LSTM-based method and system for evaluating maximum load and remaining adjustable capacity of a washing machine

Abstract

The application discloses a washing machine load maximum and residual adjustable capacity evaluation method and system based on LSTM, and the method comprises the following steps: collecting user washing machine load data; constructing a single washing machine user electricity consumption behavior prediction model based on an LSTM network, predicting the user's washing machine electricity consumption behavior by using the single washing machine user electricity consumption behavior prediction model based on the LSTM network; constructing a washing machine load maximum adjustable capacity evaluation model, evaluating the maximum up-regulation capacity and the maximum down-regulation capacity of the washing machine user by using the washing machine load maximum adjustable capacity evaluation model; and constructing a washing machine load residual adjustable capacity evaluation model, evaluating the residual adjustable capacity of the washing machine load after participating in the dispatch of the power grid again by using the washing machine load residual adjustable capacity evaluation model. The application improves the prediction accuracy of the washing machine load electricity consumption behavior, realizes fine and quantitative evaluation of the adjustable capacity of the washing machine load, and improves the power grid regulation capacity.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power system regulation, in particular to a washing machine load maximum and residual adjustable capacity evaluation method and system based on LSTM. BACKGROUND

[0002] Washing machine load evaluation is of great significance to improve the regulation capacity of urban power grids. The running time of washing machines can be arranged flexibly, and users can use washing machines during periods of low electricity prices or low grid loads. By dispersing peak loads, the pressure on the grid during peak periods is reduced, thereby achieving the purpose of peak shaving and valley filling. As a controllable load, washing machines can participate in demand response programs. When the grid load is too high or the power supply is tight, the running time of the washing machine is delayed through remote control or user guidance to reduce instantaneous load and improve grid stability. Reasonably arranging the use time of washing machines and optimizing energy use can improve energy utilization efficiency and reduce energy waste, thereby achieving the goal of energy saving and emission reduction. However, the existing washing machine load adjustable capacity evaluation has the following shortcomings: 1) inaccurate electricity behavior prediction, the prediction of user washing machine usage habits and electricity behavior is not accurate enough, and the diversity and variability of user behavior are not considered, resulting in inability to accurately evaluate the potential of load regulation; 2) rough load regulation capacity evaluation, without detailed analysis of the actual adjustable capacity of washing machine load; for example, without specific evaluation of the maximum up-regulation and maximum down-regulation capacity under different time periods and different user conditions; 3) insufficient dynamic regulation capacity, after participating in grid dispatching, the remaining regulation capacity of the washing machine is often not fully evaluated, which cannot be adjusted and responded to the demand of the grid in real time; this will limit the flexibility and effectiveness of washing machines as load regulation resources. 4) data and algorithm limitations, the existing load adjustable capacity evaluation may rely on traditional statistical methods and less data, without fully utilizing advanced technologies such as big data analysis and machine learning, resulting in insufficient accuracy and reliability of the evaluation results. SUMMARY

[0003] To solve the above problems, the present application proposes a washing machine load maximum and residual adjustable capacity evaluation method and system based on LSTM, which can improve the accuracy of washing machine electricity behavior prediction.

[0004] In order to achieve the above purpose, the present application is realized by the following technical scheme:

[0005] The washing machine load maximum and residual adjustable capacity evaluation method based on LSTM of the present application includes the following operations:

[0006] Collecting user washing machine load data, including washing machine start time, washing machine stop time, washing machine operable time range, and washing machine power;

[0007] Based on the user washing machine load data, a single washing machine user electricity consumption behavior prediction model based on an LSTM network is constructed, and the single washing machine user electricity consumption behavior prediction model based on the LSTM network is used to predict the washing machine electricity consumption behavior of the user;

[0008] According to the prediction result of the washing machine electricity consumption behavior of the user, a washing machine load maximum adjustable capacity evaluation model is constructed, and the washing machine load maximum adjustable capacity evaluation model is used to evaluate the maximum up-regulation capacity and the maximum down-regulation capacity of the washing machine user;

[0009] A washing machine load residual adjustable capacity evaluation model is constructed, and the washing machine load residual adjustable capacity evaluation model is used to evaluate the residual adjustable capacity of the washing machine load after participating in the dispatch of the power grid.

[0010] Further improvement of the present application is that the expression of the collected user washing machine load data is:

[0011]

[0012] Wherein, X i (k) is the washing machine load basic data of the user i on the kth day, is the washing machine starting time of the user i on the kth day, is the washing machine shutdown time of the user i on the kth day, is the washing machine running time range of the user i on the kth day, wherein is the earliest starting time of the user i on the kth day, is the latest starting time of the user i on the kth day, P i is the washing machine power of the user i.

[0013] Further improvement of the present application is that the expression of the single washing machine user electricity consumption behavior prediction model based on the LSTM network is:

[0014]

[0015] Wherein, f yi () is the washing machine user electricity consumption behavior LSTM training model, is the predicted washing machine user starting time, shutdown time, respectively, and Δk is the prediction step.

[0016] Further improvement of the present application is that the expression of the washing machine load maximum adjustable capacity evaluation model is:

[0017]

[0018] Wherein, P(t) is the sum of the washing machine load at t, P i is the washing machine power of the user i. the start time of the washing machine of user i, the end time of the washing machine of user i, M is the total number of washing machines in operation at t time;

[0019] The expression of the maximum up-regulation ability model of the washing machine load is:

[0020]

[0021] Wherein, P up (t) is the maximum up-regulation ability of the washing machine load at t time, is the washing machine power of user i1 which can be up-regulated, K is the total number of washing machine loads which can be moved forward, is the earliest start time of user i1 which can be up-regulated, is the start time of user i1 which can be up-regulated;

[0022] The expression of the maximum down-regulation ability model of the washing machine load is:

[0023]

[0024] Wherein, P dn (t) is the maximum down-regulation ability of the washing machine load at t time, is the washing machine power of user i2 which can be down-regulated, J is the total number of washing machine loads which can be moved backward, is the latest start time of user i2 which can be down-regulated.

[0025] Further improvement of the present application is that the washing machine load remaining adjustable ability evaluation model comprises a washing machine load remaining up-regulation ability evaluation model and a washing machine load remaining down-regulation ability evaluation model;

[0026] The expression of the washing machine load remaining up-regulation ability evaluation model is:

[0027]

[0028]

[0029] Wherein, ΔP up is the sum of the washing machine loads which can be moved forward between t1 and t2, P i is the washing machine power of user i, is the start time of the washing machine of user i, is the latest start time of user i, is the remaining up-regulation ability at t2, ΔP up (t1) is the load amount which is up-regulated in response to the power grid at t1 time, P up (t2) is the original up-regulation ability at t2 time;

[0030] The expression of the remaining down-regulation capability evaluation model of the washing machine load is:

[0031]

[0032]

[0033] Wherein, ΔP dn is the sum of the washing machine load transferred between t1 and t2, is the shutdown time of the washing machine of the user i, is the remaining down-regulation capability at t2, ΔP dn (t1) is the load amount responding to the down-regulation of the power grid at t1, P dn (t2) is the original down-regulation capability at t2.

[0034] The washing machine load maximum and remaining adjustable capability evaluation system based on LSTM of the application comprises:

[0035] The acquisition module is used for acquiring the washing machine load data of the user, including the washing machine startup time, the washing machine shutdown time, the washing machine operation time range and the washing machine power.

[0036] The prediction model construction module is used for constructing a single washing machine user electricity consumption behavior prediction model based on an LSTM network, and the single washing machine user electricity consumption behavior prediction model based on the LSTM network is used to predict the washing machine electricity consumption behavior of the user.

[0037] The maximum adjustable capability evaluation model construction module is used for constructing a washing machine load maximum adjustable capability evaluation model, and the washing machine load maximum adjustable capability evaluation model is used to evaluate the maximum up-regulation capability and the maximum down-regulation capability of the washing machine user.

[0038] The remaining adjustable capability evaluation model construction module is used for constructing a washing machine load remaining adjustable capability evaluation model, and the washing machine load remaining adjustable capability evaluation model is used to evaluate the remaining adjustable capability of the washing machine load participating in the dispatch of the power grid again.

[0039] The further improvement of the application is that the expression of the washing machine load data of the user acquired by the acquisition module is:

[0040]

[0041] Wherein, X i (k) is the washing machine load basic data of the user i on the kth day, is the washing machine startup time of the user i on the kth day, is the washing machine shutdown time of the user i on the kth day, is the washing machine available running time range of user i on the kth day, wherein is the earliest available start time of user i on the kth day, is the latest available start time of user i on the kth day, P i is the washing machine power of user i.

[0042] A further improvement of the present application is that the expression of the single washing machine user electricity consumption behavior prediction model based on the LSTM network is:

[0043]

[0044] wherein f yi is the washing machine user electricity consumption behavior LSTM training model, is the predicted washing machine user start time, is the predicted washing machine user stop time, and Δk is the prediction step.

[0045] A further improvement of the present application is that the expression of the washing machine load maximum adjustable capacity evaluation model is:

[0046]

[0047] wherein P(t) is the sum of washing machine loads at t, P i is the washing machine power of user i, is the washing machine start time of user i, is the washing machine stop time of user i, and M is the total number of washing machines in operation at t;

[0048] The expression of the washing machine load maximum adjustable capacity model is:

[0049]

[0050] wherein P up (t) is the washing machine load maximum adjustable capacity at t, is the washing machine power of user i1 that can be adjusted up, K is the total number of washing machine loads that can be moved forward, is the earliest available start time of user i1 that can be adjusted up, is the start time of user i1 that can be adjusted up;

[0051] The expression of the washing machine load maximum adjustable capacity model is:

[0052]

[0053] wherein P dn (t) is the washing machine load maximum adjustable capacity at t, is the washing machine power of user i2 that can be adjusted down, J is the total number of washing machine loads that can be moved backward, The latest start-up time of the user i2 can be adjusted downward.

[0054] Further improvement of the present application is that the washing machine load remaining adjustable capacity evaluation model comprises a washing machine load remaining adjustable capacity evaluation model and a washing machine load remaining adjustable capacity evaluation model.

[0055] The expression of the washing machine load remaining adjustable capacity evaluation model is:

[0056]

[0057]

[0058] Wherein, ΔP up is the sum of the washing machine load that can be moved forward between t1 and t2, P i is the washing machine power of the user i, is the washing machine start-up time of the user i, is the latest start-up time of the user i2, is the remaining adjustable capacity at t2, ΔP up (t1) is the load amount that responds to the grid adjustment at t1, P up (t2) is the original adjustable capacity at t2.

[0059] The expression of the washing machine load remaining adjustable capacity evaluation model is:

[0060]

[0061]

[0062] Wherein, ΔP dn is the sum of the washing machine load that can be moved forward between t1 and t2, is the washing machine power of the user i, is the washing machine start-up time of the user i, is the remaining adjustable capacity at t2, ΔP dn (t1) is the load amount that responds to the grid adjustment at t1, P dn (t2) is the original adjustable capacity at t2.

[0063] The beneficial effects of the present application are: based on the LSTM algorithm to improve the accuracy of the washing machine electricity consumption behavior prediction, to construct the maximum and remaining adjustable capacity evaluation model, to realize the fine and quantitative evaluation of the washing machine load adjustable capacity, and to improve the adjustment capacity of the grid. BRIEF DESCRIPTION OF DRAWINGS

[0064] Figure 1 is the method flowchart in the embodiment of the present application;

[0065] Figure 2is a schematic diagram of laundry machine load data collected in an embodiment of the present application;

[0066] Figure 3 is a schematic diagram of LSTM network training in an embodiment of the present application;

[0067] Figure 4 is a schematic diagram of prediction results of user laundry machine power consumption behavior in an embodiment of the present application;

[0068] Figure 5 is a schematic diagram of laundry machine load up-regulation capability in an embodiment of the present application;

[0069] Figure 6 is a schematic diagram of remaining adjustable capacity evaluation results in an embodiment of the present application. DETAILED DESCRIPTION

[0070] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application. In addition, the technical features involved in each embodiment of the present application described below can be combined with each other as long as they do not conflict with each other.

[0071] As shown in Figure 1 , the laundry machine load maximum and remaining adjustable capacity evaluation method based on LSTM of the present embodiment includes the following operations:

[0072] Step 1, collect user laundry machine load data, including laundry machine start time, laundry machine stop time, laundry machine operable time range, laundry machine power and other data, to provide a basis for laundry machine load adjustable capacity evaluation.

[0073] Step 2, construct a single laundry machine user power consumption behavior prediction model based on LSTM network. Since the user's laundry machine has certain randomness, the present embodiment trains the collected user laundry machine load data samples based on the LSTM network to predict the laundry machine power consumption behavior of a single user and master the user's power consumption characteristics, thereby providing support for evaluating the adjustable capacity of the laundry machine load.

[0074] Step 3, according to the prediction results of the user's laundry machine power consumption behavior, construct a laundry machine load maximum adjustable capacity evaluation model, which includes a laundry machine load maximum up-regulation capability model and a laundry machine load maximum down-regulation capability model, to respectively evaluate the maximum up-regulation capability and the maximum down-regulation capability of the laundry machine user.

[0075] Step 4, a washing machine load remaining adjustable capacity evaluation model is constructed to evaluate the remaining adjustable capacity of the washing machine load after participating in the dispatch, so as to provide support for continuous dispatch of the power grid. The washing machine load remaining adjustable capacity evaluation model includes a washing machine load remaining up-regulation capacity evaluation model and a washing machine load remaining down-regulation capacity evaluation model.

[0076] In step 1, the collected user washing machine load data is as shown in Figure 2 The expression is:

[0077]

[0078] Wherein, X i (k) is the basic data of the washing machine load of user i on the kth day, is the washing machine start time of user i on the kth day, is the washing machine stop time of user i on the kth day, is the washing machine available running time range of user i on the kth day, wherein is the earliest available start time of user i on the kth day, is the latest available start time of user i on the kth day, P i is the power of the washing machine of user i.

[0079] In step 2, the LSTM network training process is as shown in Figure 3 The input sample in this embodiment is: The output is: Wherein, Δk is the prediction step. The training process is represented as:

[0080]

[0081] Wherein, σ is an activation function, f k is the output of the forgetting gate, W f , b f is the corresponding forgetting gate matrix, i k is the output of the input gate, W j , b j is the corresponding input gate weight matrix, C k-1 is the old cell state information, is the selected added candidate state information, C k is the updated cell information, W C , b C is the corresponding neuron matrix, o k is the output of the output gate, W o , b o is the corresponding output gate matrix, h k is the output result, h k-1 is the hidden layer input.

[0082] The expression of the single washing machine user electricity consumption behavior prediction model based on the LSTM network is finally obtained as follows:

[0083]

[0084] wherein f yi () is the washing machine user electricity consumption behavior LSTM training model, are the predicted washing machine user start time and stop time, respectively. The electricity consumption behavior of each washing machine user is predicted by using the single washing machine user electricity consumption behavior prediction model based on the LSTM network, and the prediction results are shown in FIG. 6. Figure 4

[0085] In step 3, the washing machine load maximum adjustable capacity evaluation model is constructed according to the washing machine user electricity consumption behavior predicted by the single washing machine user electricity consumption behavior prediction model, and the load of the washing machine user at any time t is evaluated. The expression of the washing machine load maximum adjustable capacity evaluation model is as follows:

[0086]

[0087] wherein P(t) is the sum of the washing machine loads at time t, P i is the washing machine power of user i, is the washing machine start time of user i, is the washing machine stop time of user i, and M is the total number of washing machines in operation at time t.

[0088] The washing machine load maximum adjustable capacity model is constructed, which indicates that the washing machine that has a start time at time t and an earliest start time before time t can be scheduled in advance, i.e., the start time of the washing machine is time t, and the washing machine is scheduled in advance in the time period between the start time and the earliest start time, and the sum of the loads of the washing machine is the maximum adjustable capacity, and the expression is as follows:

[0089] The expression of the washing machine load maximum adjustable capacity model is as follows:

[0090]

[0091] wherein P up (t) is the washing machine load maximum adjustable capacity at time t, is the adjustable washing machine power of user i1, and K is the total number of adjustable washing machine loads, is the earliest start time of the adjustable user i1, is the start time of the adjustable user i1;

[0092] The expression of the washing machine load maximum adjustable capacity model is as follows: ​

[0093]

[0094] Among them, P dn (t) represents the maximum adjustable load capacity of the washing machine at time t. The power of the washing machine for user i2 can be reduced, and J is the total number of washing machines that can be moved to the next load. This allows for a reduction in the latest time a user's i2 can be powered on.

[0095] like Figure 5 As shown, the washing machine load remaining adjustable capacity assessment model in this embodiment is used to assess the remaining adjustable capacity of the washing machine load at time t2 after the washing machine load participates in grid dispatch at time t1. The washing machine load remaining adjustable capacity assessment model is shown in equations (7) and (8). Equation (7) represents the sum of the washing machine loads that can be moved forward between t1 and t2. In equation (8), the load amount ΔP in response to grid dispatch at time t1 is... up (t1) can be divided into two cases: 1) When the load adjusted by the power grid in this response is less than the sum of the washing machine loads that can be moved forward between t1 and t2, i.e., ΔP up (t1)≤ΔP up At time t2, the remaining up-adjustable capacity remains unaffected and is still P. up (t2). 2) When the load increase of the power grid in this response is greater than the sum of the washing machine loads that can be moved forward between t1 and t2, i.e. ΔP up (t1)>ΔP up When this occurs, it indicates that the remaining adjustable load needs to be scheduled from time t2 onwards. At this point, the remaining adjustable capacity at time t2 will decrease by an amount of (ΔP). up (t1)-ΔP up The remaining up-adjustable capacity changes at time t2.

[0096]

[0097] Where, ΔP up P is the sum of the loads of the washing machines that can be moved forward between t1 and t2. i For user i's washing machine power, For user i's washing machine startup time, The latest time user i can turn on their computer. ΔP represents the remaining up-adjustable capacity at time t2. up (t1) represents the load increase in response to the grid at time t1, P up (t2) represents the original up-adjustable capability at time t2.

[0098] The laundry machine load remaining down-regulation capability evaluation model is shown in formula (9) and formula (10). Formula (9) represents the sum of the laundry machine load that can be shifted between t1 and t2 at time t. In formula (10), the amount of load ΔP dn (t1) that is down-regulated in response to the power grid at t1 dn dn When the amount of load ΔP dn (t1) that is down-regulated in response to the power grid at t1 is greater than the sum of the laundry machine load that is shifted between t1 and t2, i.e., ΔP dn (t1) > ΔP dn , it indicates that the laundry machine load at t2 is increased, and the load can be cut, i.e., the down-regulation capability is further increased, and the increased amount is (ΔP dn (t1) - ΔP dn , and the remaining down-regulation capability at t2 is changed.

[0099]

[0100] wherein ΔP dn is the sum of the laundry machine load that is shifted between t1 and t2, is the laundry machine shutdown time of the user i, is the remaining down-regulation capability at t2, ΔP dn (t1) is the amount of load that is down-regulated in response to the power grid at t1, P dn (t2) is the original down-regulation capability at t2.

[0101] The above method is implemented by the laundry machine load maximum and remaining down-regulation capability evaluation system based on LSTM of the embodiment, and the system comprises:

[0102] A collection module is configured to collect laundry machine load data of a user, including laundry machine startup time, laundry machine shutdown time, laundry machine operable time range, and laundry machine power;

[0103] A prediction model construction module is configured to construct a single laundry machine user electricity consumption behavior prediction model based on an LSTM network, and predict the laundry machine electricity consumption behavior of the user by using the single laundry machine user electricity consumption behavior prediction model based on the LSTM network;

[0104] A maximum down-regulation capability evaluation model construction module is configured to construct a laundry machine load maximum down-regulation capability evaluation model, and evaluate the maximum up-regulation capability and the maximum down-regulation capability of the laundry machine user by using the laundry machine load maximum down-regulation capability evaluation model;

[0105] ​A residual adjustable capacity evaluation model construction module is configured to construct a washing machine load residual adjustable capacity evaluation model, and the washing machine load residual adjustable capacity evaluation model is used to evaluate the residual adjustable capacity of the washing machine load after participating in dispatching, so as to participate in power grid dispatching again.

[0106] Those skilled in the art can understand that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, unless otherwise defined herein, and should not be interpreted in an idealized or overly formal sense.

[0107] The above detailed description of the specific implementation of the application, the purpose, technical solutions and beneficial effects have been further described, it should be understood that the above described only for the specific embodiments of the present application, and not for limiting the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application, should be included in the scope of protection of the present application.

Claims

1. A method for evaluating the maximum load and the remaining adjustable capacity of a washing machine based on LSTM, characterized in that: The method comprises the following operations: Collecting user washing machine load data, including washing machine start time, washing machine stop time, washing machine available running time range, and washing machine power; Building a single washing machine user electricity consumption behavior prediction model based on an LSTM network based on the user washing machine load data, and predicting the user's washing machine electricity consumption behavior by using the single washing machine user electricity consumption behavior prediction model based on the LSTM network; According to the prediction result of the user's washing machine electricity consumption behavior, a washing machine load maximum adjustable capacity evaluation model is built, and the maximum up-regulation capacity and the maximum down-regulation capacity of the washing machine user are evaluated by using the washing machine load maximum adjustable capacity evaluation model; A washing machine load remaining adjustable capacity evaluation model is built, and the remaining adjustable capacity of the washing machine load after participating in the dispatch of the power grid is evaluated by using the washing machine load remaining adjustable capacity evaluation model; The expression of the collected user washing machine load data is: wherein X i (k) is the washing machine load base data of user i on day k, is the washing machine start-up time of user i on day k, is the washing machine shut-down time of user i on day k, is the washing machine operable time range of user i on day k, wherein is the earliest possible start-up time of user i on day k, is the latest possible start-up time of user i on day k, P i is the washing machine power of user i; The expression of the single washing machine user electricity consumption behavior prediction model based on the LSTM network is: wherein f yi is the LSTM training model of the washing machine user's electricity consumption behavior, are the predicted washing machine user's start time and stop time, respectively, and Δk is the prediction step. The expression of the washing machine load maximum adjustable capacity evaluation model is: where P(t) is the sum of the loads of the washing machines at time t, P i is the power of the washing machine of user i, is the start-up time of the washing machine of user i, is the shut-down time of the washing machine of user i, and M is the total number of washing machines in operation at time t. The expression of the washing machine load maximum up-regulation capacity model is: P up (t) is the maximum upgradable capacity of the washing machine at time t, is the upgradable power of the washing machine for user i1, K is the total number of upgradable washing machine loads, is the earliest upgradable start time of the washing machine for user i1, is the upgradable start time of the washing machine for user i1. The expression of the washing machine load maximum down-regulation capacity model is: P dn (t) is the maximum down-regulation ability of the washing machine load at time t, is the down-regulation ability of the washing machine power of user i2, and J is the total number of the washing machine load that can be moved backward, is the latest start time of the down-regulation of user i2. 2.The method of claim 1, wherein the method further comprises: The washing machine load remaining adjustable capacity evaluation model comprises a washing machine load remaining up-regulation capacity evaluation model and a washing machine load remaining down-regulation capacity evaluation model; The expression of the washing machine load remaining up-regulation capacity evaluation model is: ΔP up =∑P i , where ΔP up is the sum of shiftable washing machine load between t1 and t2, P i is the washing machine power of user i, is the washing machine on time of user i, is the latest possible on time of user i, is the remaining up-able capacity at t2, ΔP up (t1) is the amount of load shifted at t1 in response to grid up, P up (t2) is the original up-able capacity at t2; The expression of the washing machine load remaining down-regulation capacity evaluation model is: ΔP dn =∑P i , where ΔP dn is the sum of the laundry machine loads transferred between t1 and t2, is the laundry machine off time of user i, is the remaining down-regulation capability at time t2, ΔP dn (t1) is the amount of load down-regulated in response to the grid at time t1, P dn (t2) is the original down-regulation capability at time t2.

3. The system for evaluating the maximum load and the remaining adjustable capacity of a washing machine based on LSTM, characterized in that: The system comprises: A collection module is configured to collect user washing machine load data, including washing machine start time, washing machine stop time, washing machine available running time range, and washing machine power; A prediction model building module is configured to build a single washing machine user electricity consumption behavior prediction model based on an LSTM network, and predict the user's washing machine electricity consumption behavior by using the single washing machine user electricity consumption behavior prediction model based on the LSTM network; A maximum adjustable capacity evaluation model building module is configured to build a washing machine load maximum adjustable capacity evaluation model, and evaluate the maximum up-regulation capacity and the maximum down-regulation capacity of the washing machine user by using the washing machine load maximum adjustable capacity evaluation model; A remaining adjustable capacity evaluation model building module is configured to build a washing machine load remaining adjustable capacity evaluation model, and evaluate the remaining adjustable capacity of the washing machine load after participating in the dispatch of the power grid by using the washing machine load remaining adjustable capacity evaluation model; The expression of the user washing machine load data collected by the collection module is: where X i (k) is the washing machine load base data of user i on the kth day, is the washing machine start-up time of user i on the kth day, is the washing machine shut-down time of user i on the kth day, is the washing machine operable time range of user i on the kth day, where is the earliest start-up time of user i on the kth day, is the latest start-up time of user i on the kth day, P i is the washing machine power of user i; the expression of the single washing machine user electricity consumption behavior prediction model based on the LSTM network is: wherein f yi is the LSTM training model of the washing machine user's electricity consumption behavior, are the predicted washing machine user's start time and stop time, respectively, and Δk is the prediction step. The expression of the washing machine load maximum adjustable capacity evaluation model is: where P(t) is the sum of the loads of the washing machines at time t, P i is the power of the washing machine of user i, is the start-up time of the washing machine of user i, is the shut-down time of the washing machine of user i, and M is the total number of washing machines in operation at time t. The expression of the washing machine load maximum up-regulation capacity model is: P up (t) is the maximum upgradable capacity of the washing machine at time t, is the upgradable power of the washing machine for user i1, K is the total number of upgradable washing machine loads, is the earliest upgradable start time of the washing machine for user i1, is the upgradable start time of the washing machine for user i1. The expression of the washing machine load maximum down-regulation capacity model is: P dn (t) is the maximum down-regulation ability of the washing machine load at time t, is the down-regulation ability of the washing machine power of user i2, and J is the total number of the washing machine load that can be moved backward, is the latest start time of the down-regulation of user i2.

4. The LSTM-based washing machine load maximum and remaining adjustable capacity assessment system according to claim 3, characterized in that: The washing machine load remaining adjustable capacity evaluation model comprises a washing machine load remaining up-regulation capacity evaluation model and a washing machine load remaining down-regulation capacity evaluation model; The expression of the washing machine load remaining up-regulation capacity evaluation model is: ΔP up =∑P i , where ΔP up is the sum of shiftable laundry loads between t1 and t2, P i is the laundry power of user i, is the laundry on-time of user i, is the latest possible on-time of user i, is the remaining up-able capacity at t2, ΔP up (t1) is the amount of load shifted at t1 in response to the grid up, P up (t2) is the original up-able capacity at t2; The expression of the washing machine load remaining down-regulation capacity evaluation model is: ΔP dn =∑P i , where ΔP dn is the sum of the laundry machine loads transferred between t1 and t2, is the laundry machine off time of user i, is the remaining down-regulation capability at time t2, ΔP dn (t1) is the amount of load down-regulated in response to the grid at time t1, P dn (t2) is the original down-regulation capability at time t2.

Images