is guaranteed to be equal to the outgoing load in the process; when the dispatchable load includes different types of scheduling schemes, for example, when the dispatchable load includes interruptible load and transferable load, the optimized scheduling scheme can also include combining such different scheduling to obtain the optimal scheduling scheme; further, the dispatchable load can also be borne by different devices. For example, devices A, B and C can bear the dispatchable load, among which the loads of devices A and B can be interrupted, and the load of device C can be transferred. In this way, the final optimized scheduling scheme may be to interrupt the power load of device A from 18:00 to 20:00, interrupt the power load of device B from 19:00 to 20:00, and transfer the power load of device C from 18:00 to 21:00 to 2:00-5:00 of the next day.

[0055] In practical applications, the historical data obtained can first be cleaned, then standardized and normalized to reduce the error of the obtained data. The Pearson correlation analysis method can then be used to determine the parameters related to the load power, so that irrelevant data can be separated and the amount of data calculation can be reduced.

[0056] During implementation, the time period to be scheduled may be a time range of one day in the future. On this basis, the historical data may be the total power data of the previous day of the time period to be scheduled, wherein the total power data is the total power data within a certain range.

[0057] In the optimization scheduling method provided in this embodiment, the total load power in the future period can be predicted based on the load prediction model. Since the input of the load prediction model is historical data, the total load power in the future can be predicted more accurately. Then, the constraints of the dispatchable load power are determined. In this way, the phenomenon of poor response completion and waste of resources can be avoided when scheduling within the constraints. In addition, the data of the dispatchable load power can be determined based on the objective function under the constraints. Since the output of the objective function is the cost of demand response, the cost can be controlled to the lowest on the basis of satisfying the constraints. Finally, the optimization scheduling plan can be determined based on the pre-constructed dispatchable load power model. The optimization scheduling plan obtained in this way can well avoid the problems of poor corresponding completion and waste of resources, and at the same time can also reduce the cost in the demand response process as much as possible.

[0058] In an exemplary embodiment, a method for constructing a load forecasting model includes:

[0059] Build an extreme learning machine model;

[0060] The load power data before the scheduling period is used as the training set data, and the extreme learning machine model is trained based on the training set data to obtain the load forecasting model.

[0061] In this embodiment, the training set data of the extreme learning machine model is the load power data for a period of time before the time period to be scheduled. When the collection period of the training set data is close to the time period to be scheduled, the training set data can more accurately reflect the load power in the time period to be scheduled, thereby improving the prediction accuracy of the total load power.

[0062] Figure 2 It is a flow chart of a load forecasting model and a goose optimization algorithm provided by an embodiment of the present invention;

[0063] In practical applications, such as Figure 2 As shown, the construction method of the extreme learning machine model includes:

[0064] In the extreme learning machine neural network, suppose there are N arbitrary samples (x1, x2, ..., x N ), L hidden layer neurons, M output neurons, xi = [x i1 , x i2 , …, x in ], the actual output is yi=[y j1 ,y j2 , …, y jm ], the expected output is For the above single hidden layer neural network with L hidden nodes, it can be expressed as

[0065]

[0066] In the formula, β k is the output weight, G is the activation function of the hidden layer, W i is the input weight, X i is the input sample, b k is the bias of the kth neuron, y i is the output of the jth sample.

[0067] Rewritten into matrix form:

[0068] Hβ=Y(2)

[0069] Where H is the output of the hidden layer neuron, β is the output weight, and T is the expected output.

[0070]

[0071] The least squares method is used to calculate the fitting error between the output layer and the actual training data, which is expressed as:

[0072]

[0073] Once the input weights Wi and the hidden layer bias bi are randomly determined, the output matrix H of the hidden layer is uniquely determined, and the training process can be transformed into solving a linear system Hβ=Y, so the output weight β is:

[0074] β=H + Y=(H T H) -1 H T T (6)

[0075] In an exemplary embodiment, the method for constructing a load forecasting model further includes:

[0076] Based on the goose optimization algorithm, the total load power in the scheduling time period predicted by the extreme learning machine model is optimized.

[0077] In practical applications, the Goose algorithm can optimize the total load power by changing the original model learning rate, the number of neurons, the key value of the attention mechanism, and the regularization parameter. In this embodiment, the Goose algorithm can be used to optimize the optimization scheduling plan multiple times to make the obtained optimization scheduling plan more accurate.

[0078] In an exemplary embodiment, the dispatchable load power includes interruptible load power;

[0079] The dispatchable load power model includes the interruptible load power model, which is expressed by the following formula:

[0080]

[0081] in is the load at time t, is the minimum load, is the maximum load, is the start time of the operation, is the end time of the operation, For the running time, is the minimum runtime.

[0082] In practical applications, several sampling time points can be set for the time period to be scheduled. Time t refers to the moment of each sampling time point. For example, when the time period to be scheduled is one day, 96 sampling time points can be set in one day, which is equivalent to setting a sampling time point every 15 minutes.

[0083] In practical applications, the minimum load and the maximum load may be the minimum value and the maximum value of the total amount of the interruptible load.

[0084] In practical applications, interruptible loads can be divided into three levels. The basis for classification can be the compensation price when participating in demand response. Each level of interruptible load complies with the above formula.

[0085] For example, the levels can be level a, level b and level c, and the following formula is satisfied for level a:

[0086]

[0087] in is the load at time t, is the minimum load, is the maximum load, is the start time of the operation, is the end time of the operation, For the running time, is the minimum runtime.

[0088] For level b, the following formula is satisfied:

[0089]

[0090] in is the load at time t, is the minimum load, is the maximum load, is the start time of the operation, is the end time of the operation, For the running time, is the minimum runtime.

[0091] For level c, the following formula is satisfied:

[0092]

[0093] in is the load at time t, is the minimum load, is the maximum load, is the start time of the operation, is the end time of the operation, For the running time, is the minimum runtime.

[0094] In an exemplary embodiment, the dispatchable load power includes transferable load power;

[0095] The dispatchable load power model includes the transferable load power model, which is expressed by the following formula:

[0096]

[0097] in is the load at time t, is the minimum load, is the maximum load, is the start time of the operation, is the end time of the operation, Q a The required power consumption.

[0098] In practical applications, the minimum load and the maximum load may be the minimum and maximum values ​​of the total amount of the transferable load. Furthermore, the required power consumption may also be the power consumption required for the equipment performing the load transfer to complete its work.

[0099] In an exemplary embodiment, determining the constraint condition of the dispatchable load power in the total load power includes determining the constraint condition of the interruptible load model by the following formula:

[0100]

[0101] Among them, p il (m,t) represents the load of the mth interruptible device at time t, c il (m) represents the proportion of the mth interruptible load to the total load, p lood (t) represents the total load at time t, p il (m,t-1) represents the load of the mth interruptible device at time t-1, η represents the maximum interruptible ratio at consecutive moments, C il (t) represents the compensation cost of interruptible load, f m is the compensation price for different levels of interruptible load, and n represents the number of levels of interruptible load.

[0102] During implementation, during the time period to be scheduled, multiple devices may be able to interrupt the load. Based on this, it is necessary to calculate the load of each device. Therefore, in this embodiment, the load of m interruptible devices is calculated separately. In addition, in this embodiment, the maximum interruptible ratio of the interruptible devices at consecutive moments is also calculated to ensure the safe operation of the equipment.

[0103] In an exemplary embodiment, determining the constraint conditions of the dispatchable load power in the total load power includes determining the constraint conditions of the transferable load model by the following formula:

[0104]

[0105] Where ushiftl(n,t) represents the state of the nth outgoing load at time t, ushiftq(n,t) represents the state of the nth incoming load at time t, and p shiftl (n,t) represents the transfer amount of the nth transferable load at time t, δ(n) represents the proportion of the nth transferable load to the total load, and p shiftq (n,t) represents the transfer amount of the nth transferable load at time t, and σ(n) represents the proportion of the nth transferable load to the total load.

[0106] In practical applications, the total outgoing load can be controlled to be equal to the incoming load through the following formula:

[0107]

[0108] 0≤p shirtl (n,t)

[0109] 0≤p shiftq (n,t)

[0110] In addition, the supplementary costs of the transferable loads meet the following requirements:

[0111] C shift (t) = a n *shiftl(n,t)+b n *shiftq(n,t)

[0112] Among them C shift (t) is the compensation cost of the total transferable load, a n is the compensation unit price for the transferred load, b n The unit price of compensation for the transferred load.

[0113] In practice, in this embodiment, the time period to be scheduled is still taken as one day for example, and a sampling time point may be set every 15 minutes, which is equivalent to setting 96 sampling time points in one day.

[0114] In practical applications, while setting constraints on interruptible loads and transferable loads, the power balance can also be expressed by the following formula:

[0115]

[0116] The above formula indicates that the original total power consumption predicted for the whole day minus the transferred-out load plus the transferred-in load minus the interrupted load equals the total purchased power. By achieving a power balance between the purchased power and the power consumption, it is possible to avoid the waste of resources and the problem of still high power pressure due to poor response completion.

[0117] In an exemplary embodiment, the method for constructing the objective function includes:

[0118] Determine the costs incurred by purchasing electricity and the costs incurred by dispatchable loads;

[0119] The objective function is the sum of the cost of purchasing electricity and the cost of dispatchable load.

[0120] In practice, the objective function conforms to the following formula:

[0121] F=F1+F2+F3

[0122]

[0123] Among them, F is the total cost of demand response, F1 is the electricity purchase cost, F2 is the total compensation cost of interruptible load, F3 is the total compensation cost of intermediate transfer load, and V E (t) is the unit electricity price when purchasing electricity, p buy (t) is the actual amount of electricity purchased.

[0124] In an exemplary embodiment, the dispatchable load power model is represented by the following formula:

[0125]

[0126] d 2，i (t) = ΔP LD,i (t) / [P LD，i (t)p e，i ]

[0127]

[0128] Among them, Q i (t) represents the adjustable capacity of the response resource of user i at time t, that is, the value of the dispatchable load power, ΔP LD,i (t) represents the power of user i’s response resource that can be adjusted to participate in scheduling at time t, p e,i is the unit electricity price paid by user i, N D Indicates the number of sampling time points.

[0129] The optimization scheduling system provided by the present invention is described below. The optimization scheduling system described below and the optimization scheduling method described above can be referred to each other.

[0130] Figure 3 It is a structural diagram of an optimization scheduling system provided by an embodiment of the present invention.

[0131] like Figure 3 As shown, the optimization scheduling system provided in this embodiment includes:

[0132] The data acquisition module 301 is used to acquire historical data, input the historical data into a pre-built load forecasting model, and obtain the total load power in the time period to be scheduled. The historical data is the load power data before the time period to be scheduled.

[0133] A first determination module 302 is used to determine the constraint conditions of the dispatchable load power in the total load power;

[0134] The second determination module 303 is used to determine the value of the dispatchable load power when the objective function obtains the minimum value under the constraint condition with the total load power as input, the objective function is pre-constructed, and the output of the objective function is the cost in the demand response process;

[0135] The third determination module 304 is used to determine an optimal scheduling solution based on the value of the dispatchable load power and a pre-built dispatchable load power model.

[0136] In an exemplary embodiment, the optimization scheduling system further includes a first building module, which is used to build a load forecasting model. The first building module is specifically used to:

[0137] Build an extreme learning machine model;

[0138] The load power data before the scheduling period is used as the training set data, and the extreme learning machine model is trained based on the training set data to obtain the load forecasting model.

[0139] In an exemplary embodiment, the first building block is further configured to:

[0140] Based on the goose optimization algorithm, the total load power in the scheduling time period predicted by the extreme learning machine model is optimized.

[0141] In an exemplary embodiment, the dispatchable load power includes interruptible load power;

[0142] The dispatchable load power model includes the interruptible load power model, which is expressed by the following formula:

[0143]

[0144] in is the load at time t, is the minimum load, is the maximum load, is the start time of the operation, is the end time of the operation, For the running time, is the minimum runtime.

[0145] In an exemplary embodiment, the dispatchable load power includes transferable load power;

[0146] The dispatchable load power model includes the transferable load power model, which is expressed by the following formula:

[0147]

[0148] in is the load at time t, is the minimum load, is the maximum load, is the start time of the operation, is the end time of the operation, Q a For power consumption.

[0149] In an exemplary embodiment, the first determination module is specifically used to determine the constraint condition of the interruptible load model by the following formula:

[0150]

[0151] Among them, p il (m,t) represents the load of the mth interruptible device at time t, c il (m) represents the proportion of the mth interruptible load to the total load, p lood (t) represents the total load at time t, p il (m,t-1) represents the load of the mth interruptible device at time t-1, η represents the maximum interruptible ratio at consecutive moments, c il (t) represents the total compensation cost of interruptible load, f m is the compensation price for different levels of interruptible load, and n represents the number of levels of interruptible load.

[0152] In an exemplary embodiment, the first determination module is specifically used for:

[0153] The constraints of the transferable load model are determined by the following formula:

[0154]

[0155] Where ushiftl(n,t) represents the state of the nth outgoing load at time t, ushiftq(n,t) represents the state of the nth incoming load at time t, and p shiftl (n,t) represents the transfer amount of the nth transferable load at time t, δ(n) represents the proportion of the nth transferable load to the total load, and p shiftq (n,t) represents the transfer amount of the nth transferable load at time t, and σ(n) represents the proportion of the nth transferable load to the total load.

[0156] In the exemplary embodiment, a second building module is further included, and the second building module is used to build the target function. The second building module is specifically used to:

[0157] Determine the costs incurred by purchasing electricity and the costs incurred by dispatchable loads;

[0158] The objective function is the sum of the cost of purchasing electricity and the cost of dispatchable load.

[0159] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the optimization scheduling method in the demand response, and the method includes:

[0160] Obtain historical data, input the historical data into a pre-built load forecasting model, and obtain the total load power in the time period to be scheduled, where the historical data is the load power data before the time period to be scheduled;

[0161] Determine the constraints of dispatchable load power in the total load power;

[0162] Taking the total load power as input, under the constraints of the constraints, determine the value of the dispatchable load power when the objective function achieves the minimum value. The objective function is pre-constructed, and the output of the objective function is the cost in the demand response process;

[0163] Based on the numerical value of the dispatchable load power and the pre-built dispatchable load power model, an optimal dispatching plan is determined.

[0164] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), disk or optical disk, etc. Various media that can store program codes.

[0165] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the optimization scheduling method in the demand response provided by the above methods, the method includes:

[0166] Obtain historical data, input the historical data into a pre-built load forecasting model, and obtain the total load power in the time period to be scheduled, where the historical data is the load power data before the time period to be scheduled;

[0167] Determine the constraints of dispatchable load power in the total load power;

[0168] Taking the total load power as input, under the constraints of the constraints, determine the value of the dispatchable load power when the objective function achieves the minimum value. The objective function is pre-constructed, and the output of the objective function is the cost in the demand response process;

[0169] Based on the numerical value of the dispatchable load power and the pre-built dispatchable load power model, an optimal dispatching plan is determined.

[0170] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the optimization scheduling method in demand response provided by the above methods, the method comprising:

[0171] Obtain historical data, input the historical data into a pre-built load forecasting model, and obtain the total load power in the time period to be scheduled, where the historical data is the load power data before the time period to be scheduled;

[0172] Determine the constraints of dispatchable load power in the total load power;

[0173] Taking the total load power as input, under the constraints of the constraints, determine the value of the dispatchable load power when the objective function achieves the minimum value. The objective function is pre-constructed, and the output of the objective function is the cost in the demand response process;

[0174] Based on the numerical value of the dispatchable load power and the pre-built dispatchable load power model, an optimal dispatching plan is determined.

[0175] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0176] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0177] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An optimization scheduling method in demand response, characterized in that: include: Obtaining historical data, inputting the historical data into a pre-built load forecasting model to obtain the total load power in the time period to be scheduled, wherein the historical data is the load power data before the time period to be scheduled; Determining constraints on dispatchable load power in the total load power; Taking the total load power as input, under the constraint of the constraint condition, determining the value of the dispatchable load power when the objective function obtains the minimum value, the objective function is pre-constructed, and the output of the objective function is the cost in the demand response process; Based on the numerical value of the dispatchable load power and a pre-constructed dispatchable load power model, an optimized dispatching scheme is determined.

2. The optimization scheduling method according to claim 1, characterized in that: The method for constructing the load forecasting model includes: Build an extreme learning machine model; The load power data before the time period to be scheduled is used as training set data, and the extreme learning machine model is trained based on the training set data to obtain the load forecasting model.

3. The optimization scheduling method according to claim 2, characterized in that: The method for constructing the load forecasting model also includes: Based on the goose optimization algorithm, the total load power in the time period to be scheduled predicted by the extreme learning machine model is optimized.

4. The optimization scheduling method according to claim 1, characterized in that: The dispatchable load power includes interruptible load power; The dispatchable load power model includes an interruptible load power model, and the interruptible load power model is expressed by the following formula: in is the load at time t, is the minimum load, is the maximum load, is the start time of the operation, is the end time of the operation, For the running time, is the minimum runtime.

5. The optimization scheduling method according to claim 1, characterized in that: The dispatchable load power includes transferable load power; The dispatchable load power model includes a transferable load power model, and the transferable load power model is expressed by the following formula: in is the load at time t, is the minimum load, is the maximum load, is the start time of the operation, is the end time of the operation, Q a For power consumption.

6. The optimization scheduling method according to claim 4, characterized in that: The determining of the constraint conditions of the dispatchable load power in the total load power includes determining the constraint conditions of the interruptible load model by the following formula: Among them, p il (m,t) represents the load of the mth interruptible device at time t, c il (m) represents the proportion of the mth interruptible load to the total load, p lood (t) represents the total load at time t, p il (m,t-1) represents the load of the mth interruptible device at time t-1, η represents the maximum interruptible ratio at consecutive moments, c il (t) represents the total compensation cost of interruptible load, f m is the compensation price for different levels of interruptible load, and n represents the number of levels of interruptible load.

7. The optimization scheduling method according to claim 5, characterized in that: The determining of the constraint conditions of the dispatchable load power in the total load power includes determining the constraint conditions of the transferable load model by the following formula: Where ushiftl(n, t) represents the state of the nth outgoing load at time t, ushiftq(n, t) represents the state of the nth incoming load at time t, and p shiftl (n, t) represents the transfer amount of the nth transferable load at time t, δ(n) represents the proportion of the nth transferable load to the total load, and p shiftq (n, t) represents the transfer amount of the nth transferable load at time t, and σ(n) represents the proportion of the nth transferable load to the total load.

8. The optimization scheduling method according to claim 1, characterized in that: The method for constructing the objective function includes: Determine the costs incurred by purchasing electricity and the costs incurred by dispatchable loads; The objective function is the sum of the cost of purchasing electricity and the cost of the dispatchable load.

9. The optimal dispatching system in demand response is characterized by: include: A data acquisition module is used to acquire historical data, input the historical data into a pre-built load forecasting model, and obtain the total load power in the time period to be scheduled, wherein the historical data is the load power data before the time period to be scheduled; A first determination module, used to determine the constraint conditions of the dispatchable load power in the total load power; A second determination module is used to determine the value of the dispatchable load power when the objective function obtains the minimum value, taking the total load power as input and subject to the constraint condition, wherein the objective function is pre-constructed and the output of the objective function is the cost in the demand response process; The third determination module is used to determine an optimal scheduling solution based on the numerical value of the dispatchable load power and a pre-constructed dispatchable load power model.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, it implements the optimization scheduling method in demand response as described in any one of claims 1-8.

Images