Hotel dishwasher load adjustable capability evaluation and power capacity market compensation method

Abstract

This invention discloses a method for assessing the adjustable load capacity of hotel dishwashers and compensating for load changes in the electricity capacity market. The method includes the following steps: collecting hotel dishwasher load data and related data; predicting hotel passenger flow using a multimodal artificial intelligence algorithm; constructing a tiered load model for hotel dishwashers based on passenger flow; obtaining the tiered load of dishwashers using this model; and constructing a day-ahead adjustable load assessment and electricity capacity market compensation model for hotel dishwashers based on the tiered load. This model assesses the day-ahead adjustable load capacity of hotel dishwashers for both upward and downward adjustments and provides compensation to the hotel in the upward and downward capacity markets, respectively. This invention can improve the accuracy of hotel passenger flow prediction, quantitatively assess the day-ahead adjustable load capacity of hotel dishwashers, and enhance the hotel's willingness to participate in the electricity capacity market.

Description

Technical Field

[0001] This invention relates to the field of power system control technology, specifically to a method for assessing the load adjustability of hotel dishwashers and for compensating for power capacity in the market. Background Technology

[0002] Hotel dishwashers have a significant load, and effectively assessing their load is crucial for enhancing load-side regulation capabilities and supporting grid regulation. Providing hotels with market compensation for electricity capacity can increase their willingness to participate in grid operation. However, existing methods have the following shortcomings: 1) Insufficient passenger flow forecasting: Current methods do not comprehensively consider new factors such as weather, temperature, and holidays. Current passenger flow forecasting models are often based on historical data and simple time series analysis, lacking comprehensive consideration of external factors such as weather conditions (sunny / rainy days), temperature changes, and holidays (festivals / weekends). Since these factors have a significant impact on passenger flow, ignoring them leads to inaccurate forecasts, thus affecting dishwasher load assessment and regulation strategies. 2) Insufficiently detailed correlation models between passenger flow and dishwasher load: Existing methods typically assume a linear relationship between passenger flow and dishwasher load, failing to fully explore the complex correlation between the two. In fact, passenger flow fluctuations may be influenced by the interaction of multiple factors, such as concurrent catering demand and special events, which are not reflected in detail in the correlation model, resulting in inaccurate load assessment results. 3) The day-ahead adjustable capacity assessment model is not detailed enough. Existing day-ahead adjustable capacity assessment models often lack detailed consideration of power capacity compensation. Fluctuations in dishwasher load directly affect power consumption; however, current assessment methods usually ignore how to effectively compensate for power capacity during load fluctuations. This affects the reliable operation of the dishwasher, especially during high-load periods, potentially leading to insufficient power supply or equipment overload. 4) Lack of dynamic adjustment mechanisms. Many methods lack the ability to dynamically adjust dishwasher load, relying mainly on static day-ahead plans, which cannot effectively cope with changes in actual conditions on the day. For example, if customer traffic surges due to sudden weather changes, fixed scheduling schemes may not be able to adjust dishwasher load in time, leading to dishwasher overload or reduced cleaning efficiency. 5) Insufficient utilization of multimodal data. Although some methods incorporate factors such as weather and holidays, the comprehensive utilization of multimodal data and the application of deep learning methods are still insufficient, failing to fully explore the implicit correlations between data. This limits the predictive ability of the model, especially in complex operating environments. Summary of the Invention

[0003] To address the aforementioned issues, this invention proposes a method for assessing the load adjustability of hotel dishwashers and compensating for electricity capacity market demands, which can enhance hotels' willingness to participate in the electricity capacity market.

[0004] To achieve the above objectives, the present invention is implemented through the following technical solution:

[0005] This invention relates to a method for assessing the load adjustability of hotel dishwashers and for compensating for electricity capacity in the market, comprising the following operations:

[0006] Collect hotel dishwasher load data and related data, including weather information, holiday information, temperature information, historical passenger flow information, dishwasher load operation time information, dishwasher power, and power capacity market compensation coefficient;

[0007] Predict hotel occupancy rates using multimodal artificial intelligence algorithms;

[0008] Construct a tiered load model for hotel dishwashers based on passenger flow, and use the tiered load model to obtain the tiered load of the dishwashers;

[0009] Based on the tiered load of dishwashers, a model for assessing the day-ahead adjustable capacity of hotel dishwasher load and compensating for the power capacity market is constructed. The model assesses the day-ahead adjustable capacity of hotel dishwasher load for both upward and downward adjustments and provides compensation to the hotel in the upward and downward capacity markets, respectively.

[0010] A further improvement of this invention is that the expressions for the collected hotel dishwasher load data and related data are as follows:

[0011]

[0012] X2(t)=[t za ,t zb ,t wa ,t wb ,t z1 ,t z2 ,t w1 ,t w2 [P0(t)]

[0013] Where X1(t) represents the non-hotel dishwasher load information on day t, w(t) represents the weather information on day t, with a value of 1 indicating a sunny day, a value of 2 indicating a cloudy day, a value of 3 indicating a rainy day, and a value of 4 indicating a snowy day; d(t) represents the holiday information on day t, with a value of 1 indicating a holiday, a value of 2 indicating a weekend, and a value of 3 indicating a weekday; T(t) represents the temperature information on day t; and L(t) represents the historical passenger flow information on day t. The upward capacity compensation coefficient provided by the electricity capacity market; X2(t) represents the capacity reduction compensation factor provided by the electricity capacity market; X2(t) represents the operating information of the hotel dishwasher on day t. za The earliest time to start washing dishes is around noon. zb The deadline for washing dishes is noon; t waThe earliest time to start washing dishes in the evening, t wb The deadline for washing dishes is in the evening; t z1 For the dishwasher's turn-on time at noon, t z2 The dishwasher will be turned off at noon; t w1 For the dishwasher's start time at night, t w2 P0(t) represents the time when the dishwasher is turned off at night; P0(t) represents the load of a single dishwasher in the hotel.

[0014] A further improvement of this invention lies in: using a multimodal artificial intelligence algorithm to predict hotel passenger flow, specifically including:

[0015] The feature fusion method combines data from different modalities to form a multimodal feature vector for the hotel, expressed as:

[0016] X' d (t)=[w'(t),d'(t),T'(t),L'(t)]

[0017] Where X' d (t) is the fused hotel multimodal feature vector, w'(t) is the weather information vector after unique thermal encoding, d'(t) is the holiday information vector after unique thermal encoding, T'(t) is the standardized temperature value, and L'(t) is the standardized historical passenger flow value.

[0018] The hotel's multimodal feature vectors are input into a multilayer perceptron to predict hotel occupancy. The objective function of the prediction is to minimize the error between the predicted and actual values, where the expression for the objective function is:

[0019]

[0020] Where δ(t) is the mean square error of the hotel passenger flow predicted by the multimodal artificial intelligence algorithm, N is the number of days, L(t) is the predicted hotel passenger flow, and L(t) is the historical passenger flow information on day t.

[0021] The formula for predicting hotel passenger traffic is:

[0022] L(t)=f mt (w'(t),d'(t),T'(t),L'(t))

[0023] Among them, f mt () represents a multimodal artificial intelligence algorithm prediction model.

[0024] A further improvement of this invention is that the expression for the stepped load model of the hotel dishwasher is:

[0025]

[0026] Where P(t) is the tiered load of the hotel dishwasher, M1, M2, M3, and M4 are the number of dishwashers started, P0(t) is the basic operating load of the dishwasher, γ1, γ2, γ3, and γ4 are the hotel passenger flow thresholds, and L(t) is the predicted hotel passenger flow.

[0027] A further improvement of this invention is that the expression for the day-ahead adjustable capacity assessment and electricity capacity market compensation model for hotel dishwashers is:

[0028]

[0029]

[0030]

[0031]

[0032] Wherein, ΔP up (t) represents the hotel dishwasher's available capacity for load adjustment as of the current day, ΔP dn (t) represents the hotel dishwasher's available capacity for load reduction as of the current day, P z (t) represents the dishwasher load at the hotel at noon, P w (t) represents the nighttime dishwasher load at the hotel. za The earliest time to start washing dishes is around noon. zb The deadline for washing dishes is noon. wa The earliest time to start washing dishes in the evening, t wb The deadline for washing dishes is in the evening. z1 The dishwasher is turned on at noon. z2 The dishwasher is scheduled to shut off at noon. w1 For the dishwasher's operating time at night, t w2 Y is the time to turn off the dishwasher at night. up To compensate for the increased market capacity of hotel dishwashers, Y dn To compensate for the reduced market capacity due to the decreased demand for hotel dishwashers, The upward capacity compensation factor provided by the electricity capacity market. This refers to the capacity reduction compensation factor provided by the electricity capacity market.

[0033] The beneficial effects of this invention are: it improves the accuracy of hotel occupancy forecasting and refines the correlation between occupancy and hotel dishwashers. It quantifies the day-ahead adjustability of hotel dishwasher load and, through a hotel dishwasher load power capacity market compensation model, increases the hotel's enthusiasm for participating in the power capacity market and enhances the grid's regulation capacity. Attached Figure Description

[0034] Figure 1 This is a flowchart from an embodiment of the present invention;

[0035] Figure 2 This is a schematic diagram illustrating the load operation characteristics of a hotel dishwasher in an embodiment of the present invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0037] like Figure 1 As shown, the method for assessing the adjustable load capacity of a hotel dishwasher and compensating for electricity market demand in this embodiment includes the following steps:

[0038] Step 1: Collect hotel dishwasher load data and related data, including weather information, holiday information, temperature information, historical guest flow information, dishwasher load operation time information, dishwasher power, and electricity capacity market compensation coefficient. The dishwasher load operation time information includes the earliest start time and latest end time for washing dishes at noon and in the evening, as well as the dishwasher start-up and shutdown times. The collected data is represented as follows:

[0039]

[0040] X2(t)=[t za ,t zb ,t wa ,t wb ,t z1 ,t z2 ,t w1 ,t w2 ,P0(t)](2)

[0041] Wherein, X1(t) is the non-hotel dishwasher load information on day t, w(t) is the weather information on day t, with a value of 1 representing a sunny day, a value of 2 representing a cloudy day, a value of 3 representing a rainy day, and a value of 4 representing a snowy day; d(t) is the holiday information on day t, with a value of 1 representing a holiday, a value of 2 representing a weekend, and a value of 3 representing a weekday; T(t) is the temperature information on day t; and L(t) is the historical passenger flow information on day t, including the passenger flow at noon and the passenger flow in the evening. The upward capacity compensation coefficient provided by the electricity capacity market; X2(t) represents the capacity reduction compensation factor provided by the electricity capacity market; X2(t) represents the operating information of the hotel dishwasher on day t. zaThe earliest time to start washing dishes is around noon. zb The deadline for washing dishes is noon; t wa The earliest time to start washing dishes in the evening, t wb The deadline for washing dishes is in the evening; t z1 For the dishwasher's turn-on time at noon, t z2 The dishwasher will be turned off at noon; t w1 For the dishwasher's start time at night, t w2 P0(t) represents the time when the dishwasher is turned off at night; P0(t) represents the load of a single dishwasher in the hotel.

[0042] Step 2: Predict hotel occupancy using a multimodal AI algorithm. Multimodal AI algorithms can be trained on data from different modalities to improve the effectiveness and accuracy of predictions. This embodiment uses a multimodal AI algorithm to predict hotel occupancy. The algorithm is trained on weather information w(t) for day t, holiday information d(t) for day t, temperature information T(t) for day t, and historical occupancy information L(t) for day t to predict hotel occupancy. Specifically, this includes:

[0043] First, the feature fusion method is used to combine data from different modalities to form a unified feature vector, namely the hotel multimodal feature vector, as shown in expression (3). This is a feature vector composed of inputs from different modalities, representing all relevant input data of hotel passenger flow at the current time t:

[0044] X' d (t)=[w'(t),d'(t),T'(t),L'(t)] (3)

[0045] Where X' d (t) is the fused hotel multimodal feature vector, w'(t) is the weather information vector after one-hot encoding, d'(t) is the holiday information vector after one-hot encoding, T'(t) is the standardized temperature value, and L'(t) is the standardized historical passenger flow value.

[0046] Secondly, the hotel's multimodal feature vector X' d (t) is input into a multilayer perceptron (MLP) and used to predict hotel passenger flow through a series of fully connected layers. In this embodiment, the objective function of prediction is to minimize the error between the predicted value and the actual value. In this embodiment, the minimum mean squared error (MSE) is taken, as shown in expression (4):

[0047]

[0048] Where δ(t) is the mean square error of the hotel occupancy volume predicted by the multimodal artificial intelligence algorithm, N is the number of days, and L(t) is the predicted hotel occupancy volume.

[0049] After the above training, a hotel passenger flow prediction based on multimodal artificial intelligence can be obtained, as shown in expression (5), with the hotel multimodal feature vector X' as input. d (t) can be used to predict the hotel’s guest traffic L(t) for the next day.

[0050] L(t)=f mt (w'(t),d'(t),T'(t),L'(t)) (5)

[0051] Among them, f mt () represents a multimodal artificial intelligence algorithm prediction model.

[0052] Step 3: Construct a tiered load model for hotel dishwashers based on passenger flow. The hotel selects to activate different numbers of dishwashers based on passenger flow to ensure the completion of the dishwashing task. Fewer dishwashers are activated when passenger flow is low, while multiple dishwashers need to be activated simultaneously when passenger flow is high. This embodiment uses a tiered load model for hotel dishwashers based on passenger flow to accurately describe the hotel dishwasher process and the resulting tiered load. The tiered load model for hotel dishwashers based on passenger flow is shown in expression (6):

[0053]

[0054] Where P(t) is the tiered load of the hotel dishwasher, M1, M2, M3, and M4 are the number of dishwashers started, P0(t) is the basic operating load of the dishwasher, γ1, γ2, γ3, and γ4 are the hotel passenger flow thresholds, and L(t) is the predicted hotel passenger flow.

[0055] Step 4: Construct a day-ahead adjustable capacity assessment and power capacity market compensation model for hotel dishwashers. Based on the constructed tiered load model for hotel dishwashers, this embodiment constructs a day-ahead adjustable capacity assessment model for hotel dishwashers to evaluate the day-ahead adjustable capacity for hotel dishwasher loads, providing support for the new power system dispatching. Based on the assessed adjustable capacity, a power capacity market compensation model for hotel dishwasher loads is constructed, providing compensation to hotels in both the upward and downward capacity markets, thereby increasing the enthusiasm of hotels to participate in the power capacity market and enhancing the grid's regulation capacity.

[0056] The operating characteristics of hotel dishwashers, such as Figure 2As shown, the hotel dishwasher load typically operates at noon and in the evening, usually starting at the end of lunch and dinner. During the dishwashing phase, it can participate in grid regulation, providing the grid with upward or downward adjustment capacity by shifting the load forward or backward. The constructed day-ahead adjustable capacity assessment model for the hotel dishwasher load is shown in expressions (7) and (8):

[0057]

[0058] Wherein, ΔP up (t) represents the hotel dishwasher's available capacity for load adjustment as of the current day, ΔP dn (t) represents the hotel dishwasher's available capacity for load reduction as of the current day, P z (t) represents the dishwasher load at the hotel at noon, P w (t) represents the nighttime dishwasher load at the hotel. Where P z (t), P w (t) is calculated based on the hotel’s midday and evening passenger flow predicted in step 2, and further calculated based on expression (6) in step 3.

[0059] The market compensation model for the power capacity of hotel dishwasher load is shown in expressions (9) and (10), where expression (9) is the market capacity compensation model for the upward adjustment of hotel dishwasher load and expression (10) is the market capacity compensation model for the downward adjustment of hotel dishwasher load.

[0060]

[0061] Among them, Y up To compensate for the increased market capacity of hotel dishwashers, Y dn To compensate for the reduced market capacity due to the decreased demand for hotel dishwashers, The upward capacity compensation factor provided by the electricity capacity market. This refers to the capacity reduction compensation factor provided by the electricity capacity market.

[0062] By following the above steps, the day-ahead adjustable capacity of hotel dishwashers can be effectively assessed, and compensation can be provided in the electricity capacity market, thereby increasing the hotel's enthusiasm for participating in the electricity capacity market and enhancing the grid's regulation capacity.

[0063] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless defined as herein.

[0064] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for assessing the load adjustability of hotel dishwashers and compensating for power capacity in the market, characterized by: This includes the following operations: Collect hotel dishwasher load data and related data, including weather information, holiday information, temperature information, historical passenger flow information, dishwasher load operation time information, dishwasher power, and power capacity market compensation coefficient; Predict hotel occupancy rates using multimodal artificial intelligence algorithms; Construct a tiered load model for hotel dishwashers based on passenger flow, and use the tiered load model to obtain the tiered load of the dishwashers; Based on the tiered load of dishwashers, a model for assessing the day-ahead adjustable capacity of hotel dishwasher load and the compensation model for the power capacity market is constructed. The model assesses the day-ahead adjustable capacity of hotel dishwasher load for both upward and downward adjustments and provides compensation to the hotel for the upward and downward adjustment capacity markets, respectively. The method of using multimodal artificial intelligence algorithms to predict hotel occupancy specifically includes: The feature fusion method combines data from different modalities to form a multimodal feature vector for the hotel, expressed as: X' d (t)=[w'(t),d'(t),T'(t),L'(t)] Where X' d (t) is the fused hotel multimodal feature vector, w'(t) is the weather information vector after unique thermal encoding, d'(t) is the holiday information vector after unique thermal encoding, T'(t) is the standardized temperature value, and L'(t) is the standardized historical passenger flow value. The hotel's multimodal feature vectors are input into a multilayer perceptron to predict hotel occupancy. The objective function of the prediction is to minimize the error between the predicted and actual values, where the expression for the objective function is: Where δ(t) is the mean square error of the hotel passenger flow predicted by the multimodal artificial intelligence algorithm, N is the number of days, L(t) is the predicted hotel passenger flow, and L(t) is the historical passenger flow information on day t. The formula for predicting hotel passenger traffic is: L”(t)=f mt (w'(t),d'(t),T'(t),L'(t)) Among them, f mt () represents a multimodal artificial intelligence algorithm prediction model; The expression for the day-ahead adjustable capacity assessment and electricity capacity market compensation model for the hotel dishwasher is as follows: Wherein, ΔP up (t) represents the hotel dishwasher's available capacity for load adjustment as of the current day, ΔP dn (t) represents the hotel dishwasher's available capacity for load reduction as of the current day, P z (t) represents the dishwasher load at the hotel at noon, P w (t) represents the nighttime dishwasher load at the hotel. za The earliest time to start washing dishes is around noon. zb The deadline for washing dishes is noon. wa The earliest time to start washing dishes in the evening, t wb The deadline for washing dishes is in the evening. z1 The dishwasher is turned on at noon. z2 The dishwasher is scheduled to shut off at noon. w1 For the dishwasher's operating time at night, t w2 Y is the time to turn off the dishwasher at night. up To compensate for the increased market capacity of hotel dishwashers, Y dn To compensate for the reduced market capacity due to the decreased demand for hotel dishwashers, The upward capacity compensation factor provided by the electricity capacity market. This refers to the capacity reduction compensation factor provided by the electricity capacity market.

2. The method for assessing the adjustable load capacity of hotel dishwashers and compensating for power capacity market demand as described in claim 1, characterized in that: The expressions for the collected hotel dishwasher load data and related data are as follows: X2(t)=[t za ,t zb ,t wa ,t wb ,t z1 ,t z2 ,t w1 ,t w2 ,P0(t)] Where: X1(t) is the non-hotel dishwasher load information on day t; w(t) is the weather information on day t, with a value of 1 representing a sunny day, a value of 2 representing a cloudy day, a value of 3 representing a rainy day, and a value of 4 representing a snowy day; d(t) is the holiday information on day t, with a value of 1 representing a holiday, a value of 2 representing a weekend, and a value of 3 representing a weekday; T(t) is the temperature information on day t; and L(t) is the historical passenger flow information on day t. The upward capacity compensation coefficient provided by the electricity capacity market; X2(t) represents the capacity reduction compensation factor provided by the electricity capacity market; X2(t) represents the operating information of the hotel dishwasher on day t. za The earliest time to start washing dishes is around noon. zb The deadline for washing dishes is noon; t wa The earliest time to start washing dishes in the evening, t wb The deadline for washing dishes is in the evening; t z1 For the dishwasher's turn-on time at noon, t z2 The dishwasher will be turned off at noon; t w1 For the dishwasher's start time at night, t w2 P0(t) represents the time when the dishwasher is turned off at night; P0(t) represents the load of a single dishwasher in the hotel.

3. The method for assessing the adjustable load capacity of hotel dishwashers and compensating for power capacity market demand as described in claim 1, characterized in that: The expression for the hotel dishwasher stepped load model is as follows: Where P(t) is the tiered load of the hotel dishwasher, M1, M2, M3, and M4 are the number of dishwashers started, P0(t) is the basic operating load of the dishwasher, γ1, γ2, γ3, and γ4 are the hotel passenger flow thresholds, and L(t) is the predicted hotel passenger flow.

Images