Equipment energy consumption optimization scheduling method and system based on big data analysis

Abstract

The invention discloses an equipment energy consumption optimization scheduling method and system based on big data analysis, and relates to the field of energy management and intelligent scheduling. The method comprises the following steps: collecting multi-dimensional state data in an equipment operation process, constructing a unit time energy consumption function and extracting an energy consumption disturbance structure index; an input stress dissipation index, a spatial heterogeneous adaptation index and a behavior impedance difference factor are introduced to form an equipment operation characteristic parameter system; an energy consumption deviation structure is constructed in combination with actual operation data, a disturbance feedback correction factor is generated, and a scheduling strategy feedback correction and adaptive evolution mechanism oriented to multiple cycles is established, so that a complete energy consumption optimization scheduling method system covering data acquisition, state modeling, parameter extraction, combined scheduling and closed-loop updating is constructed. Dynamic perception, fine identification and adaptive optimization of equipment energy consumption scheduling are realized by constructing a multi-dimensional disturbance structure modeling, difference characteristic parameter extraction and closed-loop feedback correction mechanism.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of energy management and intelligent scheduling, in particular to a device energy consumption optimization scheduling method and system based on big data analysis. BACKGROUND

[0002] With the continuous improvement of industrial automation level, complex device systems are increasingly widely deployed in various production, manufacturing and energy management scenarios. The scheduling strategy of multi-device collaborative operation is of great significance to ensure the overall operation efficiency of the system, reduce energy waste and improve dynamic adaptability. Under this background, the device energy consumption scheduling problem has become one of the research focuses in the field of energy efficiency management.

[0003] In the prior art, device scheduling mainly relies on static strategies or empirical rules, which often cannot fully cope with real-time disturbances and energy consumption anomalies in the running process. In the face of dynamically changing operating environment and complex coupling behavior of multiple devices, traditional scheduling methods have significant limitations in identifying the collaborative relationship between devices, dynamic adaptability and abnormal response mode, resulting in limited overall energy consumption optimization effect.

[0004] In addition, although some energy consumption scheduling techniques based on prediction models introduce data-driven analysis methods, they are mostly limited to energy consumption prediction or simple sorting level, lack comprehensive modeling of heterogeneous state adaptability between devices, energy consumption disturbance structure characteristics and system-level collaborative stability, and are difficult to support dynamic scheduling decisions for complex multi-device systems. At the same time, the energy consumption feedback after scheduling execution is often not fully utilized, and the strategy lacks an effective closed-loop correction mechanism, making it difficult to achieve time-series iteration and adaptive evolution of scheduling parameters.

[0005] Therefore, it is urgent to build a device energy consumption optimization scheduling method that integrates running state perception, disturbance structure modeling, scheduling potential quantization and feedback-driven updating, which can realize intelligent, dynamic and multi-dimensional adaptive optimization of scheduling strategies on the basis of ensuring operation safety. SUMMARY

[0006] Based on the shortcomings of the prior art described above, the purpose of the present application is to provide a device energy consumption optimization scheduling method and system based on big data analysis to solve the above technical problems.

[0007] To achieve the above purpose, the present application provides the following technical solution: a device energy consumption optimization scheduling method based on big data analysis, comprising:

[0008] In a scheduling period, the running state data of a set of devices to be scheduled with a preset number is collected, the unit time energy consumption function of each device is constructed according to the collected running state data, and an energy consumption disturbance structure index representing the running disturbance intensity is generated;

[0009] According to the energy consumption disturbance structure index and the operation state data, the input stress dissipation index and the spatial heterogeneous adaptation index are calculated, the behavior impedance difference factor between any two devices is constructed, and the device operation characteristic parameter set is formed;

[0010] According to the device operation characteristic parameter, the scheduling potential energy function is constructed, the cooperative stability level and the disturbance risk intensity of the preset candidate device in the scheduling period are measured, and the scheduling potential energy function is taken as the objective function of the scheduling combination optimization;

[0011] According to the scheduling potential energy function, the structure adaptability threshold and the behavior conflict judgment condition, a device set meeting the adaptability requirement and not constituting an operation conflict is selected from the to-be-scheduled devices, the marginal potential energy contribution value of each device in the set in the potential energy function is calculated, the devices are sorted according to the contribution value, a scheduling priority queue is generated, and a scheduling instruction is output;

[0012] After the scheduling task is completed, the actual energy consumption data of the scheduled device is collected, the data is compared with the prediction model result at multiple time points, the energy consumption deviation structure is calculated, the disturbance feedback correction factor is generated according to the energy consumption deviation structure, and the input stress dissipation index and the spatial heterogeneous adaptation index are updated.

[0013] The application further provides that the operation state data of the to-be-scheduled device set in the scheduling period is collected, including the multi-time period continuous sampling of the device voltage, current, control input intensity and disturbance response information;

[0014] Based on the collected operation state data, the device unit time energy consumption function is constructed;

[0015] The energy consumption disturbance structure index representing the disturbance intensity of the device operation is formed by extracting the dynamic characteristics of the unit time energy consumption function and the disturbance response information.

[0016] The application further provides that the device operation characteristic parameter set includes:

[0017] Based on the device energy consumption disturbance structure index and the device operation state data collected in the scheduling period, the input stress dissipation index and the spatial heterogeneous adaptation index of each device are calculated respectively;

[0018] Based on the input stress dissipation index and the spatial heterogeneous adaptation index, the behavior impedance difference factor is constructed for any two devices, which is used for quantitatively describing the difference and mutual influence relationship between the devices.

[0019] The device operation characteristic parameter set including the dynamic characteristics of a single device and the coupling relationship between devices is formed by comprehensively considering the input stress dissipation index, the spatial heterogeneous adaptation index and the behavior impedance difference factor between devices.

[0020] The application is further configured to construct the scheduling potential energy function, which comprises:

[0021] Based on the equipment operation characteristic parameters, a scheduling potential energy function of the candidate equipment set in the scheduling period is constructed; the scheduling potential energy function comprehensively represents the energy consumption dynamic characteristics and adaptability of the equipment individuals, and the mutual coupling relationship between the equipment in the operation cooperation process;

[0022] By introducing the cooperation stability structure and the disturbance risk structure, the overall operation coordination degree of the candidate equipment set and the bearing elasticity to external disturbance are respectively measured;

[0023] The scheduling potential energy function is taken as the objective function of the equipment combination scheduling optimization, and the equipment cooperation potential energy level information is passed to the downstream scheduling priority generation step, which is used to support the judgment basis of the equipment screening, marginal contribution evaluation and scheduling instruction output link.

[0024] The application is further configured to select, from the to-be-scheduled equipment set, an equipment set that meets the adaptability standard and has no behavior conflict in the running state according to the evaluation result of the scheduling potential energy function, the judgment condition of the structural adaptability threshold and the behavior conflict judgment condition;

[0025] For each equipment in the screened equipment set, based on the change of the corresponding scheduling potential energy function after the equipment is included in the current combination, a marginal potential energy contribution value of the equipment is determined;

[0026] The screened equipment is sorted according to the size of the marginal potential energy contribution value, and a scheduling priority queue is formed;

[0027] According to the scheduling priority queue, corresponding scheduling instructions are output.

[0028] The application is further configured that the marginal potential energy contribution value is constructed based on the current combination structure of the screened equipment set, and the change of the scheduling potential energy function caused by the introduction of the target equipment in the structure;

[0029] The marginal potential energy contribution value combines the input stress dissipation index, the spatial heterogeneity adaptation index of the target equipment and the behavior impedance difference factor relationship between the target equipment and each equipment in the selected equipment set, and reflects the change of the cooperation stability and the change of the disturbance coupling strength caused by the target equipment in the current scheduling structure;

[0030] The marginal potential energy contribution value is passed to the scheduling instruction generation link as the judgment basis of the scheduling priority sorting.

[0031] The application is further configured to collect the actual energy consumption data of the equipment in all the dispatched scheduling instructions in the previous scheduling period after the scheduling task is completed.

[0032] The actual energy consumption data includes a unit time energy consumption measurement value corresponding to a continuous time in a scheduling period;

[0033] The actual energy consumption data is matched with the predicted energy consumption data generated based on the unit time energy consumption function at each time, and an energy consumption deviation structure covering the whole scheduling period is constructed;

[0034] According to the energy consumption change offset trajectory, the response mutation amplitude and the control input coupling relationship presented in the energy consumption deviation structure, a corresponding disturbance feedback correction factor is generated;

[0035] Based on the adjustment strength of the disturbance feedback correction factor, the input stress dissipation index and the spatial heterogeneity adaptation index of each device in the previous period are adjusted in multiple dimensions, and a parameter structure after feedback correction is formed;

[0036] The corrected parameter structure is used as the input basis of the device operation characteristic parameter in the next scheduling period, so that the dynamic correction and time sequence iteration of the scheduling parameter are realized.

[0037] The application further provides that the energy consumption deviation structure includes a multi-time sequence deviation record set formed by one-to-one mapping of the actual energy consumption data and the predicted energy consumption data of each device in the scheduling period at continuous sampling time;

[0038] The multi-time sequence deviation record set constitutes a double-layer mapping structure, one layer of which is associated with the unique number of the device and the corresponding sampling time sequence, and the other layer is associated with the actual energy consumption offset value and the control input state at each time point;

[0039] The energy consumption deviation structure is used to identify the energy consumption abnormal response segments appearing in the actual operation process, including the deviation cumulative mutation segment, the frequent fluctuation segment and the disturbance delay segment, and accordingly provides a multi-type energy consumption drift label for triggering the construction strategy selection and the device operation state update path screening of the subsequent disturbance feedback correction factor.

[0040] The application further provides that the disturbance feedback correction factor is composed of three types of feedback source information:

[0041] The first type of feedback source information includes the consistency label of the energy consumption deviation stability degree and the disturbance change trend of the device in the continuous sampling period;

[0042] The second type of feedback source information includes the synchronous offset trajectory between the control input intensity change history and the energy consumption response difference;

[0043] The third type of feedback source information includes the offset coupling degree between the energy consumption decay rate of the predicted energy consumption structure near the sudden disturbance point and the actual response structure;

[0044] After the three types of feedback source information are shunted through the feedback channel, the response adjustment term of the input stress dissipation index, the adaptive compression term of the spatial heterogeneity adaptation index and the reservation term of the prediction model correction path are corresponded respectively, a dynamic update vector is constructed through the parameter transmission structure for controlling the multi-dimensional time sequence correction process of the equipment operation characteristic parameters.

[0045] The application also provides a device energy consumption optimization scheduling system based on big data analysis, the system comprises:

[0046] The data acquisition and energy consumption modeling module: in the scheduling period, the running state data of the preset number of to-be-scheduled device set is collected, the unit time energy consumption function of each device is constructed according to the collected running state data, and the energy consumption disturbance structure index representing the running disturbance intensity is generated;

[0047] The characteristic parameter extraction module: according to the energy consumption disturbance structure index and the running state data, the input stress dissipation index and the spatial heterogeneity adaptation index are calculated, the behavior impedance difference factor between any two devices is constructed, and the device running characteristic parameter set is formed;

[0048] The potential function construction module: the scheduling potential function is constructed according to the device running characteristic parameter, the cooperative stability level and the disturbance risk intensity of the preset candidate device in the scheduling period are measured, and the scheduling potential function is taken as the objective function of the scheduling combination optimization;

[0049] The scheduling optimization and instruction generation module: according to the scheduling potential function, the structure adaptability threshold and the behavior conflict judgment condition, the device set meeting the adaptability requirement and not constituting the operation conflict is selected from the to-be-scheduled device, the marginal potential energy contribution value of each device in the set in the potential function is calculated, the devices are sorted according to the contribution value, the scheduling priority queue is generated, and the scheduling instruction is output;

[0050] The feedback correction and parameter update module: after the scheduling task is completed, the actual energy consumption data of the scheduled device is collected, the data is compared with the prediction model result at multiple time points, the energy consumption deviation structure is calculated, the disturbance feedback correction factor is generated according to the energy consumption deviation structure, which is used for updating the input stress dissipation index and the spatial heterogeneity adaptation index, and the adaptive update of the scheduling parameters is completed in the next scheduling period.

[0051] The application provides a device energy consumption optimization scheduling method and system based on big data analysis, which comprises the following steps: collecting the running state data of a preset number of to-be-scheduled device sets in a scheduling period, constructing a unit time energy consumption function of each device according to the collected running state data, and generating an energy consumption disturbance structure index representing the running disturbance intensity; calculating an input stress dissipation index and a spatial heterogeneous adaptation index according to the energy consumption disturbance structure index and the running state data, constructing a behavior impedance difference factor between any two devices, and forming a device running characteristic parameter set; constructing a scheduling potential energy function according to the device running characteristic parameters, measuring the cooperative stability level and disturbance risk intensity of the preset candidate devices in the scheduling period, and taking the scheduling potential energy function as the objective function of scheduling combination optimization; selecting a device set that meets the adaptability requirements and does not constitute a running conflict from the to-be-scheduled devices according to the scheduling potential energy function, the structural adaptability threshold and the behavior conflict judgment condition, calculating the marginal potential energy contribution value of each device in the set in the potential energy function, sorting according to the contribution value, generating a scheduling priority queue, and outputting a scheduling instruction; after the scheduling task is completed, collecting the actual energy consumption data of the scheduled devices, comparing the data with the prediction model results at multiple time points, calculating the energy consumption deviation structure, generating a disturbance feedback correction factor according to the energy consumption deviation structure, and updating the aforementioned input stress dissipation index and spatial heterogeneous adaptation index to complete the adaptive update of the scheduling parameters in the next scheduling period, which has the beneficial effects of:

[0052] 1. Realize fine modeling of running disturbance structure: by collecting multi-dimensional running state data such as voltage, current, control input intensity and disturbance response of the device, constructing a unit time energy consumption function, and extracting an energy consumption disturbance structure index, the system can fully perceive the dynamic energy consumption change characteristics and disturbance response mode in the device running process;

[0053] 2. Introduce multi-dimensional characteristic index to enhance the running difference description ability between devices: construct input stress dissipation index, spatial heterogeneous adaptation index and behavior impedance difference factor, the system can quantify the difference according to the individual running performance of the device and the interactive coupling state between devices, and provide a structured and multi-level behavior expression basis for scheduling decision;

[0054] 3. Build energy consumption feedback closed-loop correction mechanism to improve the adaptive ability of the scheduling system: by collecting the actual energy consumption data after the completion of the scheduling task, constructing a multi-time sequence energy consumption deviation structure, extracting a disturbance feedback correction factor, dynamically correcting the key parameters and promoting the adaptive evolution of the device running characteristic parameters, and building a closed-loop feedback and multi-period iterative optimization system of the scheduling strategy.

[0055] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, the specific embodiments of the present application can be implemented according to the content of the description, and in order to make the above and other purposes, characteristics and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor. In the drawings:

[0057] Figure 1 A flow chart of a device energy consumption optimization scheduling method based on big data analysis is shown for an exemplary embodiment of the present application;

[0058] Figure 2 A structural schematic diagram of a device energy consumption optimization scheduling system based on big data analysis is shown for an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0059] The embodiments of the present application will be described below with reference to the drawings and preferred embodiments, and those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in the specification. The present application can also be implemented or applied by different specific embodiments, and the details in the specification can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, but not for limiting the protection scope of the present application.

[0060] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present application in a schematic manner, and only the components related to the present application are shown in the diagrams, but not the number, shape and size of the components when actually implemented. The actual implementation of each component may be randomly changed in shape, number and proportion, and the layout pattern of the components may also be more complex.

[0061] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application, however, it is obvious for those skilled in the art that the embodiments of the present application can be implemented without these specific details, and in other embodiments, the known structures and devices are shown in the form of block diagrams rather than in the form of details, so as not to make the embodiments of the present application difficult to understand.

[0062] Embodiment one:

[0063] A device energy consumption optimization scheduling method based on big data analysis, as shown in Figure 1 comprises:

[0064] In a scheduling period, the running state data of a preset number of to-be-scheduled device set is collected, a unit time energy consumption function of each device is constructed according to the collected running state data, and an energy consumption disturbance structure index representing the running disturbance intensity is generated;

[0065] According to the energy consumption disturbance structure index and the running state data, the input stress dissipation index and the spatial heterogeneity adaptation index are calculated, the behavior impedance difference factor between any two devices is constructed, and the device running characteristic parameter set is formed;

[0066] A scheduling potential energy function is constructed according to the device running characteristic parameters, the cooperative stability level and the disturbance risk intensity of the preset candidate device in the scheduling period are measured, and the scheduling potential energy function is taken as the objective function of the scheduling combination optimization;

[0067] According to the scheduling potential energy function, the structural adaptability threshold and the behavior conflict judgment condition, a device set that meets the adaptability requirement and does not constitute a running conflict is selected from the to-be-scheduled devices, the marginal potential energy contribution value of each device in the set in the potential energy function is calculated, the devices are sorted according to the contribution value, a scheduling priority queue is generated, and a scheduling instruction is output;

[0068] After the scheduling task is completed, the actual energy consumption data of the scheduled device is collected, the data is compared with the prediction model result at multiple time points, the energy consumption deviation structure is calculated, the disturbance feedback correction factor is generated according to the energy consumption deviation structure, and is used to update the input stress dissipation index and the spatial heterogeneity adaptation index, and the adaptive update of the scheduling parameters is completed in the next scheduling period.

[0069] The application further provides that the running state data of the to-be-scheduled device set in the scheduling period comprises multi-period continuous sampling of device voltage, current, control input intensity and disturbance response information; specifically, the control input intensity is the input control signal intensity of the device, which is the direct influence of external instructions or parameter settings on the device running; the disturbance response information reflects the reaction characteristics of the device to external disturbances (such as environmental changes, power fluctuations, etc.), and is used to identify the stability and adaptability of the device; through multi-period continuous sampling of device voltage, current, control input intensity and disturbance response, the running state of the device can be comprehensively and dynamically obtained, thereby providing omnidirectional and time-series data support for subsequent energy consumption modeling and scheduling decision-making;

[0070] Based on the collected running state data, a device unit time energy consumption function is constructed; specifically, the unit time energy consumption of the device is E(t), and the device unit time energy consumption function is defined as: Wherein, V(t) is the voltage of the device at time t, I(t) is the current of the device at time t, f ctrl (u(t is a function of control input intensity, describes the influence of control signal intensity on energy consumption, defined by device control algorithm, wherein u(t) is the control input signal intensity; by constructing the energy consumption function of the device per unit time, the energy consumption performance of each device in different working states is accurately quantified, providing basic data support for subsequent scheduling decisions. The energy consumption function can reflect the real-time running state and load change of the device, so that the scheduling system can dynamically adjust the scheduling strategy based on time series data;

[0071] By extracting the dynamic characteristics of the unit time energy consumption function and the disturbance response information, an energy consumption disturbance structure index representing the running disturbance intensity of the device is formed. Specifically, the disturbance response characteristic reflects the energy consumption change reaction of the device after being disturbed (such as load change, environmental change, etc.), and the dynamic characteristic extraction extracts the response mode of the device when facing disturbance from the energy consumption function, which can be modeled by methods such as amplitude change, frequency response, etc. The energy consumption disturbance structure index is defined as ΔE(t), which is represented by the change relationship between the energy consumption of the device and the control input: ΔE(t) = |E post (t) - E pre (t) |, wherein E post (t) is the energy consumption of the device at time t after being disturbed, with the unit of watt-hour, and E pre (t) is the energy consumption of the device at time t before being disturbed, with the unit of watt-hour. The disturbance structure index reflects the response intensity of the device to the disturbance, and can reflect the stability of the device when it is disturbed externally. By extracting the dynamic characteristics of the disturbance response and generating the energy consumption disturbance structure index, the system can clearly understand the adaptability and stability of the device in operation, especially in the case of external disturbance. This provides real-time feedback for the optimization decision of the scheduling system, making the device energy consumption scheduling more intelligent and accurate.

[0072] The application further provides that the forming device running feature parameter set comprises:

[0073] Based on the device energy consumption disturbance structure index and the device running state data collected in the scheduling period, the input stress dissipation index and the spatial heterogeneity adaptation index of each device are calculated respectively. Specifically, the calculation formula of the input stress dissipation index is: The input stress dissipation index is used to measure the energy dissipation ability of the device caused by the control input signal and external disturbance in the running process. The index describes how the device effectively converts energy into work output when facing internal and external input disturbances, rather than invalid loss; the calculation formula of the spatial heterogeneity adaptation index is: ​The external environment disturbance amount of the device at time t reflects the influence of the environment on the running state of the device, and is dimensionless, and the spatial isomerism adaptation index is used to measure the adaptation ability of the device to the external environment change in the multi-dimensional space.

[0074] Based on the input stress dissipation index and the spatial isomerism adaptation index, a behavior impedance difference factor is constructed for any two devices, which is used to quantitatively describe the difference and mutual influence relationship between the running behaviors of the devices; specifically, the behavior impedance difference factor is used to describe the possible behavior difference between any two devices in the scheduling process. The factor quantitatively reflects the energy coupling effect, cooperation efficiency and mutual influence between the devices, and can provide a basis for subsequent scheduling decision; the factor quantifies the mutual influence and impedance difference between the device i and the device j in the running process, specifically, the impedance difference considers the energy transmission and mutual regulation between the devices, and the calculation formula is: Wherein, Δη input (i) and Δη space (i) are the changes of the input stress dissipation index and the spatial isomerism adaptation index of the device i in the running process; Δη input (j) and Δη space (j) are the changes of the input stress dissipation index and the spatial isomerism adaptation index of the device j in the running process; ΔE i and ΔE j are the energy consumption disturbance structure indexes of the device i and the device j respectively, reflecting their energy dissipation characteristics under disturbance response; by introducing the behavior impedance difference factor, the mutual influence and cooperation ability between the devices can be quantified comprehensively, which provides a reliable basis for subsequent device screening and scheduling priority sorting, and ensures the efficiency and stability of the scheduling scheme

[0075] By comprehensively introducing the input stress dissipation index, the spatial isomerism adaptation index and the behavior impedance difference factor between the devices, a device running characteristic parameter set containing the dynamic characteristics of a single device and the coupling relationship between the devices is formed.

[0076] The application further provides that the scheduling potential energy function comprises:

[0077] Based on the device running characteristic parameters, a scheduling potential energy function of the candidate device set in the scheduling period is constructed; the scheduling potential energy function comprehensively represents the energy consumption dynamic characteristics and adaptation ability of the device individual, and the mutual coupling relationship between the devices in the running cooperation process;

[0078] By introducing the cooperative stability structure and the disturbance risk structure, the overall operation coordination degree of the candidate device set and the bearing elasticity to external disturbance are respectively measured. Specifically, the cooperative stability structure describes whether the devices can maintain stable operation state and avoid performance degradation due to interaction between devices when cooperating together. The cooperative stability structure can be modeled based on the mutual influence between devices, wherein S co (i,j) represents the stability degree of device i and device j in the cooperation process, γ ij is the coupling strength between device i and device j, d ij is the relative distance or performance difference between device i and device j; the disturbance risk structure describes the ability of the device to withstand disturbance when facing external disturbance (such as load change, environmental factors, etc.), which has a certain elasticity. The disturbance risk structure is represented as: wherein R d (i) represents the risk bearing capacity of device i under disturbance, β i is the response elasticity of device i, δ i is the disturbance intensity;

[0079] The scheduling potential energy function is taken as the objective function of the device combination scheduling optimization, and the device cooperative potential energy level information is passed to the downstream scheduling priority generation step, which is used to support the judgment basis of device screening, marginal contribution evaluation and scheduling instruction output link. Specifically, the construction formula of the scheduling potential energy function is: wherein E schedule is the total scheduling potential energy function, reflecting the overall scheduling effect of the device in the current scheduling period, S i is the individual energy consumption dynamic characteristic of device i, S co (i,j) is the cooperative stability between device i and device j, R d (i) is the disturbance risk bearing capacity of device i, and α, β, γ are weight coefficients for adjusting the relative importance of each factor. The scheduling potential energy function comprehensively represents the cooperative stability and disturbance risk of the device. The state of the device is evaluated by introducing the above-mentioned cooperative stability structure and disturbance risk structure. The final goal is to construct an objective function for optimizing the combination of device scheduling.

[0080] The application is further configured that the evaluation result of the scheduling potential energy function, the determination condition of the structural adaptability threshold value and the behavior conflict determination condition are used to screen a device set that meets the adaptability standard and has no behavior conflict in the running state from the to-be-scheduled device set; specifically, the structural adaptability threshold value refers to the adaptability of the device in the current scheduling environment. This is a threshold parameter, which represents the ability of the device to withstand external disturbances and internal condition changes. For each device i, the threshold value can be expressed as: θ i =f(S co (i),R d (i)) where S co (i) is the cooperative stability of the device i, R d (i) is the disturbance risk bearing capacity of the device i, and the function f is an adaptability threshold value model calculated based on the device characteristics. The behavior conflict determination condition is used to determine whether there is a behavior conflict between devices. The behavior conflict between devices is usually manifested as a decrease in running efficiency caused by resource competition or poor cooperation between devices. The behavior conflict factor between devices is C ij , which is 1 when there is a conflict and 0 when there is no conflict, where Π is an indicator function, which indicates that there is a conflict when the difference in cooperative stability between devices exceeds the threshold value δ;

[0081] For each device in the screened device set, the marginal potential energy contribution value of the device is determined based on the change in the corresponding scheduling potential energy function after the device is included in the current combination; the marginal potential energy contribution value ΔE i is used to measure the influence of each device on the overall scheduling potential energy, which specifically reflects the changes in cooperative stability and disturbance coupling strength caused by the device in the current scheduling structure.

[0082] The screened devices are sorted according to the size of the marginal potential energy contribution value to form a scheduling priority queue; the larger the marginal potential energy contribution value of the device i, the stronger the role of the device in improving the overall system scheduling efficiency, and the device should be scheduled first;

[0083] The corresponding scheduling instruction is output according to the scheduling priority queue.

[0084] The application is further configured that the marginal potential energy contribution value is constructed based on the current combination structure of the screened device set, and the change in the scheduling potential energy function caused by the introduction of the target device in the structure;

[0085] The marginal potential energy contribution value is related to the input stress dissipation index, the spatial heterogeneity adaptability index of the target device and the behavior impedance difference factor of the device to each device in the selected device set, and reflects the changes in cooperative stability and disturbance coupling strength caused by the target device in the current scheduling structure; specifically, the marginal potential energy contribution value ΔE iIt can be calculated using the following formula: in, It is the scheduling potential function E schedule The derivative of the individual energy consumption dynamic characteristics of device i reflects the contribution of device i to changes in energy consumption. It is the derivative of the scheduling potential function on the cooperative stability between device i and device j. It is the derivative of the scheduling potential energy function with respect to the disturbance risk bearing capacity of device i;

[0086] The marginal potential energy contribution value is transmitted to the scheduling instruction generation stage as the basis for determining scheduling priority.

[0087] The present invention is further configured such that, after the scheduling task is completed, the actual energy consumption data of all devices that have received scheduling instructions in the previous scheduling cycle are collected in different time periods.

[0088] Actual energy consumption data includes unit-time energy consumption measurements corresponding to consecutive moments within the scheduling cycle;

[0089] Actual energy consumption data is matched against predicted energy consumption data generated based on the unit-time energy consumption function on a time-by-time basis to construct an energy consumption deviation structure Π covering the entire scheduling cycle. m (τ), Π m (τ) represents the energy consumption deviation of device m at time point τ;

[0090] Based on the energy consumption change offset trajectory, response abrupt change amplitude, and coupling relationship with the control input presented in the energy consumption deviation structure, a corresponding disturbance feedback correction factor is generated; specifically, the local disturbance change intensity is defined as: Υ m (τ)=|Π m (τ+δ)-Π m (τΛ m (τ+δ)-Λ m (τ)|wherein, Λ m (τ) represents the control input strength of device m at time τ, δ represents the disturbance evaluation window length, and Υ m (τ) represents the synchronous response strength reflecting the combined changes in energy consumption offset and control input, used to locate abrupt change segments and abnormal drift intervals. The tag generation rules are as follows:

[0091] If Υ m If (τ)>η1 and the direction of change remains consistent, it is marked as a "drift delay segment";

[0092] If Υ m (τ) If it suddenly increases and then quickly decreases, it is marked as a "mutation segment";

[0093] If in ζ consecutive time intervals Υ mIf the fluctuation is frequent, it is marked as a "frequent fluctuation section".

[0094] All label sets are denoted as

[0095] The input stress dissipation index and the spatial heterogeneity adaptation index of each device in the previous period are adjusted based on the adjustment strength of the disturbance feedback correction factor, respectively, to form a feedback corrected parameter structure;

[0096] The corrected parameter structure is used as the input basis for the operating characteristic parameters of the device in the next scheduling period, to realize dynamic correction and timing iteration of the scheduling parameters.

[0097] The application further provides that the energy consumption deviation structure includes a multi-time sequence deviation record set formed by one-to-one mapping of actual energy consumption data and predicted energy consumption data of each device at continuous sampling time points in the scheduling period;

[0098] The multi-time sequence deviation record set constitutes a double-layer mapping structure, one layer of which is associated with the unique number of the device and the corresponding sampling time sequence, and the other layer is associated with the actual energy consumption offset value and the control input state at each time point.

[0099] The energy consumption deviation structure is used to identify energy consumption abnormal response segments that occur in the actual operation process, including deviation cumulative mutation segments, frequent fluctuation segments and disturbance delay segments, thereby providing multiple types of energy consumption drift labels for triggering the construction strategy selection of the subsequent disturbance feedback correction factor and the device operating state update path screening. m (τ) = Θ m (τ) - Ξ m (τ), Wherein, Π m (τ) is the energy consumption deviation of device m at time point τ, Θ m (τ) is the actual unit time energy consumption of device m, Ξ m (τ) is the unit time energy consumption of device m at the same time point output by the prediction model, is a set of continuous sampling time points in the scheduling period, by traversing to form a device number-time-point-deviation three-dimensional mapping structure

[0100] The application further provides that the disturbance feedback correction factor is composed of three types of feedback source information:

[0101] The first type of feedback source information includes a consistency label of the energy consumption deviation stability degree of the device in a continuous sampling period and a change trend of the disturbance; specifically, the first type of feedback source information extracts a stable consistency label feedback factor, and the formula is: Wherein, is an input response gradient, which reflects the consistency of the disturbance direction and the input change and quantifies the controllability of the prediction error;

[0102] The second type of feedback source information includes a synchronous offset trajectory between the control input intensity change history and the energy consumption response difference; specifically, the second type of feedback source information extracts a synchronous offset feedback factor, and the formula is: Wherein, ΔΛ m (τ)=Λ m (τ)-Λ m (τ-δ), ΔΠ m (τ)=Π m (τ)-Π m (τ-δ) is used to measure the synchronous influence of the control input change on the energy consumption deviation;

[0103] The third type of feedback source information includes the offset coupling degree between the energy consumption decay rate of the predicted energy consumption structure near the sudden disturbance point and the actual response structure; specifically, the third type of feedback source information extracts a sudden disturbance point coupling factor, and the formula is: Only the time points in the mutation label set are calculated, and the model coupling error of the predicted response and the actual response under the sharp disturbance is expressed by the difference of the second time derivative;

[0104] After the three types of feedback source information are divided by the feedback channel, they correspond to the response adjustment term of the input stress dissipation index, the adaptation compression term of the spatial isomerism adaptation index, and the reservation term of the prediction model correction path, respectively. A dynamic update vector is constructed through a parameter transmission structure, which is used for a multi-dimensional time sequence correction process of the control device operation characteristic parameters. Specifically, the three factors form an update vector: The system updates the input stress dissipation index Φ m and the spatial isomerism adaptation index Γ m as follows: Wherein, ρ1, ρ2 ∈ (0, 1) are adaptive adjustment coefficients, Φ m ', Γ m ' are updated parameters used for next period scheduling, and three types of disturbance feedback correction factors are constructed, covering multiple dimensions of input response, control coupling, and prediction offset, forming a high-dimensional dynamic correction logic to support adaptive evolution of scheduling parameters.

[0105] The dynamic updating of the vector control parameter structure is corrected by feedback, so that the device scheduling system has the closed-loop adjustment ability and long-term stable evolution mechanism in complex operation environment.

[0106] Embodiment two:

[0107] Please refer to Figure 2 The exemplary device energy consumption optimization scheduling system based on big data analysis includes:

[0108] The data acquisition and energy consumption modeling module acquires the running state data of the preset number of scheduled device set in the scheduling period, constructs the energy consumption function of each device per unit time according to the acquired running state data, and generates the energy consumption disturbance structure index representing the running disturbance intensity.

[0109] The feature parameter extraction module calculates the input stress dissipation index and the spatial heterogeneity adaptation index according to the energy consumption disturbance structure index and the running state data, constructs the behavior impedance difference factor between any two devices, and forms the device running feature parameter set.

[0110] The potential function construction module constructs the scheduling potential function according to the device running feature parameters, measures the coordination stability level and disturbance risk intensity of the preset candidate device in the scheduling period, and takes the scheduling potential function as the objective function of the scheduling combination optimization.

[0111] The scheduling optimization and instruction generation module selects the device set that meets the adaptability requirements and does not constitute the operation conflict from the scheduled devices according to the scheduling potential function, the structure adaptability threshold and the behavior conflict judgment condition, calculates the marginal potential energy contribution value of each device in the potential function, sorts them according to the contribution value, generates the scheduling priority queue, and outputs the scheduling instruction.

[0112] The feedback correction and parameter updating module acquires the actual energy consumption data of the scheduled device after the completion of the scheduling task, compares the data with the prediction model result at multiple time points, calculates the energy consumption deviation structure, generates the disturbance feedback correction factor according to the energy consumption deviation structure, and updates the input stress dissipation index and the spatial heterogeneity adaptation index, so as to complete the adaptive update of the scheduling parameters in the next scheduling period.

[0113] It should be noted that the device energy consumption optimization scheduling system based on big data analysis provided in the above embodiment and the device energy consumption optimization scheduling method based on big data analysis provided in the above embodiment belong to the same concept, wherein the specific operation execution manner of each module and unit has been described in detail in the method embodiment, which will not be repeated here. The device energy consumption optimization scheduling system based on big data analysis provided in the above embodiment can be realized by different functional modules according to the above functions in actual application, that is, the internal structure of the system is divided into different functional modules to complete all or part of the above described functions, which is not limited here.

[0114] The above embodiments can be realized all or partially by software, hardware, firmware or other any combination. When realized by software, the above embodiments can be realized all or partially in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center and the like containing one or more available medium sets. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0115] It should be understood that the term "and / or" herein only describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone, wherein A and B can be singular or plural. In addition, the character " / " herein generally represents that the front and rear associated objects are in an "or" relationship, but can also represent an "and / or" relationship, which can be understood according to the context.

[0116] In this application, "at least one" means one or more, "multiple" means two or more. "At least one of the following (one)" or the like means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0117] It should be understood that the size of the sequence of the above processes in various embodiments of the present application does not mean the order of execution, and the execution order of the processes should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0118] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0119] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0120] In several embodiments provided in the present application, it should be understood that the disclosed system can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0121] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, i.e. they can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0122] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0123] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0124] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for optimizing equipment energy consumption scheduling based on big data analysis, characterized in that, include: During the scheduling cycle, the operating status data of the set of devices to be scheduled with preset numbers is collected. Based on the collected operating status data, the unit time energy consumption function of each device is constructed, and an energy consumption disturbance structure index characterizing the intensity of operating disturbance is generated. Based on the energy consumption disturbance structure index and operating status data, the input stress dissipation index and spatial heterogeneity adaptation index are calculated. For any two devices, a behavioral impedance difference factor is constructed to form a set of equipment operating characteristic parameters. Based on the equipment operating characteristic parameters, a scheduling potential function is constructed to measure the cooperative stability level and disturbance risk intensity of the preset candidate equipment within the scheduling cycle. The scheduling potential function is used as the objective function for scheduling combinatorial optimization. Based on the scheduling potential energy function, structural adaptability threshold, and behavioral conflict judgment conditions, a set of devices that meet the adaptability requirements and do not constitute operational conflicts is selected from the devices to be scheduled. For each device in the set, its marginal potential energy contribution value in the potential energy function is calculated, and the devices are sorted according to the size of the contribution value to generate a scheduling priority queue and output scheduling instructions. After the scheduling task is completed, the actual energy consumption data of the scheduled equipment is collected, and the data is compared with the prediction model results at multiple time points to calculate the energy consumption deviation structure. Based on the energy consumption deviation structure, a disturbance feedback correction factor is generated to update the aforementioned input stress dissipation index and spatial heterogeneity adaptation index. The adaptive update of the scheduling parameters is completed in the next scheduling cycle.

2. The equipment energy consumption optimization and scheduling method based on big data analysis according to claim 1, characterized in that, During the scheduling cycle, the operating status data of the set of equipment to be scheduled is collected, including continuous sampling of equipment voltage, current, control input strength and disturbance response information over multiple time periods; Based on the collected operational status data, construct the energy consumption function of the device per unit time; By extracting the dynamic characteristics of the energy consumption function and disturbance response information per unit time, an energy consumption disturbance structure index is formed to characterize the intensity of equipment operation disturbance.

3. The equipment energy consumption optimization and scheduling method based on big data analysis according to claim 2, characterized in that, The set of equipment operating characteristic parameters includes: Based on the equipment energy consumption disturbance structure index and the equipment operation status data collected during the scheduling cycle, the input stress dissipation index and spatial heterogeneity adaptation index of each piece of equipment are calculated respectively. Based on the input stress dissipation index and the spatial heterogeneity adaptation index, a behavioral impedance difference factor is constructed for any two devices to quantitatively describe the differences in operating behavior and mutual influence between devices. By comprehensively inputting the stress dissipation index, spatial heterogeneity adaptation index, and inter-equipment behavioral impedance difference factor, a set of equipment operation characteristic parameters is formed, which includes the dynamic characteristics of a single piece of equipment and the coupling relationship between equipment.

4. The equipment energy consumption optimization and scheduling method based on big data analysis according to claim 3, characterized in that, Constructing the scheduling potential function includes: Based on the equipment operation characteristic parameters, a scheduling potential function for the candidate equipment set within the scheduling cycle is constructed. The scheduling potential function comprehensively characterizes the energy consumption dynamic characteristics and adaptability of individual equipment, as well as the mutual coupling relationship between equipment in the operation coordination process. By introducing a cooperative stability structure and a disturbance risk structure, the overall operational coordination of the candidate equipment set and its resilience to external disturbances are measured, respectively. The scheduling potential function is used as the objective function for equipment combination scheduling optimization. The information on the cooperative potential level of equipment is passed to the downstream scheduling priority generation step to support the judgment basis of equipment selection, marginal contribution assessment and scheduling instruction output.

5. The equipment energy consumption optimization and scheduling method based on big data analysis according to claim 1, characterized in that, Based on the evaluation results of the scheduling potential function, the judgment conditions of the structural adaptability threshold and the judgment conditions of the behavioral conflict, a set of equipment that meets the adaptability criteria and does not have behavioral conflicts in the operation state is selected from the set of equipment to be scheduled. For each device in the selected set of devices, the marginal potential energy contribution value of the device is determined based on the change in the corresponding scheduling potential energy function after it is included in the current combination. The screening devices are sorted according to their marginal potential energy contribution values ​​to form a scheduling priority queue; Output the corresponding scheduling instructions based on the scheduling priority queue.

6. The equipment energy consumption optimization and scheduling method based on big data analysis according to claim 5, characterized in that, The marginal potential energy contribution value is constructed based on the current combination structure of the selected set of devices, in which the change in the scheduling potential energy function caused by the target device is introduced; The marginal potential energy contribution value is combined with the input stress dissipation index, spatial heterogeneity adaptation index and behavioral impedance difference factor of the target equipment to each equipment in the selected equipment set, reflecting the cooperative stability change and disturbance coupling strength change caused by the target equipment in the current scheduling structure. The marginal potential energy contribution value is transmitted to the scheduling instruction generation stage as the basis for determining scheduling priority.

7. The equipment energy consumption optimization and scheduling method based on big data analysis according to claim 5, characterized in that, After the scheduling task is completed, collect the actual energy consumption data of all devices that have received scheduling instructions in the previous scheduling cycle in different time periods. Actual energy consumption data includes unit-time energy consumption measurements corresponding to consecutive moments within the scheduling cycle; The actual energy consumption data is matched with the predicted energy consumption data generated based on the unit time energy consumption function on a time-by-time basis to construct an energy consumption deviation structure covering the entire scheduling cycle; Based on the energy consumption change offset trajectory, response abrupt change amplitude and control input coupling relationship presented in the energy consumption deviation structure, a corresponding disturbance feedback correction factor is generated; The input stress dissipation index and spatial heterogeneity adaptation index of each device in the previous cycle are adjusted in multiple dimensions based on the adjustment intensity of the disturbance feedback correction factor to form the parameter structure after feedback correction. The revised parameter structure is used as the input basis for the equipment operation characteristic parameters in the next scheduling cycle, so as to realize the dynamic correction and time-series iteration of scheduling parameters.

8. The equipment energy consumption optimization and scheduling method based on big data analysis according to claim 7, characterized in that, The energy consumption deviation structure includes a set of multi-time-series deviation records formed by mapping the actual energy consumption data and predicted energy consumption data of each device at continuous sampling times within the scheduling cycle; The multi-time-series deviation record set constitutes a two-layer mapping structure. One layer associates the unique device number with the corresponding sampling time sequence, and the other layer associates the actual energy consumption offset value and control input status at each time point. The energy consumption deviation structure is used to identify abnormal energy consumption response segments that occur during actual operation, including deviation accumulation mutation segments, frequent fluctuation segments, and disturbance delay segments. Based on this, multiple types of energy consumption drift tags are provided to trigger the selection of subsequent disturbance feedback correction factor construction strategies and the screening of equipment operation status update paths.

9. The equipment energy consumption optimization and scheduling method based on big data analysis according to claim 7, characterized in that, The disturbance feedback correction factor consists of three types of feedback source information: The first type of feedback source information includes a label indicating the consistency between the stability of the device's energy consumption deviation and its disturbance change trend within a continuous sampling period; The second type of feedback source information includes the synchronous offset trajectory between the history of changes in control input intensity and the difference in energy consumption response; The third type of feedback source information includes the degree of offset coupling between the predicted energy consumption decay rate of the energy consumption structure near the sudden disturbance point and the actual response structure. After being diverted through the feedback channel, the three types of feedback source information correspond to the response adjustment term of the input stress dissipation index, the adaptation compression term of the spatial heterogeneity adaptation index, and the retention term of the prediction model correction path, respectively. A dynamic update vector is constructed through the parameter transfer structure to control the multi-dimensional time-series correction process of the equipment operation characteristic parameters.

10. A device energy consumption optimization scheduling system based on big data analysis, used to implement the device energy consumption optimization scheduling method based on big data analysis as described in any one of claims 1-9, characterized in that, include: Data acquisition and energy consumption modeling module: During the scheduling cycle, it collects the operating status data of the set of devices to be scheduled with preset numbers, constructs the unit time energy consumption function of each device based on the collected operating status data, and generates an energy consumption disturbance structure index that characterizes the intensity of operating disturbance. Feature parameter extraction module: Based on energy consumption disturbance structure index and operating status data, calculate input stress dissipation index and spatial heterogeneity adaptation index, construct behavioral impedance difference factor between any two devices, and form a set of device operating feature parameters; Potential energy function construction module: Constructs a scheduling potential energy function based on equipment operating characteristic parameters, measures the cooperative stability level and disturbance risk intensity of preset candidate equipment within the scheduling cycle, and uses the scheduling potential energy function as the objective function for scheduling combinatorial optimization; Scheduling optimization and instruction generation module: Based on the scheduling potential energy function, structural adaptability threshold and behavioral conflict judgment conditions, it selects a set of devices that meet the adaptability requirements and do not constitute operational conflicts from the devices to be scheduled. For each device in the set, it calculates its marginal potential energy contribution value in the potential energy function, sorts them according to the size of the contribution value, generates a scheduling priority queue, and outputs scheduling instructions. Feedback correction and parameter update module: After the scheduling task is completed, the actual energy consumption data of the scheduled equipment is collected, and the data is compared with the prediction model results at multiple time points. The energy consumption deviation structure is calculated, and the disturbance feedback correction factor is generated based on the energy consumption deviation structure. This factor is used to update the aforementioned input stress dissipation index and spatial heterogeneity adaptation index, and the adaptive update of the scheduling parameters is completed in the next scheduling cycle.

Images