Cloud computing-based intelligent optimal scheduling system for waterworks

Abstract

The invention discloses a waterworks intelligent optimization scheduling system based on cloud computing, which belongs to the technical field of waterworks scheduling optimization and comprises a simulation module, a simulation optimization module, a data acquisition module and a dynamic optimization module. The simulation module is used for acquiring water supply information of the waterworks and establishing a water supply simulation model according to the water supply information; the simulation optimization module is used for carrying out simulation optimization on the scheduling scheme and carrying out simulation optimization analysis on the optimized and adjusted scheduling scheme again until the scheduling scheme meets the requirement; the data acquisition module is used for performing real-time water supply data acquisition to obtain water supply acquisition data; the dynamic optimization module is used for dynamically analyzing and adjusting the scheduling scheme according to the water supply acquisition data, and obtaining dynamic prediction data through a water supply prediction model; carrying out analogue simulation according to the water supply simulation model and the dynamic prediction data to obtain a scheduling acquisition analysis result at each time; and analyzing the scheduling acquisition analysis result of each time, and adjusting the scheduling scheme according to the analysis result.

Description

Technical Field

[0001] The present invention belongs to the technical field of water plant dispatch optimization, and in particular is an intelligent optimization dispatch system for a water plant based on cloud computing. Background Art

[0002] With the acceleration of urbanization and the continuous growth of population, the water plant, as the core of the urban water supply system, has a direct impact on the quality of life of residents and the stable development of the social economy. However, the traditional water plant dispatching system often faces many challenges, such as inflexible dispatching strategies, unreasonable equipment configuration, and low dispatching efficiency. These problems seriously restrict the optimal operation and sustainable development of the water supply system.

[0003] First, the traditional dispatching system mainly relies on manual experience and historical data to make dispatching decisions, lacking the real-time and precision of dispatching adjustments. Especially in the face of sudden changes in water demand or equipment failures, it is often difficult to respond effectively in time, resulting in an imbalance between supply and demand or waste of resources.

[0004] Secondly, unreasonable equipment configuration is also an important factor restricting the efficiency of the water supply system. The high energy consumption, low efficiency and lack of intelligent management methods of old equipment make the overall operating cost of the water supply system high, which is also not conducive to energy conservation, emission reduction and environmental protection.

[0005] Based on this, in order to realize the intelligent optimization and scheduling of the water plant, the present invention provides a water plant intelligent optimization and scheduling system based on cloud computing. Summary of the invention

[0006] In order to solve the problems existing in the above solutions, the present invention provides an intelligent optimization and scheduling system for water plants based on cloud computing.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A water plant intelligent optimization dispatching system based on cloud computing, including a simulation module, a simulation optimization module, a data acquisition module and a dynamic optimization module;

[0009] The simulation module is used to obtain water supply information of the water plant, and establish a water supply simulation model based on the water supply information, and the water supply simulation model is used to perform water supply simulation; establish a water supply prediction model, and the water supply prediction model is used to perform water supply prediction and obtain corresponding water supply demand prediction data.

[0010] The simulation optimization module is used to simulate and optimize the scheduling plan, predict water supply demand through the water supply prediction model, and obtain demand prediction data; obtain the scheduling plan, simulate the demand prediction data and the scheduling plan through the water supply simulation model, and obtain the simulation scheduling result;

[0011] Analyze the simulation scheduling results to determine whether there are scheduling failure areas;

[0012] When it is determined that there is no unqualified scheduling area, the simulation optimization is stopped;

[0013] When it is determined that there are areas of unqualified scheduling, the scheduling plan is optimized and adjusted according to the unqualified scheduling areas; the scheduling plan after optimization and adjustment is simulated and optimized again until there are no unqualified scheduling areas.

[0014] Furthermore, the method for analyzing the simulation scheduling results includes:

[0015] Obtain the scheduling target corresponding to the scheduling plan, integrate the simulation scheduling results and the corresponding scheduling target into scheduling evaluation data, and mark the scheduling evaluation data as (FG, MG);

[0016] Establish a scheduling evaluation model, the expression of the scheduling evaluation model is:

[0017]

[0018] Where: (FG, MG) is the input data, the input data is the scheduling evaluation data; the output data is the scheduling evaluation value DP (FG, MG);

[0019] Analyze the scheduling evaluation data through the scheduling evaluation model to obtain the corresponding scheduling evaluation value;

[0020] When the scheduling evaluation value is 1, it is determined that there is a scheduling unqualified area, and the location of the scheduling unqualified area is determined;

[0021] When no scheduling evaluation value is 1, it is determined that there is no scheduling failure area.

[0022] The data acquisition module is used to perform real-time water supply data acquisition to obtain water supply acquisition data.

[0023] The dynamic optimization module is used to dynamically analyze and adjust the scheduling plan according to the water supply collection data, obtain the water supply collection data, and use the water supply prediction model combined with the water supply collection data to predict water supply demand and obtain dynamic prediction data;

[0024] The water supply simulation model is used to simulate the scheduling scheme and the dynamic prediction data at each time to obtain the scheduling collection and analysis results corresponding to each time;

[0025] Analyze the dispatch collection and analysis results at each time to determine whether there are areas where dispatch fails;

[0026] When it is determined that there is no unqualified area for scheduling at each time, no corresponding operation is performed;

[0027] When it is determined that there is a scheduling unqualified area, the corresponding time is marked as the optimization time, the scheduling unqualified area corresponding to each optimization time is identified, and the scheduling plan is adjusted according to each scheduling unqualified area and the corresponding optimization time.

[0028] Furthermore, the method for adjusting the scheduling plan according to each scheduling unqualified area and the corresponding optimization time includes:

[0029] Identify the dispatch collection analysis results and dispatch targets corresponding to each dispatch failure area, and mark them as regional analysis results and regional dispatch targets respectively; determine the reasons for dispatch failure based on the regional analysis results and regional dispatch targets;

[0030] According to the reasons for each scheduling failure, each optimization time is merged to obtain each optimization period;

[0031] Set the adjustment method for each optimization period, and optimize the scheduling plan according to each adjustment method.

[0032] Furthermore, the method of merging the optimization times according to the reasons for the failure of each scheduling includes:

[0033] Step SA1: sort the optimization times in chronological order to obtain a first sequence, analyze the reasons for the scheduling failure of each optimization time, and determine the adjustment range corresponding to each optimization time;

[0034] Step SA2: Mark the first optimized time in the first sequence as the initial time point; mark the optimized time adjacent to the initial time point in the first sequence as the time point to be selected;

[0035] When there are no more time points to be selected, the analysis ends;

[0036] Step SA3: Identify the adjustment range methods corresponding to the initial time point and the selected time point respectively; define the merging requirements, compare the two adjustment range methods, and determine whether they meet the merging requirements;

[0037] When it is determined that the merging requirement is not met, the initial time point is marked as the optimization period, and the optimization time corresponding to the initial time point is removed from the first sequence, and the process returns to step SA2;

[0038] When it is determined that the merging requirements are met, the initial time point and the selected time point are merged to obtain the merged period, and the adjustment range method corresponding to the merged period is set;

[0039] Step SA4: marking the optimized time adjacent to the merged period in the first sequence as a candidate time point, and obtaining an adjustment range mode of the candidate time point;

[0040] When there are no more time points to be selected, the analysis ends;

[0041] Step SA5: Compare the two adjustment range methods to determine whether they meet the merging requirements;

[0042] When it is determined that the merging requirement is not met, the merging period is marked as an optimization period, and the optimization time corresponding to the merging period is removed from the first sequence, and the process returns to step SA2;

[0043] When it is determined that the merging requirements are met, the merging period and the selected time point are merged to obtain a new merging period, and the adjustment range mode corresponding to the merging period is set; and the process returns to step SA4.

[0044] Furthermore, the method for setting the adjustment mode of each optimization period includes:

[0045] Identify the adjustment range method corresponding to each optimization period, and determine the priorities corresponding to the adjustment range method;

[0046] Determine the adjustment method corresponding to the optimization period according to the priority and adjustment range;

[0047] When the adjustment range is adjusted manually, the corresponding optimization period is marked and the adjustment warning is issued to the corresponding management personnel.

[0048] Furthermore, it also includes a status analysis module, which is used to analyze the water supply status of the water plant and determine the equipment with abnormal performance.

[0049] Furthermore, the method for determining the device with abnormal performance includes:

[0050] Obtain the dispatching collection and analysis results in real time, and collect the measured results corresponding to each dispatching collection and analysis result; integrate the measured results and the dispatching collection and analysis results into verification result data, and mark the verification result data as (HS, DG);

[0051] Set the result verification model. The expression of the result verification model is:

[0052]

[0053] Where: (HS, DG) is the input data, the input data is the calibration result data; the output data is the calibration judgment value KD (HS, DG);

[0054] The verification result data is analyzed through the result verification model to determine the abnormal areas, and the performance abnormalities of the equipment are determined based on the abnormal areas.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] Through the mutual cooperation among the simulation module, simulation optimization module, data acquisition module, dynamic optimization module and state analysis module, the dynamic optimization of the water plant scheduling plan is realized; the intelligent scheduling strategy, optimization of equipment configuration and improvement of scheduling efficiency are realized, providing strong support for the long-term stable operation and continuous optimization of the water supply system; it can also carry out continuous optimization and adjustment according to the scheduling execution status and actual results, to ensure the long-term stable and efficient operation of the water supply system. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only 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.

[0058] Figure 1 This is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0059] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only 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.

[0060] like Figure 1 As shown, a water plant intelligent optimization scheduling system based on cloud computing includes a simulation module, a simulation optimization module, a data acquisition module, a dynamic optimization module and a state analysis module;

[0061] The simulation module is used to establish a water supply simulation model based on the water supply situation of the water plant, which is used to simulate water supply, and is mainly established using existing modeling technology and simulation technology; obtain water supply information of the water plant, such as pipe network information, equipment information and other information related to water supply simulation, and the established water supply simulation model is simulated according to the normal performance of various equipment, pipe networks, etc.; and establish a water supply prediction model, which is used to predict the water supply demand of the entire water supply area and obtain corresponding water supply demand prediction data; it is also established based on existing prediction technology according to the historical water supply data of the water plant.

[0062] The simulation optimization module is used to simulate and optimize the scheduling scheme, which is a water supply scheduling method that has been formulated by the user according to the needs; the water supply demand is predicted through the water supply prediction model to obtain the corresponding demand prediction data; this prediction is based on possible water supply data, which is used for the water supply situation that may be encountered in the subsequent scheduling scheme in the application, and has a certain difference from the actual situation. The subsequent prediction needs to be made based on the actual collected water supply data;

[0063] Obtain the scheduling plan, simulate the demand forecast data and the scheduling plan through the water supply simulation model, and obtain the simulation scheduling result. The simulation scheduling result is the scheduling result corresponding to the scheduling according to the scheduling plan under the demand forecast data within a period of time; analyze the simulation scheduling result, that is, compare the simulation scheduling result with the scheduling target that the scheduling plan needs to achieve; determine whether there is a scheduling unqualified area;

[0064] When it is determined that there is no unqualified scheduling area, the simulation optimization is stopped;

[0065] When it is determined that there is an unqualified scheduling area, the scheduling plan is optimized and adjusted according to the unqualified scheduling area; the optimized and adjusted scheduling plan is simulated and optimized again until there is no unqualified scheduling area. The scheduling plan is optimized and adjusted. In this embodiment, it is generally adjusted manually. It may be a problem with the scheduling plan design. Some problems are difficult to adjust intelligently. However, after subsequent verification, if problems occur again, intelligent adjustments can be made; in other embodiments, adjustments and improvements can also be made based on existing technologies or according to the following methods.

[0066] In one implementation, the method for analyzing the simulation scheduling results includes:

[0067] Obtain the scheduling target corresponding to the scheduling scheme, establish a scheduling evaluation model, and use the scheduling evaluation model to compare the simulation scheduling results with the corresponding scheduling targets to determine whether the simulation scheduling results meet the scheduling target requirements; integrate the simulation scheduling results and the corresponding scheduling targets into scheduling evaluation data, and mark the scheduling evaluation data as (FG, MG); the expression of the scheduling evaluation model is: Where: (FG, MG) is the input data, the input data is the scheduling evaluation data; the output data is the scheduling evaluation value DP (FG, MG);

[0068] Analyze the scheduling evaluation data through the scheduling evaluation model to obtain the corresponding scheduling evaluation value;

[0069] When the scheduling evaluation value is 1, it is determined that there is a scheduling unqualified area, and the location of the scheduling unqualified area is determined;

[0070] When no scheduling evaluation value is 1, it is determined that there is no scheduling failure area.

[0071] The data acquisition module is used to collect real-time water supply data and obtain water supply acquisition data; that is, to collect the current real real-time water supply data, including corresponding water supply demand data.

[0072] The dynamic optimization module is used to dynamically analyze and adjust the scheduling plan according to the water supply collection data, obtain the water supply collection data, and use the water supply prediction model to combine the water supply collection data to predict the water supply demand, and obtain demand prediction data. In order to distinguish it from the demand prediction data in the simulation optimization module, the demand prediction data in the dynamic optimization module is marked as dynamic prediction data;

[0073] The scheduling scheme and the dynamic prediction data at each time are simulated through the water supply simulation model to obtain the simulation scheduling results corresponding to each time. In order to distinguish them from the simulation scheduling results in the simulation optimization module, the simulation scheduling results in the dynamic optimization module are marked as scheduling collection and analysis results;

[0074] Analyze the dispatch collection and analysis results at each time to determine whether there are areas where dispatch is unqualified; make an assessment based on the dispatch evaluation model;

[0075] When it is determined that there is no unqualified area for scheduling at each time, no corresponding operation is performed;

[0076] When it is determined that there is a scheduling unqualified area, the corresponding time is marked as the optimization time, the scheduling unqualified area corresponding to each optimization time is identified, and the scheduling plan is adjusted according to each scheduling unqualified area and the corresponding optimization time.

[0077] In one embodiment, the method for adjusting the scheduling scheme according to each scheduling unqualified area and the corresponding optimization time includes:

[0078] Identify the dispatch collection analysis results and dispatch targets corresponding to each dispatch unqualified area, and mark them as regional analysis results and regional dispatch targets respectively; determine the reasons for dispatch unqualified according to the regional analysis results and regional dispatch targets; such as insufficient water volume, insufficient water pressure, unqualified water quality, etc., which can be determined by comparison; in one embodiment, an intelligent model can be established in combination with various existing unqualified reasons, and the reasons for dispatch unqualified can be intelligently determined through the intelligent model;

[0079] According to the reasons for each unqualified scheduling, the optimization times are merged to obtain each optimization period; the adjustment method of each optimization period is set, and the scheduling plan is optimized and adjusted according to each adjustment method.

[0080] Methods for merging the optimized times according to the reasons for each scheduling failure include:

[0081] Step SA1: sort the optimization times in chronological order to obtain the first sequence, analyze the reasons for each scheduling failure, and determine the adjustment range method corresponding to each scheduling failure reason; for example, for a water pressure problem, what range of pressurization can be used to solve the problem, with a range, pressurization as an adjustment method, and combined with its range as an adjustment range method; illustratively, various scheduling failure reasons and the adjustment methods that can be adopted for each scheduling failure reason can be summarized, and then the applicable adjustment methods are matched according to the scheduling failure reasons, and then the adjustment range of the corresponding adjustment method is determined according to the failure gap corresponding to the scheduling failure reason, to form an adjustment range method; if there is no solution, that is, no adjustment method is matched, the manual adjustment method is defaulted and the range is not set; in other embodiments, a corresponding intelligent model can be established in combination with existing artificial intelligence technology, and the intelligent model can be used to analyze each scheduling failure reason to determine the adjustment range method;

[0082] Step SA2: Mark the first optimized time in the first sequence as the initial time point; mark the optimized time adjacent to the initial time point in the first sequence as the time point to be selected; when there is no time point to be selected, end the analysis;

[0083] Step SA3: Identify the adjustment range methods corresponding to the initial time point and the selected time point respectively; define the merging requirement, which is that the two adjustment range methods can be adjusted using the same adjustment method, that is, have an adjustment intersection, and check whether the adjustment methods are the same. If the adjustment methods are the same, compare the corresponding adjustment ranges to determine the intersection range. If there is no intersection, it indicates that the same adjustment method cannot be used for the same adjustment; compare the two adjustment range methods to determine whether they meet the merging requirement;

[0084] When it is determined that the merging requirements are not met, the initial time point is marked as an optimization period, that is, it is independently used as an optimization period, and the optimization time corresponding to the initial time point is removed from the first sequence, and the process returns to step SA2;

[0085] When it is determined that the merging requirements are met, the initial time point and the selected time point are merged to obtain the merged period, and the adjustment range method corresponding to the merged period is determined according to the corresponding adjustment intersection;

[0086] Step SA4: Mark the optimized time adjacent to the merged period in the first sequence as a candidate time point, obtain the adjustment range of the candidate time point, and end the analysis when there is no candidate time point;

[0087] Step SA5: Compare the two adjustment range methods to determine whether they meet the merging requirements;

[0088] When it is determined that the merging requirement is not met, the merging period is marked as the optimization period, and the optimization time corresponding to the merging period is removed from the first sequence, and the process returns to step SA2;

[0089] When it is determined that the merging requirements are met, the merging period and the selected time point are merged to obtain a new merging period, and the adjustment range method corresponding to the new merging period is determined according to the corresponding adjustment intersection; return to step SA4.

[0090] Methods for setting the adjustment method for each optimization period include:

[0091] Identify the adjustment range method corresponding to each optimization period, and determine the priorities corresponding to the adjustment range method. For example, the priorities corresponding to the adjustment range are determined according to parameters such as cost, adjustment difficulty, adjustment efficiency, and impact. The priority can be determined by a single parameter or by combining the weight ratios of multiple parameters. The specific priority can be determined in combination with the existing priority determination method.

[0092] Determine the adjustment method corresponding to the optimization period according to the priority and adjustment range;

[0093] When the adjustment range is adjusted manually, the corresponding optimization period is marked and the adjustment warning is issued to the corresponding management personnel.

[0094] The state analysis module is used to analyze the water supply state of the water plant, obtain the scheduling collection and analysis results in real time, and collect the measured results corresponding to each scheduling collection and analysis result. The measured results are the actual scheduling results generated after scheduling according to the scheduling plan;

[0095] Compare the measured results with the dispatch collection and analysis results to determine the area where the results exceed the allowable error range, and then determine the corresponding abnormal cause. It can be determined according to the reasons for the dispatch failure, and then determine which device or devices have failed to meet normal performance and caused the abnormal cause; determine the performance abnormality equipment.

[0096] Exemplarily, a result verification model is set based on the error tolerance requirement. The result verification model is used to verify the measured results and the scheduling acquisition analysis results to determine whether there are measured results that do not meet the error tolerance requirement. The error tolerance requirement is set according to the possible error of the simulation and the user's allowable error; the measured results and the scheduling acquisition analysis results are integrated into the verification result data, and the verification result data is marked as (HS, DG); the expression of the result verification model is Where: (HS, DG) is the input data, the input data is the calibration result data; the output data is the calibration judgment value KD (HS, DG);

[0097] The calibration result data is analyzed through the result calibration model to determine the abnormal areas, and the equipment with abnormal performance is determined based on the abnormal areas. The abnormal area is the water use area that failed the calibration, and the equipment with abnormal performance is determined based on the corresponding equipment that may cause the cause.

[0098] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0099] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A cloud computing-based intelligent optimization and dispatching system for water plants, characterized in that: It includes simulation module, simulation optimization module, data acquisition module and dynamic optimization module; The simulation module is used to obtain water supply information of the water plant, and establish a water supply simulation model based on the water supply information, and the water supply simulation model is used to perform water supply simulation; establish a water supply prediction model, and the water supply prediction model is used to perform water supply prediction and obtain corresponding water supply demand prediction data; The simulation optimization module is used to simulate and optimize the scheduling plan, predict water supply demand through the water supply prediction model, and obtain demand prediction data; Obtain the scheduling plan, simulate the demand forecast data and scheduling plan through the water supply simulation model, and obtain the simulation scheduling results; Analyze the simulation scheduling results to determine whether there are scheduling failure areas; When it is determined that there is no unqualified scheduling area, the simulation optimization is stopped; When it is determined that there is an unqualified scheduling area, the scheduling plan is optimized and adjusted according to the unqualified scheduling area; the optimized and adjusted scheduling plan is simulated and optimized again until there is no unqualified scheduling area; The data acquisition module is used to collect water supply data in real time and obtain water supply collection data; The dynamic optimization module is used to dynamically analyze and adjust the scheduling plan according to the water supply collection data, obtain the water supply collection data, and use the water supply prediction model combined with the water supply collection data to predict water supply demand and obtain dynamic prediction data; The water supply simulation model is used to simulate the scheduling scheme and the dynamic prediction data at each time to obtain the scheduling collection and analysis results corresponding to each time; Analyze the dispatch collection and analysis results at each time to determine whether there are areas where dispatch fails; When it is determined that there is no unqualified area for scheduling at each time, no corresponding operation is performed; When it is determined that there is a scheduling unqualified area, the corresponding time is marked as the optimization time, the scheduling unqualified area corresponding to each optimization time is identified, and the scheduling plan is adjusted according to each scheduling unqualified area and the corresponding optimization time.

2. According to the cloud computing-based intelligent optimization and dispatching system for water plants according to claim 1, it is characterized in that: Methods for analyzing simulation scheduling results include: Obtain the scheduling target corresponding to the scheduling plan, integrate the simulation scheduling results and the corresponding scheduling target into scheduling evaluation data, and mark the scheduling evaluation data as (FG, MG); Establish a scheduling evaluation model, the expression of the scheduling evaluation model is: Where: (FG, MG) is the input data, the input data is the scheduling evaluation data; the output data is the scheduling evaluation value DP (FG, MG); Analyze the scheduling evaluation data through the scheduling evaluation model to obtain the corresponding scheduling evaluation value; When the scheduling evaluation value is 1, it is determined that there is a scheduling unqualified area, and the location of the scheduling unqualified area is determined; When no scheduling evaluation value is 1, it is determined that there is no scheduling failure area.

3. According to the cloud computing-based intelligent optimization scheduling system for water plants according to claim 1, it is characterized in that: Methods for adjusting the scheduling plan based on each scheduling unqualified area and the corresponding optimization time include: Identify the dispatch collection analysis results and dispatch targets corresponding to each dispatch failure area, and mark them as regional analysis results and regional dispatch targets respectively; determine the reasons for dispatch failure based on the regional analysis results and regional dispatch targets; According to the reasons for each scheduling failure, each optimization time is merged to obtain each optimization period; Set the adjustment method for each optimization period, and optimize the scheduling plan according to each adjustment method.

4. According to the cloud computing-based intelligent optimization scheduling system for water plants according to claim 3, it is characterized in that: Methods for merging the optimized times according to the reasons for each scheduling failure include: Step SA1: sort the optimization times in chronological order to obtain a first sequence, analyze the reasons for the scheduling failure of each optimization time, and determine the adjustment range corresponding to each optimization time; Step SA2: Mark the first optimized time in the first sequence as the initial time point; mark the optimized time adjacent to the initial time point in the first sequence as the time point to be selected; When there are no more time points to be selected, the analysis ends; Step SA3: Identify the adjustment range methods corresponding to the initial time point and the selected time point respectively; define the merging requirements, compare the two adjustment range methods, and determine whether they meet the merging requirements; When it is determined that the merging requirement is not met, the initial time point is marked as the optimization period, and the optimization time corresponding to the initial time point is removed from the first sequence, and the process returns to step SA2; When it is determined that the merging requirements are met, the initial time point and the selected time point are merged to obtain the merged period, and the adjustment range method corresponding to the merged period is set; Step SA4: marking the optimized time adjacent to the merged period in the first sequence as a candidate time point, and obtaining an adjustment range mode of the candidate time point; When there are no more time points to be selected, the analysis ends; Step SA5: Compare the two adjustment range methods to determine whether they meet the merging requirements; When it is determined that the merging requirement is not met, the merging period is marked as an optimization period, and the optimization time corresponding to the merging period is removed from the first sequence, and the process returns to step SA2; When it is determined that the merging requirements are met, the merging period and the selected time point are merged to obtain a new merging period, and the adjustment range mode corresponding to the merging period is set; and the process returns to step SA4.

5. According to claim 4, a cloud computing-based intelligent optimization and dispatching system for water plants is characterized in that: Methods for setting the adjustment method for each optimization period include: Identify the adjustment range method corresponding to each optimization period, and determine the priorities corresponding to the adjustment range method; Determine the adjustment method corresponding to the optimization period according to the priority and adjustment range; When the adjustment range is adjusted manually, the corresponding optimization period is marked and the adjustment warning is issued to the corresponding management personnel.

6. The cloud computing-based intelligent optimization and dispatching system for water plants according to claim 1 is characterized in that: It also includes a status analysis module, which is used to analyze the water supply status of the water plant and determine equipment with abnormal performance.

7. The cloud computing-based intelligent optimization and dispatching system for water plants according to claim 6 is characterized in that: Methods for determining equipment with abnormal performance include: Obtain the dispatching collection and analysis results in real time, and collect the measured results corresponding to each dispatching collection and analysis result; integrate the measured results and the dispatching collection and analysis results into verification result data, and mark the verification result data as (HS, DG); Set the result verification model. The expression of the result verification model is: Where: (HS, DG) is the input data, the input data is the calibration result data; the output data is the calibration judgment value KD (HS, DG); The verification result data is analyzed through the result verification model to determine the abnormal areas, and the performance abnormalities of the equipment are determined based on the abnormal areas.

Images