Power resource scheduling method and device, computer device and storage medium

Abstract

The application relates to a power resource scheduling method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring power scheduling demands, power expected powers, power scheduling costs and power risk data of units in a target area; determining target units from the units according to the power scheduling costs and the power risk data of the units; determining power scheduling quantities of the target units according to the power scheduling demands of the units and the target units; acquiring the power scheduling quantities and power operation powers of the target units; determining scheduling data of the target units according to the power scheduling quantities and the power scheduling demands of the target units; determining response powers of the target units according to the power expected powers and the power operation powers of the target units; and updating the power risk data of the target units according to the response powers and the scheduling data. The method can improve the accuracy of power resource scheduling.

Description

Technical Field

[0001] This application relates to the field of power technology, and in particular to a method, apparatus, computer equipment, storage medium and computer program product for dispatching power resources. Background Technology

[0002] With the deepening of the construction of new power systems, user-side resources such as commercial complexes, industrial parks, buildings, and scenic spots are gradually being incorporated into the electricity market trading system, including demand response, spot markets, and ancillary services. Existing energy management technologies are relatively mature in data acquisition and monitoring, enabling real-time acquisition of parameters such as user load and equipment status. In traditional implementations, dispatch decisions typically rely on static adjustable capacity and human experience to determine and submit power dispatch requests. However, relying solely on static data for dispatch decisions can easily lead to discrepancies between submitted capacity and actual performance, resulting in insufficient response completion rates, increased contract deviations, or distorted revenue calculations—a critical technical challenge that urgently needs to be addressed in this field. Summary of the Invention

[0003] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for dispatching power resources to address the aforementioned technical problems.

[0004] Firstly, this application provides a method for dispatching power resources. The method includes:

[0005] Obtain data on power dispatching needs, expected power output, power dispatching costs, and power risks for each unit within the target area;

[0006] Based on the power dispatch costs and power risk data of each unit, target units are identified from among the units; and based on the power dispatch needs of each unit and the target units, the power dispatch volume of each target unit is determined.

[0007] Obtain the power dispatch quantity and power operation power of the target unit;

[0008] Based on the power dispatch volume and power dispatch demand of the target units, determine the dispatch data for each target unit; and based on the expected power and operating power of the target units, determine the response power of each target unit.

[0009] The power risk data of each target unit is updated based on the response power and the scheduling data.

[0010] In one embodiment, obtaining the expected power output and power dispatch cost includes:

[0011] Obtain the historical operating power of each unit, and determine the expected power of each unit based on the historical operating power;

[0012] The scheduling cost and penalty cost of each unit are obtained, and the power scheduling cost is determined based on the scheduling cost and penalty cost; the scheduling cost is used to characterize the cost required to perform power scheduling; the penalty cost is used to characterize the default cost required when the scheduling quantity does not meet the corresponding power scheduling demand.

[0013] In one embodiment, determining the target unit from among the units based on the power dispatch costs and power risk data of each unit includes:

[0014] Based on the power dispatch costs stated by each unit, determine the dispatch priority of each unit in the current time period;

[0015] Based on the power risk data provided by each unit, determine the risk level of each unit in the current time period;

[0016] Based on the scheduling priority and the risk level, select the target unit from among all units whose scheduling priority and risk level both meet the preset requirements.

[0017] In one embodiment, determining the power dispatch volume for each target unit based on the power dispatch needs of each unit and the target unit includes:

[0018] Based on the power dispatch requirements, determine the initial power dispatch quantity for each target unit;

[0019] Based on the power risk data provided by each target unit, determine the risk level of each target unit;

[0020] Based on the risk level, determine the scheduling volume correction coefficient for each target unit;

[0021] The initial power dispatch quantity is adjusted according to the correction coefficient to determine the power dispatch quantity for each target unit.

[0022] In one embodiment, determining the dispatch data for each target unit based on the power dispatch volume and power dispatch demand of the target unit includes:

[0023] Based on the power dispatch volume of each target unit, determine the expected response volume of each target unit;

[0024] Based on the expected response volume and the power dispatching requirements, the dispatching data for each target unit is determined.

[0025] In one embodiment, updating the power risk data of each target unit based on the response power and the scheduling data includes:

[0026] Based on the response power and the scheduling data, candidate risk data are determined;

[0027] If the difference between the candidate risk data and the power risk data exceeds a preset threshold, the power risk data will be updated to candidate risk data.

[0028] Secondly, this application also provides a power resource dispatching device. The device includes:

[0029] The data acquisition module is used to acquire data on power dispatching needs, expected power output, power dispatching costs, and power risks for each unit within the target area.

[0030] The scheduling determination module is used to determine the target unit from among the units based on the power scheduling cost and power risk data of each unit; and to determine the power scheduling amount of each target unit based on the power scheduling needs of each unit and the target unit.

[0031] The data acquisition module is also used to acquire the power dispatch amount and power operation power of the target unit;

[0032] The scheduling determination module is further configured to determine the scheduling data of each target unit based on the power scheduling amount and the power scheduling demand of the target unit; and to determine the response power of each target unit based on the expected power and the operating power of the target unit.

[0033] The risk update module is used to update the power risk data of each target unit based on the response power and the scheduling data.

[0034] In one embodiment, the data acquisition module is further configured to:

[0035] Obtain the historical operating power of each unit, and determine the expected power of each unit based on the historical operating power;

[0036] The scheduling cost and penalty cost of each unit are obtained, and the power scheduling cost is determined based on the scheduling cost and penalty cost; the scheduling cost is used to characterize the cost required to perform power scheduling; the penalty cost is used to characterize the default cost required when the scheduling quantity does not meet the corresponding power scheduling demand.

[0037] In one embodiment, the scheduling determination module is further configured to:

[0038] Based on the power dispatch costs stated by each unit, determine the dispatch priority of each unit in the current time period;

[0039] Based on the power risk data provided by each unit, determine the risk level of each unit in the current time period;

[0040] Based on the scheduling priority and the risk level, select the target unit from among all units whose scheduling priority and risk level both meet the preset requirements.

[0041] In one embodiment, the scheduling determination module is further configured to:

[0042] Based on the power dispatch requirements, determine the initial power dispatch quantity for each target unit;

[0043] Based on the power risk data provided by each target unit, determine the risk level of each target unit;

[0044] Based on the risk level, determine the scheduling volume correction coefficient for each target unit;

[0045] The initial power dispatch quantity is adjusted according to the correction coefficient to determine the power dispatch quantity for each target unit.

[0046] In one embodiment, the scheduling determination module is further configured to:

[0047] Based on the power dispatch volume of each target unit, determine the expected response volume of each target unit;

[0048] Based on the expected response volume and the power dispatching requirements, the dispatching data for each target unit is determined.

[0049] In one embodiment, the risk update module includes:

[0050] Based on the response power and the scheduling data, candidate risk data are determined;

[0051] If the difference between the candidate risk data and the power risk data exceeds a preset threshold, the power risk data will be updated to candidate risk data.

[0052] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the power resource scheduling method as described in any one of the embodiments of this disclosure.

[0053] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the power resource scheduling method as described in any one of the embodiments of this disclosure.

[0054] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the power resource scheduling method as described in any one of the embodiments of this disclosure.

[0055] The aforementioned power resource dispatching methods, devices, computer equipment, storage media, and computer program products achieve precise selection of target units and adaptive allocation of dispatching volume by dynamically integrating dispatching cost and risk data from two dimensions. On the one hand, they reduce overall dispatching expenditures with an economy-oriented approach; on the other hand, they improve response reliability with risk controllability as a constraint, effectively resolving the contradiction between cost optimization and execution deviation in traditional dispatching strategies. Simultaneously, they perform closed-loop updates to power risk data based on actual dispatching response results, enabling the risk assessment model to have continuous learning and dynamic optimization capabilities, thereby gradually improving the system's prediction accuracy and control efficiency for the response behavior of each unit during multiple rounds of dispatching. Attached Figure Description

[0056] Figure 1 This is an application environment diagram of a power resource scheduling method in one embodiment;

[0057] Figure 2 This is a flowchart illustrating a power resource scheduling method in one embodiment;

[0058] Figure 3 This is a flowchart illustrating the implementation of a power resource scheduling method in one embodiment;

[0059] Figure 4 This is a structural block diagram of a power resource dispatching device in one embodiment;

[0060] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0062] The power resource scheduling method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on the cloud or other network servers. Server 104 can obtain power dispatching needs, expected power output, power dispatching costs, and power risk data for each unit within the target area, and execute the power resource dispatching method provided in this application embodiment based on this data. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster composed of multiple servers.

[0063] In one embodiment, such as Figure 2 As shown, a method for scheduling power resources is provided, including the following steps:

[0064] Step S200: Obtain power dispatching demand, expected power output, power dispatching cost, and power risk data for each unit within the target area.

[0065] The target area can include regions encompassing multiple adjustable load resources, such as commercial complexes, industrial parks, commercial buildings, and scenic spots. Each unit refers to an independent adjustable load unit within the target area participating in power dispatch response. Power dispatch demand can include the total power dispatch volume required by each unit within the target area. Expected power output can include the predicted adjustable power value for each unit during its dispatch period. Power dispatch cost can include the comprehensive cost incurred by each unit in participating in this power dispatch. Power risk data can be used to quantify the potential deviation between each unit's actual response capability and its expected performance. Terminals or servers can acquire basic operational data from each unit through the power acquisition system and integrate it with demand information released by the dispatch market to obtain the aforementioned required data.

[0066] In one exemplary embodiment, power dispatching demand can be issued by a power trading center or dispatching agency, and may specifically include the power value and duration corresponding to specific tasks such as peak shaving, valley filling, and frequency regulation; the expected power can be obtained by predictive modeling based on historical operating data of each unit, equipment type, and current operating conditions; the power dispatching cost can comprehensively consider energy consumption cost, equipment loss cost, and opportunity cost; and the power risk data can be dynamically evaluated and generated based on historical performance records, equipment reliability indicators, and real-time status parameters.

[0067] Step S202: Based on the power dispatching costs and power risk data of each unit, determine the target unit from among the units; and based on the power dispatching needs of each unit and the target unit, determine the power dispatching volume of each target unit.

[0068] The target units can include those selected to participate in actual power dispatch response within the current dispatch cycle. When determining target units, the economic efficiency of their dispatch costs and the reliability of their risk data can be considered comprehensively: units with lower dispatch costs and lower risk levels (stronger performance capabilities, etc.) are given priority for inclusion in the target unit set. When determining the power dispatch volume for each target unit, an initial allocation can be made based on the overall power dispatch demand, and the initial allocation can be dynamically adjusted according to the risk level of each unit. This ensures that the total dispatch volume meets the demand while reducing the risk of overall deviation due to insufficient response from individual units.

[0069] In one exemplary embodiment, power dispatch demand can be decomposed into candidate units according to preset rules (such as proportional, priority weighting, etc.) to form an initial power dispatch quantity; and a corresponding dispatch quantity correction coefficient can be calculated based on the power risk data of each unit (such as historical response deviation rate, equipment availability rate, real-time status score, etc.). For example, the higher the risk, the smaller the correction coefficient, thereby reducing its actual dispatch quantity; finally, the actual power dispatch quantity of each target unit is obtained, which serves as the basis for subsequent execution and evaluation.

[0070] In one exemplary embodiment, an optimization objective function can be established based on the total scheduling demand of the target area. The optimization direction is to minimize the total scheduling cost and the overall response deviation risk. The optimal power scheduling quantity of each target unit can be obtained by solving the problem through integer programming or heuristic algorithms. Under the constraint of meeting the total power scheduling demand, the economy and reliability of the scheduling scheme can be balanced.

[0071] Step S204: Obtain the power dispatch quantity and power operation power of the target unit.

[0072] The power operation power can include real-time power data fed back by each target unit during actual dispatch execution, which can be collected through smart meters, energy management systems, or IoT terminal devices. This data is used to measure the actual response of each unit to dispatch instructions and serves as a key input for subsequent calculation of response power and updating of risk data.

[0073] Step S206: Determine the dispatch data of each target unit based on the power dispatch volume and power dispatch demand of the target unit; and determine the response power of each target unit based on the expected power and power operation power of the target unit.

[0074] The dispatch data can include the expected response indicators of each target unit participating in the dispatch this time. Specifically, it can be determined by combining the power dispatch volume allocated to the target unit and the overall power dispatch demand to obtain data such as the unit's dispatch ratio and expected contribution. The response power can be used to characterize the adjustment amount of the target unit's actual execution of dispatch instructions. By subtracting the actual power operation power collected from the expected power power in advance, the actual response power of the target unit during this dispatch process can be obtained, which intuitively reflects the matching between its actual response capability and the expected prediction results.

[0075] In one exemplary embodiment, the response power can be the average value over the scheduling period, or it can be segmented and statistically analyzed according to different time intervals, for subsequent accurate evaluation of the actual response performance of each unit. By comparing the actual response power with the expected response power in the scheduling data, the response deviation of the target unit in this scheduling can be obtained, providing a data basis for subsequent risk data updates.

[0076] Step S208: Update the power risk data of each target unit based on the response power and the scheduling data.

[0077] The response power can include statistical data related to the actual response power obtained by each target unit in this dispatch. Combined with the expected response indicators in the dispatch data predetermined in this dispatch, the actual response deviation of each target unit in this dispatch can be calculated. Based on the deviation results, the power risk data used for subsequent dispatch decisions can be adjusted. If the actual response deviation of a target unit is small, it indicates that the unit's actual performance capability meets or exceeds expectations, and its risk level can be appropriately reduced, thus decreasing its corresponding risk weight in subsequent dispatch decisions. If the actual response deviation is large, its risk level should be increased accordingly, and its dispatch allocation or selection priority should be reduced in subsequent dispatches. By dynamically updating the power risk data of each target unit through rolling iteration, the accuracy and reliability of subsequent power dispatch schemes can be continuously improved.

[0078] In one exemplary embodiment, the response power may also include negative feedback from each unit, such as complaint data information; if equipment failure or sudden load fluctuations prevent the power from being adjusted as required, negative feedback can be directly incorporated into the risk data calculation to further improve the accuracy of risk assessment.

[0079] In one exemplary embodiment, the power risk data can be divided into three levels: high, medium, and low, each corresponding to a different range of dispatch volume correction coefficients. For example, low-risk units (such as historical compliance rate ≥95%, equipment online rate ≥98%) can be assigned a correction coefficient of 1.0 to 1.2, allowing for moderate over-allocation to improve resource utilization efficiency; medium-risk units (compliance rate 80% to 95%) correspond to a coefficient of 0.8 to 1.0, and are executed according to the initial allocation; high-risk units (compliance rate <80% or with multiple default records) have their coefficient reduced to 0.5 to 0.8, significantly compressing their dispatch share. This hierarchical strategy ensures the overall system response reliability while avoiding the idleness of high-quality resources due to excessive conservatism.

[0080] The aforementioned power resource dispatching method achieves precise selection of target units and adaptive allocation of dispatching volume by dynamically integrating dispatching cost and risk data from two dimensions. On the one hand, it reduces overall dispatching expenditure with an economy-oriented approach; on the other hand, it improves response reliability with risk controllability as a constraint, effectively resolving the contradiction between cost optimization and execution deviation in traditional dispatching strategies. Simultaneously, it updates power risk data in a closed loop based on actual dispatching response results, enabling the risk assessment model to have continuous learning and dynamic optimization capabilities. This gradually improves the system's prediction accuracy and control efficiency for the response behavior of each unit during multiple rounds of dispatching.

[0081] In one embodiment, obtaining the expected power output and power dispatch cost includes:

[0082] Obtain the historical operating power of each unit, and determine the expected power of each unit based on the historical operating power.

[0083] The scheduling cost and penalty cost of each unit are obtained, and the power scheduling cost is determined based on the scheduling cost and penalty cost; the scheduling cost is used to characterize the cost required to perform power scheduling; the penalty cost is used to characterize the default cost required when the scheduling quantity does not meet the corresponding power scheduling demand.

[0084] The penalty cost can be quantified based on the default clauses stipulated in the electricity market rules or dispatch agreements, for example, calculated by multiplying the unfulfilled dispatch volume by the unit penalty rate. In practical applications, penalty costs can serve as an important component of electricity dispatch costs, guiding units to be more prudent when applying for dispatch capacity, thereby improving the feasibility and execution rate of the overall dispatch plan. By incorporating penalty costs into the dispatch cost system, not only is the effectiveness of the economic incentive mechanism enhanced, but a more comprehensive decision-making basis is also provided for subsequent selection of target units based on cost-risk joint assessment.

[0085] In one exemplary embodiment, the construction of power risk data can be based on a multi-source information fusion mechanism, including but not limited to historical dispatch response deviation rates, equipment health status scores, real-time communication reliability indicators, and external environmental disturbance factors. For example, for industrial load users, the interruptibility level during different dispatch periods can be quantified by combining the start-up and shutdown characteristics of their production equipment and process continuity requirements; for commercial buildings, their response flexibility can be assessed based on the adjustment margin of flexible loads such as air conditioning and lighting, and user comfort tolerance thresholds. After standardization, the above features are output as a comprehensive risk score through weighted fusion or machine learning models, serving as the core representation of power risk data. The dispatch data can also be further refined into instruction sequences with finer time granularity. For example, in frequency regulation scenarios, the power adjustment slope and steady-state maintenance duration of each target unit in different time windows such as 5 minutes and 15 minutes can be dynamically adjusted according to the real-time change rate of grid frequency fluctuations, and this dynamic instruction set can be incorporated into the dispatch data scope, thereby realizing the evolution from total allocation to a "process-controllable" dispatch mode.

[0086] In this embodiment, historical operating power data is used to model and predict the adjustable capacity of each unit during the dispatch period to obtain the expected power output. Simultaneously, considering the energy consumption, operation and maintenance costs directly incurred by units participating in dispatch, as well as the penalty costs for breach of contract that may be triggered due to insufficient response, a power dispatch cost index is constructed that incorporates both economic and constraint factors. This cost index not only reflects the direct expenditure of the current dispatch task but also embeds the potential costs of non-compliance risks. Therefore, potential breach of contract costs are incorporated into the decision-making process during the target unit selection stage, further improving the economic efficiency of the dispatch plan and reducing potential risk losses in overall dispatch from the source.

[0087] In one embodiment, determining the target unit from among the units based on the power dispatch costs and power risk data of each unit includes:

[0088] Based on the power dispatch costs stated by each unit, the dispatch priority of each unit in the current time period is determined.

[0089] Based on the power risk data provided by each unit, the risk level of each unit in the current period is determined.

[0090] Based on the scheduling priority and the risk level, select the target unit from among all units whose scheduling priority and risk level both meet the preset requirements.

[0091] The scheduling priority can be sorted from low to high based on the unit power scheduling cost, with lower costs resulting in higher priority, thus prioritizing the selection of candidate units with better economic efficiency. Risk levels can be sorted from low to high based on risk scores, retaining only candidate units with risk scores below a preset risk threshold in the candidate set. When selecting target units, they can be filtered sequentially from high to low scheduling priority until the set of candidate target units meets the total power demand for this power scheduling. This approach prioritizes lower-cost units to ensure the overall economy of scheduling, while using risk thresholds to exclude units with excessively high risks, ensuring the overall reliability of the scheduling plan and balancing economic efficiency and safety.

[0092] In one exemplary embodiment, a linkage mechanism between scheduling priority thresholds and risk level thresholds can be set. For example, if a unit's scheduling cost is in the top XX% and its risk score is below XX, it can be automatically included as a target unit. If the scheduling cost is low but the risk is slightly high (e.g., in the medium-risk range), a secondary verification can be performed based on its historical response stability or current equipment status, and it can only be selected if additional conditions are met (e.g., normal real-time communication and no recent fault alarms). This mechanism avoids the possibility of missing high-quality resources or misselecting high-risk units due to single-dimensional screening, further improving the accuracy and robustness of target unit selection.

[0093] In this embodiment, by jointly screening scheduling priority and risk level, the dual constraints of economy and reliability are achieved.

[0094] In one embodiment, determining the power dispatch volume for each target unit based on the power dispatch needs of each unit and the target unit includes:

[0095] Based on the power dispatch requirements, determine the initial power dispatch volume for each target unit.

[0096] Based on the power risk data provided by each target unit, the risk level of each target unit is determined.

[0097] Based on the risk level, determine the scheduling correction coefficient for each target unit.

[0098] The initial power dispatch quantity is adjusted according to the correction coefficient to determine the power dispatch quantity for each target unit.

[0099] The initial power dispatch volume can be derived from the total power dispatch demand based on the number of target units, dispatch priority, or preset allocation rules; the risk level can be divided into three levels—high, medium, and low—based on the aforementioned power risk data, or a continuous scoring method can be adopted; the dispatch volume correction coefficient is negatively correlated with the risk level, that is, the higher the risk, the smaller the correction coefficient, thereby reducing the actual dispatch volume of the unit to control the overall response deviation risk.

[0100] In one exemplary embodiment, the correction coefficient can be set in the form of a piecewise function: for low-risk units, the correction coefficient is 1.0 to 1.2, allowing them to undertake tasks slightly higher than the initial allocation to improve the utilization rate of high-quality resources; for medium-risk units, the correction coefficient is 0.8 to 1.0, basically maintaining the initial allocation; and for high-risk units, a correction coefficient of 0.5 to 0.8 is applied, significantly reducing their dispatch share. Through this mechanism, the load allocation of each target unit is dynamically optimized under the premise of meeting the overall dispatch requirements, achieving synergistic optimization of economy and reliability. The adjusted power dispatch quantity can also meet the physical constraints of each unit, such as the upper limit of maximum adjustable power, the lower limit of minimum technical output, and the ramp rate limit. If the corrected dispatch quantity exceeds the feasible operating range of a target unit, it needs to be cut to the boundary value, and the unallocated portion is redistributed to other eligible target units to ensure the conservation of the total dispatch quantity and the feasibility of the scheme.

[0101] In this embodiment, the initial allocation of scheduling quotas is dynamically adjusted based on the actual risk level of each unit. This allows low-risk, high-quality units to undertake more scheduling tasks and fully utilize their response capabilities. At the same time, the scheduling allocation quotas for high-risk units are reduced to prevent their excessive response deviations from affecting the completion of the overall scheduling tasks. Based on meeting the overall scheduling requirements, the economy and reliability of the scheme are further balanced, and the fault tolerance of the scheduling results and the overall execution effect are improved.

[0102] In one embodiment, determining the dispatch data for each target unit based on the power dispatch volume and power dispatch demand of the target unit includes:

[0103] Based on the power dispatch volume of each target unit, determine the expected response volume of each target unit.

[0104] Based on the expected response volume and the power dispatching requirements, the dispatching data for each target unit is determined.

[0105] The expected response volume can include the expected power adjustment range corresponding to the dispatch volume allocated to the target unit, which can be used as a benchmark value to evaluate the response effect of the target unit. By comparing the expected response volume of a single target unit with the total power dispatch demand, the dispatch proportion of that target unit can be obtained. This data can be used for subsequent attribution analysis of the overall response deviation, clarifying the contribution of each target unit to the overall response deviation, and providing support for the accurate updating of risk data.

[0106] In one exemplary embodiment, the scheduling data can also include refined instructions in the time dimension. For example, the expected response amount can be decomposed into power adjustment targets for multiple sub-periods, and different response delay tolerance windows can be set based on the adjustment characteristics of each unit. For energy storage devices with rapid response capabilities, they can be required to complete more than 90% of the power adjustment within one minute after the scheduling instruction is issued; while for industrial loads with slower response, they are allowed to gradually reach the target value within 5 to 10 minutes. Such timing constraint information can serve as an important component of the scheduling data, guiding dynamic monitoring and deviation judgment during subsequent actual execution. In addition, the scheduling data can also be associated with metadata such as communication channel identifiers, control protocol types, and feedback reporting frequencies to ensure that scheduling instructions can be accurately issued and execution status can be obtained in a timely manner, thereby providing complete data link support for closed-loop verification.

[0107] In this embodiment, by converting the power dispatch volume of each target unit into specific expected response volumes and combining it with the overall power dispatch demand, structured dispatch data is generated, including the unit's dispatch proportion, contribution weight, and time-dimensional allocation plan. This dispatch data not only clarifies the responsibility boundaries of each unit in this dispatch task but also provides a benchmark for the subsequent quantitative evaluation of the actual execution effect.

[0108] In one embodiment, updating the power risk data of each target unit based on the response power and the scheduling data includes:

[0109] Based on the response power and the scheduling data, candidate risk data are determined;

[0110] If the difference between the candidate risk data and the power risk data exceeds a preset threshold, the power risk data will be updated to candidate risk data.

[0111] In this embodiment, by comparing the actual response power with the expected scheduling data, the performance of the target unit in this scheduling is quantified, and candidate risk data reflecting its latest response capability is generated.

[0112] In one exemplary embodiment, the power resource scheduling method can be as follows: Figure 3 The implementation shown may specifically include:

[0113] Step S300: Collect user-side load, adjustable capacity, response events, market prices, contract coverage, equipment status, and user feedback records within the target area to form a multi-source energy dataset.

[0114] Step S302 involves cleaning the multi-source energy dataset, filling in missing values, removing abnormal loads, and aligning the time granularity to construct a user load feature profile.

[0115] In one exemplary embodiment, the user load profile includes at least one of baseline load, adjustable capacity, comfort sensitivity parameters, willingness to participate curve, reliability potential curve, and pricing surface.

[0116] The baseline load is generated by weighting the historical loads of the target users under similar dates, time periods, or temperature conditions. Its expression is:

[0117]

[0118] In the formula: The baseline load for user i in time period t; The historical load for the k-th similar sample day; is the sample weight; K is the number of similar samples per day.

[0119] Step S304: Calculate baseline load, adjustable capacity, comfort cost, participation willingness probability, and user bidding function based on user load characteristic profiles to generate a candidate response resource pool.

[0120] In one exemplary embodiment, the adjustable capacity is determined by the baseline load, minimum guaranteed load, equipment constraints, and comfort constraints. The adjustable capacity for user i during time period t is expressed as:

[0121]

[0122] In the formula: Adjustable capacity; To ensure minimum load; Adjustable capacity on the equipment side; Adjustable capacity to meet comfort boundaries. Furthermore, the comfort cost is used to characterize the environmental or operational impact on users due to load adjustments. The comfort cost function is expressed as:

[0123]

[0124] In the formula: For comfort costs; For environmental comfort deviation; To adjust the power; As an indicator variable for sensitive business hours; , , User profile parameters are defined. Further, the participation willingness probability in step S304 is determined based on the compensation price, notification lead time, comfort cost, and historical reliability score. The participation willingness probability is expressed as:

[0125]

[0126] In the formula: For participation probability; To compensate for price or market gains; To allow for advance notice; Score historical reliability; , , , These are the model parameters.

[0127] Step S306: By combining market type, response date, response power lower limit, market price, contract deviation cost, and default penalty cost, an electricity market declaration optimization model is established and a declaration strategy is generated.

[0128] In one exemplary embodiment, the application optimization model aims to maximize the expected net revenue from aggregated resources. The application revenue objective function is expressed as:

[0129]

[0130] In the formula: The number of reported responses during time period t; Let be the decision variable for whether user i participates in time period t; As a penalty for breach of contract; Costs related to contract or plan deviations; , The cost weight is used. Furthermore, the application optimization model satisfies constraints on application capacity, user reliability, and number of participations. The application capacity constraint is expressed as:

[0131]

[0132] The constraints on user reliability and participation frequency are expressed as follows:

[0133]

[0134] In the formula: and These are the minimum and maximum application capacities, respectively. The minimum reliability threshold; This refers to the number of times a user participates on a given day. This represents the maximum number of times a user can participate in a given day.

[0135] Step S308: After the response is executed, collect the actual reduction amount, participation status, number of complaints, feedback type and feedback reason, calculate the user response reliability index and generate a user reliability list.

[0136] In one exemplary embodiment, user response reliability metrics include engagement, completion rate, complaint rate, intensity of negative feedback, and historical performance stability. The overall user reliability score is expressed as:

[0137]

[0138] In the formula: For participation; To lower the completion rate; For the complaint rate; The intensity of negative feedback; To ensure historical stability in fulfilling obligations; to These are the weight parameters.

[0139] Step S310: Perform closed-loop correction on subsequent application capacity, candidate user weight, response notification time, compensation price, and response period based on user response reliability indicators.

[0140] In one exemplary embodiment, the closed-loop correction adjusts the user's effective adjustable capacity based on a reliability score. The user's effective adjustable capacity is expressed as:

[0141]

[0142] In the formula: This is the corrected effective adjustable capacity; , , This is an adjustment factor; when the reliability score decreases or the complaint rate increases, the system automatically reduces the weight of subsequent user reports.

[0143] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0144] Based on the same inventive concept, this application also provides a power resource scheduling apparatus for implementing the power resource scheduling method described above. The solution provided by this apparatus is similar to the solution described in the above method; therefore, the specific limitations of one or more power resource scheduling apparatus embodiments provided below can be found in the limitations of the power resource scheduling method described above, and will not be repeated here.

[0145] In one embodiment, such as Figure 4As shown, a power resource dispatching device 400 is provided, including: a data acquisition module 401, a dispatching determination module 403, and a risk update module 405, wherein:

[0146] The data acquisition module is used to acquire data on power dispatching needs, expected power output, power dispatching costs, and power risks for each unit within the target area.

[0147] The scheduling determination module is used to determine the target unit from among the units based on the power scheduling cost and power risk data of each unit; and to determine the power scheduling amount of each target unit based on the power scheduling needs of each unit and the target unit.

[0148] The data acquisition module is also used to acquire the power dispatch amount and power operation power of the target unit;

[0149] The scheduling determination module is further configured to determine the scheduling data of each target unit based on the power scheduling amount and the power scheduling demand of the target unit; and to determine the response power of each target unit based on the expected power and the operating power of the target unit.

[0150] The risk update module is used to update the power risk data of each target unit based on the response power and the scheduling data.

[0151] In one embodiment, the data acquisition module is further configured to:

[0152] Obtain the historical operating power of each unit, and determine the expected power of each unit based on the historical operating power;

[0153] The scheduling cost and penalty cost of each unit are obtained, and the power scheduling cost is determined based on the scheduling cost and penalty cost; the scheduling cost is used to characterize the cost required to perform power scheduling; the penalty cost is used to characterize the default cost required when the scheduling quantity does not meet the corresponding power scheduling demand.

[0154] In one embodiment, the scheduling determination module is further configured to:

[0155] Based on the power dispatch costs stated by each unit, determine the dispatch priority of each unit in the current time period;

[0156] Based on the power risk data provided by each unit, determine the risk level of each unit in the current time period;

[0157] Based on the scheduling priority and the risk level, select the target unit from among all units whose scheduling priority and risk level both meet the preset requirements.

[0158] In one embodiment, the scheduling determination module is further configured to:

[0159] Based on the power dispatch requirements, determine the initial power dispatch quantity for each target unit;

[0160] Based on the power risk data provided by each target unit, determine the risk level of each target unit;

[0161] Based on the risk level, determine the scheduling volume correction coefficient for each target unit;

[0162] The initial power dispatch quantity is adjusted according to the correction coefficient to determine the power dispatch quantity for each target unit.

[0163] In one embodiment, the scheduling determination module is further configured to:

[0164] Based on the power dispatch volume of each target unit, determine the expected response volume of each target unit;

[0165] Based on the expected response volume and the power dispatching requirements, the dispatching data for each target unit is determined.

[0166] In one embodiment, the risk update module includes:

[0167] Based on the response power and the scheduling data, candidate risk data are determined;

[0168] If the difference between the candidate risk data and the power risk data exceeds a preset threshold, the power risk data will be updated to candidate risk data.

[0169] Each module in the aforementioned power resource dispatching device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0170] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for scheduling power resources. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0171] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0172] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0173] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0174] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0175] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for dispatching power resources, characterized in that, The method includes: Obtain data on power dispatching needs, expected power output, power dispatching costs, and power risks for each unit within the target area; Based on the power dispatch costs and power risk data of each unit, target units are identified from among the units; and based on the power dispatch needs of each unit and the target units, the power dispatch volume of each target unit is determined. Obtain the power dispatch quantity and power operation power of the target unit; Based on the power dispatch volume and power dispatch demand of the target units, determine the dispatch data for each target unit; and based on the expected power and operating power of the target units, determine the response power of each target unit. The power risk data of each target unit is updated based on the response power and the scheduling data.

2. The method according to claim 1, characterized in that, The acquisition of the expected power output and power dispatch cost includes: Obtain the historical operating power of each unit, and determine the expected power of each unit based on the historical operating power; The scheduling cost and penalty cost of each unit are obtained, and the power scheduling cost is determined based on the scheduling cost and penalty cost; the scheduling cost is used to characterize the cost required to perform power scheduling; the penalty cost is used to characterize the default cost required when the scheduling quantity does not meet the corresponding power scheduling demand.

3. The method according to claim 1, characterized in that, The process of determining the target unit from among the units based on the power dispatch costs and power risk data of each unit includes: Based on the power dispatch costs stated by each unit, determine the dispatch priority of each unit in the current time period; Based on the power risk data provided by each unit, determine the risk level of each unit in the current time period; Based on the scheduling priority and the risk level, select the target unit from among all units whose scheduling priority and risk level both meet the preset requirements.

4. The method according to claim 1, characterized in that, The step of determining the power dispatch volume for each target unit based on the power dispatch needs of each unit and the target unit includes: Based on the power dispatch requirements, determine the initial power dispatch quantity for each target unit; Based on the power risk data provided by each target unit, determine the risk level of each target unit; Based on the risk level, determine the scheduling volume correction coefficient for each target unit; The initial power dispatch quantity is adjusted according to the correction coefficient to determine the power dispatch quantity for each target unit.

5. The method according to claim 1, characterized in that, The step of determining the dispatch data for each target unit based on the power dispatch volume and power dispatch demand of the target unit includes: Based on the power dispatch volume of each target unit, determine the expected response volume of each target unit; Based on the expected response volume and the power dispatching requirements, the dispatching data for each target unit is determined.

6. The method according to claim 1, characterized in that, The step of updating the power risk data of each target unit based on the response power and the scheduling data includes: Based on the response power and the scheduling data, candidate risk data are determined; If the difference between the candidate risk data and the power risk data exceeds a preset threshold, the power risk data will be updated to candidate risk data.

7. A power resource dispatching device, characterized in that, The device includes: The data acquisition module is used to acquire data on power dispatching needs, expected power output, power dispatching costs, and power risks for each unit within the target area. The scheduling determination module is used to determine the target unit from among the units based on the power scheduling cost and power risk data of each unit; and to determine the power scheduling amount of each target unit based on the power scheduling needs of each unit and the target unit. The data acquisition module is also used to acquire the power dispatch amount and power operation power of the target unit; The scheduling determination module is further configured to determine the scheduling data of each target unit based on the power scheduling amount and the power scheduling demand of the target unit; and to determine the response power of each target unit based on the expected power and the operating power of the target unit. The risk update module is used to update the power risk data of each target unit based on the response power and the scheduling data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images