A power grid quality and efficiency evaluation decision-making method and system based on multiple scenarios

Abstract

The present invention provides a method and system for evaluating the quality and efficiency of a power grid based on multiple scenarios, and relates to the technical field of power grid operation and management. The method includes: determining multiple current operation scenarios, operation data, and current operation costs of a power grid according to the operation environment and operation status of the power grid, and determining the influence weights of the current operation scenarios and operation data in the current operation costs according to the current operation scenarios and operation data; determining the current cost allocation data of the power grid according to the influence weights corresponding to the current operation scenarios and operation data; obtaining the future cost allocation data of a preset future time period through an operation scenario prediction model according to the current cost allocation data; obtaining the cost change data of the power grid according to the future cost allocation data and the current cost allocation data; and determining the control decision of the power grid according to the cost change data. By allocating weights to multiple power grid operation scenarios, the unstable factors of the power grid are reduced, the equipment failure rate is reduced, and the overall reliability of the power grid is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid operation management, and in particular to a power grid quality and efficiency evaluation decision-making method and system based on multiple scenarios. Background Art

[0002] In the operation and management of modern power systems, the quality and efficiency evaluation decision of power grid equipment such as transformers, transmission lines and distribution equipment is one of the key factors to improve power grid efficiency and ensure stable operation of the power grid. In order to reasonably allocate power grid resources, the quality and efficiency evaluation decision of power grid equipment involves reasonable cost calculation and accurate optimization decision of power grid equipment.

[0003] In the prior art, cost allocation is usually based on simplified linear models and empirical formulas. However, methods relying on linear models or empirical formulas often ignore the complexity and dynamics of grid operation. When the grid operates in a complex scenario with multiple scenarios superimposed, such as weather conditions, load demand, grid equipment status and other factors that have a comprehensive impact on grid operation, the above methods are difficult to adapt to the changing operating scenarios and conditions, resulting in large errors in the cost allocation and optimization decisions of grid equipment, and thus making the grid quality and efficiency evaluation decisions inconsistent with the current operating status of the grid equipment. Summary of the invention

[0004] The problem solved by the present invention is how to improve the accuracy of cost calculation and optimization decision-making for power grid equipment.

[0005] To solve the above problems, the present invention provides a multi-scenario based power grid quality and efficiency evaluation decision method, comprising:

[0006] Determine multiple current operation scenarios, operation data and current operation costs of the power grid according to the power grid operation environment and power grid operation status, wherein the current operation scenario includes current weather, current time and current energy market price, and the power grid operation status includes current power grid load demand and current power grid equipment data;

[0007] Determine the influence weights of the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price on the current operating cost, respectively, according to the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price;

[0008] Determine the current cost allocation data of the power grid according to the current weather, the current power grid load demand, the current power grid equipment data, the current time and the current energy market price, combined with the impact weights corresponding to the current weather, the current power grid load demand, the current power grid equipment data, the current time and the current energy market price respectively;

[0009] According to the current cost allocation data, obtaining future cost allocation data for a preset future time period by running a scenario prediction model;

[0010] Obtaining cost change data of the power grid according to the future cost allocation data and the current cost allocation data;

[0011] A control decision of the power grid is determined according to the cost change data.

[0012] Optionally, determining, according to the current weather, the current grid load demand, the current grid equipment data, the current time, and the current energy market price, the influence weights of the current weather, the current grid load demand, the current grid equipment data, the current time, and the current energy market price on the current operating cost, respectively, includes:

[0013] Inputting the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price into the input layer of the quality and efficiency evaluation model;

[0014] The current weather, the current grid load demand, the current grid equipment data, the current time, and the current energy market price are encoded through the input layer to obtain corresponding data features, and the data features are input into the convolution layer of the quality and efficiency evaluation model;

[0015] The data features are processed through an attention mechanism to obtain attention weights corresponding to the current weather, the current grid load demand, the current grid equipment data, the current time, and the current energy market price;

[0016] Through the attention weight, the influence weights of the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price on the current operating cost are obtained.

[0017] Optionally, the determining the current cost allocation data of the power grid according to the current weather, the current power grid load demand, the current power grid equipment data, the current time and the current energy market price, in combination with the influence weights respectively corresponding to the current weather, the current power grid load demand, the current power grid equipment data, the current time and the current energy market price, comprises:

[0018] Mapping the impact weights corresponding to the current weather, the current grid load demand, the current grid equipment data, the current time, and the current energy market price to the current operating cost, respectively, to obtain the proportion corresponding to each impact weight;

[0019] Determine the cost data of the current weather, the current grid load demand, the current grid equipment data, the current time, and the current energy market price in the current operating cost, respectively, according to the product of the current operating cost and the proportion of each of the impact weights;

[0020] The cost data corresponding to the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price are used as the current cost allocation data of the grid.

[0021] Optionally, obtaining future cost allocation data for a preset future time period by running a scenario prediction model according to the current cost allocation data includes:

[0022] Input the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price into the operation scenario prediction model for prediction, and obtain the future weather, future grid load demand, future grid equipment data, future time and future energy market price within the preset future time period;

[0023] Inputting the future weather, the future grid load demand, the future grid equipment data, the future time and the future energy market price into the quality and efficiency evaluation model, and determining the influence weights of the future weather, the future grid load demand, the future grid equipment data, the future time and the future energy market price on the future operating cost through the quality and efficiency evaluation model;

[0024] And according to the proportion of the impact weight in the future operating cost in the future operating cost, the cost data of the future weather, the future grid load demand, the future grid equipment data, the future time and the future energy market price in the preset future time period are obtained;

[0025] And based on the cost data, the future cost allocation data is determined.

[0026] Optionally, obtaining the cost change data of the power grid according to the future cost allocation data and the current cost allocation data includes:

[0027] Determining whether it is necessary to regulate the operation of the power grid based on the future cost allocation data;

[0028] If so, determining the target operating cost of the power grid in the preset future time period according to the future cost allocation data;

[0029] According to the influence weights of the future weather, the future grid load demand, the future grid equipment data, the future time, and the future energy market price on the future operating cost, the target operating cost is apportioned to obtain cost data of the future weather, the future grid load demand, the future grid equipment data, the future time, and the future energy market price in the target operating cost;

[0030] The cost change data is determined according to the future weather, the future grid load demand, the future grid equipment data, the future time, and the cost data of the future energy market price in the target operating cost.

[0031] Optionally, judging whether it is necessary to regulate the operation of the power grid by using the future cost allocation data includes:

[0032] Determining the future operating cost according to the future cost allocation data;

[0033] Determining whether the future operating cost is less than or equal to a preset cost threshold;

[0034] If yes, it is determined that there is no need to regulate the operation of the power grid, and the future cost allocation data for the preset future time period is continuously acquired;

[0035] If not, it is determined that the operation of the power grid needs to be regulated.

[0036] Optionally, determining the cost change data according to the future weather, the future grid load demand, the future grid equipment data, the future time, and the cost data of the future energy market price in the target operating cost includes:

[0037] Determine the cost fluctuation data corresponding to the future weather, the future grid load demand, the future grid equipment data, the future time, and the future energy market price, respectively, according to the cost data of the future weather, the future grid load demand, the future grid equipment data, the future time, and the future energy market price in the target operating cost and the cost data in the current operating cost;

[0038] The cost fluctuation data of the future weather, the future grid load demand, the future grid equipment data, the future time and the future energy market price are used as the cost variation data.

[0039] Optionally, determining a control decision of the power grid according to the cost change data includes:

[0040] Inputting the future weather, the future grid load demand, the future grid equipment data, the future time, and the cost fluctuation data of the future energy market price into a deep learning network model;

[0041] Obtaining an estimated control cost of the power grid through the deep learning network model;

[0042] Determining whether the future operating cost is less than a preset cost threshold after the power grid is regulated according to the estimated regulation cost;

[0043] If so, the estimated regulation cost is used as the final regulation cost, and the regulation decision of the power grid is generated according to the final regulation cost.

[0044] Optionally, generating the regulation decision of the power grid according to the final regulation cost includes:

[0045] According to the final control cost, obtaining the control cost of all grid devices in the grid in the preset future time period;

[0046] A control decision of each of the grid devices is determined according to the control cost of each of the grid devices, and the control decisions of all the grid devices are used as the control decisions of the grid.

[0047] The present invention also provides a power grid quality and efficiency evaluation decision system based on multiple scenarios, comprising:

[0048] a data acquisition unit, configured to determine a plurality of current operation scenarios, operation data, and current operation costs of the power grid according to the power grid operation environment and the power grid operation status, wherein the current operation scenario includes the current weather, the current time, and the current energy market price, and the power grid operation status includes the current power grid load demand and the current power grid equipment data;

[0049] a weight allocation unit, configured to determine, according to the current weather, the current grid load demand, the current grid equipment data, the current time, and the current energy market price, the influence weights of the current weather, the current grid load demand, the current grid equipment data, the current time, and the current energy market price on the current operating cost;

[0050] A first data processing unit is used to determine the current cost allocation data of the power grid according to the current weather, the current power grid load demand, the current power grid equipment data, the current time and the current energy market price, in combination with the influence weights corresponding to the current weather, the current power grid load demand, the current power grid equipment data, the current time and the current energy market price respectively;

[0051] A prediction unit, configured to obtain future cost allocation data for a preset future time period by running a scenario prediction model according to the current cost allocation data;

[0052] A second data processing unit, configured to obtain cost change data of the power grid according to the future cost allocation data and the current cost allocation data;

[0053] A decision-making unit is used to determine a control decision of the power grid according to the cost change data.

[0054] The power grid quality and efficiency evaluation decision-making method and system based on multiple scenarios of the present invention determine multiple current operation scenarios, operation data and current operation costs of the power grid according to the power grid operation environment and power grid operation conditions, and accurately reflect the actual operation status and cost influencing factors of the power grid by comprehensively considering multiple operation scenarios including weather conditions, time, energy market price, power grid load demand and power grid equipment data, thereby improving the accuracy of cost calculation. A dynamic weight allocation strategy is adopted to dynamically analyze the influence weights of influencing factors according to different operation scenarios, so as to more flexibly adapt to changes in power grid operation and improve the applicability and effectiveness of decision-making. Combined with the operation scenario prediction model, according to the current cost allocation data, the future cost allocation data of the preset future time period is obtained through the operation scenario prediction model, which not only analyzes the current data, but also predicts the cost allocation situation in the future time period, provides forward-looking decision support for power grid management, and formulates more reasonable and effective power grid regulation decisions based on accurate cost allocation data and cost change analysis, optimizes power grid operation, reduces unnecessary economic expenditures, and improves the economic efficiency of power grid operation. The present invention utilizes the influence weights of operation scenarios and operation data in the current operation costs to accurately determine cost allocation and optimized control decisions, which can effectively reduce unstable factors in power grid operation and reduce equipment failure rates, thereby improving the overall reliability of the power grid, providing refined and efficient decision-making support for power grid operations, and helping to achieve energy conservation and consumption reduction in the power grid and reduce carbon emissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flow chart of a power grid quality and efficiency evaluation decision method based on multiple scenarios in one embodiment of the present invention;

[0056] Figure 2 It is a structural diagram of a power grid quality and efficiency evaluation decision system based on multiple scenarios in another embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0058] Combination Figure 1 As shown, the present invention provides a power grid quality and efficiency evaluation decision-making method based on multiple scenarios, including:

[0059] Based on the power grid operating environment and the power grid operating conditions, multiple current operating scenarios, operating data and current operating costs of the power grid are determined, wherein the current operating scenarios include current weather, current time and current energy market prices, and the power grid operating conditions include current power grid load demand and current power grid equipment data.

[0060] Specifically, the various environments and conditions of power grid operation are comprehensively considered to establish the current operation scenario, operation data and current operation cost of the power grid. This process involves in-depth analysis of the specific state of the power grid at a specific moment, including the current weather conditions, time nodes and price changes in the energy market. For example, extreme weather (hot or cold) causes a surge in electricity demand, and the energy demand patterns at night and during the day are also significantly different. At the same time, fluctuations in energy market prices directly affect the operation cost. In addition, the current load demand of the power grid and the equipment status (for example, the operating efficiency of the generator set and the loss of the transmission line, etc.) are also key factors in determining the operation cost. By accurately evaluating these operation scenarios and data, in-depth research on the complexity of power grid operation provides a comprehensive and detailed basis for further cost allocation, efficiency optimization and decision-making, ensuring that the decision-making process is closely aligned with the actual operation status of the power grid.

[0061] According to the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price, determine the influence weights of the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price on the current operating cost.

[0062] Specifically, in the decision-making method for power grid quality and efficiency evaluation based on multiple scenarios, a core link is to confirm the relative importance of each influencing factor in the current operation cost of the power grid, that is, the respective impact weight, so as to accurately quantify the specific contribution of current weather conditions, power grid load demand, power grid equipment status, current time and energy market price to the specific operation cost of the power grid. Among them, the determination of impact weight is a highly dynamic and data-driven process, which requires in-depth insights into historical data, operation experience and real-time operation environment. For example, extreme heat waves may cause a surge in air conditioning use, resulting in a sharp increase in power grid load demand. At this time, weather conditions and power grid load will receive higher weights; similarly, if it enters the peak power consumption period, the current time will have a particularly significant impact on the cost; and when energy prices are high, the weight of energy market price factors will also increase. Equipment data, such as transformer efficiency and transmission line losses, will also be weighted according to their contribution to the overall cost. By weighting these factors, a more accurate power grid operation cost model can be constructed, which not only captures the independent impact of each factor, but also evaluates the possible interactions between them.

[0063] The current cost sharing data of the power grid is determined based on the current weather, the current power grid load demand, the current power grid equipment data, the current time and the current energy market price, combined with the impact weights corresponding to the current weather, the current power grid load demand, the current power grid equipment data, the current time and the current energy market price respectively.

[0064] Specifically, in the process of determining the current cost sharing data of the power grid, the focus is on organically combining the weight of each influencing factor with its corresponding actual data. Specifically, it is necessary to collect and analyze the current weather (such as temperature, humidity, wind speed, etc.), the actual load demand of the power grid (i.e., the power consumption of users), equipment data (including the status and performance indicators of generators, transformers, transmission lines, etc.), the current time (peak and valley periods), and the price information of the energy market. Subsequently, based on the specific weight of each influencing factor, this information is calculated and integrated to obtain the cost sharing directly related to the current power grid operation. For example, if the hot weather leads to an increase in cooling load, the weight of the weather factor will occupy a larger proportion in the calculation; if it is during the peak power usage period, the weight of the current time will be higher; and when energy prices rise, the impact of market prices will be more significantly reflected in the cost sharing. Ultimately, these weighted data information work together to form the current cost sharing of the power grid.

[0065] Based on the current cost allocation data, future cost allocation data for a preset future time period is obtained by running a scenario prediction model.

[0066] Specifically, the current cost allocation data is applied to the operation scenario prediction model in order to predict and preset the cost allocation of the power grid in the future. The operation scenario prediction model usually combines historical data, time series analysis, machine learning algorithms or other advanced prediction methods to process and analyze patterns and trends in historical and real-time data. Using this model, the cost allocation in the next period of time can be predicted based on the current cost allocation, taking into account factors such as weather forecasts, predicted load change trends, equipment maintenance plans and possible market price changes. For example, if the weather forecast shows that there will be a heat wave in the next few days, the model may predict that the resulting increase in air conditioning use will increase load demand, resulting in an increase in cost allocation; while if there is an oversupply in the energy market or prices are expected to fall, the model may predict that the cost allocation will be reduced. Such predictions not only help grid operators prepare in advance for possible cost fluctuations, but also guide the optimization of long-term operation and maintenance strategies to ensure that the power grid can operate in an efficient and cost-effective manner.

[0067] The cost change data of the power grid is obtained according to the future cost allocation data and the current cost allocation data.

[0068] Specifically, by using the future cost allocation data obtained by the operation scenario prediction model and comparing it with the current cost allocation data, the change data of the power grid cost can be obtained. This reveals the increase or decrease trend that the power grid cost may face in the preset future time period, and which factors will have the greatest impact on the cost change. The determination of cost change data includes the evaluation of the evolution of operating costs from the perspective of overall economic efficiency, such as the interaction of factors such as seasonal weather changes, expected energy market fluctuations, expected changes in power grid load demand, or aging of power grid equipment. By dynamically depicting the contours of cost changes, the operation and maintenance plan of the power grid can be adjusted more strategically to achieve cost control and risk management. For example, future cost estimates show that load demand will increase significantly during specific peak hours, and demand-side management or peak-shaving measures may need to be taken to reduce cost impact. Based on the cost change data, the regulation decision of the power grid is determined.

[0069] Specifically, after analyzing the future and current cost allocations, if it is found that specific factors or periods will lead to significant cost increases, corresponding measures can be taken, namely, grid regulation decisions. These measures may include increasing power generation to meet expected high load demand, activating demand response programs to reduce loads during peak hours, optimizing the scheduling of generators, and updating or upgrading equipment that is inefficient and causes cost increases. During low-load periods, the grid may optimize costs by reducing power generation or choosing a more economical energy mix.

[0070] The power grid quality and efficiency evaluation decision method based on multiple scenarios of the present invention determines multiple current operation scenarios, operation data and current operation costs of the power grid according to the power grid operation environment and power grid operation conditions, and comprehensively considers multiple operation scenarios including weather conditions, time, energy market price, power grid load demand and number of power grid equipment to accurately reflect the actual operation status and cost influencing factors of the power grid, thereby improving the accuracy of cost allocation. A dynamic weight allocation strategy is adopted to dynamically analyze the influence weights of influencing factors according to different operation scenarios, which can more flexibly adapt to changes in power grid operation and improve the applicability and effectiveness of decision-making. Combined with the operation scenario prediction model, according to the current cost allocation data, the future cost allocation data of the preset future time period is obtained through the operation scenario prediction model. Not only is the current data analyzed, but the cost allocation situation in the future time period can also be predicted, providing forward-looking decision support for power grid management, and formulating more reasonable and effective power grid regulation decisions based on accurate cost allocation data and cost change analysis, optimizing power grid operation, reducing unnecessary economic expenditures, and improving the economic efficiency of power grid operation. Through accurate cost allocation and optimized control decisions, the present invention can effectively reduce unstable factors in power grid operation and reduce equipment failure rates, thereby improving the overall reliability of the power grid, providing refined and efficient decision-making support for power grid operations, and helping to achieve energy conservation and consumption reduction and reduce carbon emissions in the power grid.

[0071] In an embodiment of the present invention, determining the influence weights of the current weather, the current grid load demand, the current grid equipment data, the current time, and the current energy market price on the current operating cost respectively according to the current weather, the current grid load demand, the current grid equipment data, the current time, and the current energy market price includes:

[0072] Inputting the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price into the input layer of the quality and efficiency evaluation model;

[0073] The current weather, the current grid load demand, the current grid equipment data, the current time, and the current energy market price are encoded through the input layer to obtain corresponding data features, and the data features are input into the convolution layer of the quality and efficiency evaluation model;

[0074] The data features are processed through an attention mechanism to obtain attention weights corresponding to the current weather, the current grid load demand, the current grid equipment data, the current time, and the current energy market price;

[0075] Through the attention weight, the influence weights of the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price on the current operating cost are obtained.

[0076] In this embodiment, first, various factors, such as current weather, grid load demand, grid equipment data, current time and energy market price, are collected and input into the input layer of the quality and efficiency evaluation model. At the input layer, these data are encoded and the corresponding data features are extracted. This step can use traditional encoding methods or deep learning technology to achieve more complex feature extraction. Then, the extracted data features are sent to the convolution layer of the model. In the convolution layer, the data can be further processed, and the convolution operation can be used to capture local feature relationships and patterns. Next, the attention mechanism is introduced. This is a technology that uses the model to focus on the important parts of the data. The data features are processed through the attention mechanism to calculate the relative importance of each factor to the current operating cost, that is, the attention weight. These weights are ultimately manifested as weights that affect the cost of the power grid, providing a quantitative measure of the proportion of each factor in the cost.

[0077] The multi-scenario-based power grid quality and efficiency assessment decision-making method of the present invention ensures that the model can adaptively identify which factors are the most critical under specific operating conditions through the application of the attention mechanism, thereby assigning higher weights to these factors.

[0078] In an embodiment of the present invention, the current cost allocation data of the power grid is determined according to the current weather, the current power grid load demand, the current power grid equipment data, the current time, and the current energy market price, in combination with the influence weights corresponding to the current weather, the current power grid load demand, the current power grid equipment data, the current time, and the current energy market price, including:

[0079] Mapping the impact weights corresponding to the current weather, the current grid load demand, the current grid equipment data, the current time, and the current energy market price to the current operating cost, respectively, to obtain the proportion corresponding to each impact weight;

[0080] Determine the cost data of the current weather, the current grid load demand, the current grid equipment data, the current time, and the current energy market price in the current operating cost, respectively, according to the product of the current operating cost and the proportion of each of the impact weights;

[0081] The cost data corresponding to the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price are used as the current cost allocation data of the grid.

[0082] In this embodiment, when the above method for determining the current cost allocation data of the power grid is specifically implemented, the weights corresponding to each influencing factor (current weather, power grid load demand, power grid equipment data, current time and energy market price) are first mapped to the current operating cost, and the proportion of each factor in the total cost is calculated. This step involves multiplying the weight of each factor by its corresponding cost data to obtain the specific contribution of the factor to the total cost. In a preferred embodiment of the present invention, if the weight of the current weather is 0.3, and the cost caused by the weather factor is 1 million yuan, then the allocation of the weather factor in the current operating cost is 300,000 yuan. Similarly, other factors are also calculated similarly according to their respective weights. Finally, the cost data of all factors are summarized to obtain the current cost allocation data of the power grid. This process ensures that the calculation of the cost data not only takes into account the independent impact of each factor, but also reflects their comprehensive role in the actual operating cost.

[0083] The multi-scenario-based power grid quality and efficiency evaluation decision-making method of the present invention improves the accuracy and transparency of cost data by accurately calculating the contribution of each influencing factor to the power grid operation cost. Compared with traditional fixed weights or empirical formulas, this method can more truly reflect the dynamic changes and complex interactions of various factors in power grid operation, thereby making the cost data more consistent with actual operation conditions.

[0084] In the embodiment of the present invention, obtaining future cost allocation data for a preset future time period by running a scenario prediction model according to the current cost allocation data includes:

[0085] Input the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price into the operation scenario prediction model for prediction, and obtain the future weather, future grid load demand, future grid equipment data, future time and future energy market price within the preset future time period;

[0086] Inputting the future weather, the future grid load demand, the future grid equipment data, the future time and the future energy market price into the quality and efficiency evaluation model, and determining the influence weights of the future weather, the future grid load demand, the future grid equipment data, the future time and the future energy market price on the future operating cost through the quality and efficiency evaluation model;

[0087] And according to the proportion of the impact weight in the future operating cost in the future operating cost, the cost data of the future weather, the future grid load demand, the future grid equipment data, the future time and the future energy market price in the preset future time period are obtained;

[0088] And based on the cost data, the future cost allocation data is determined.

[0089] In this embodiment, when implementing the above-mentioned method for predicting future cost sharing data, the current key factors - weather, grid load demand, grid equipment data, time and energy market price - are first input into the operation scenario prediction model. This model relies on technical means such as historical data, weather forecasts, load prediction algorithms and market trend analysis to predict the changing trends of these key factors in the future. For example, future weather conditions are predicted based on seasonal changes, load prediction technology is used to estimate future grid load demand, and future grid equipment conditions and energy prices are predicted considering equipment aging, maintenance plans and energy market dynamics. Then, these future prediction values ​​are input into the quality and efficiency evaluation model, and the influence weight of each factor in the future operating cost is determined by the model analysis. These weights reflect the relative impact of each factor on the future total cost, so that the cost sharing of each factor in the future can be calculated.

[0090] The multi-scenario-based power grid quality and efficiency evaluation decision-making method of the present invention improves the foresight and strategic nature of power grid operation management by accurately predicting the contribution of various factors to costs in the future, and helps to achieve the long-term goals of cost control and optimized operations.

[0091] In the embodiment of the present invention, obtaining the cost change data of the power grid according to the future cost allocation data and the current cost allocation data includes:

[0092] Determining whether it is necessary to regulate the operation of the power grid based on the future cost allocation data;

[0093] If so, determining the target operating cost of the power grid in the preset future time period according to the future cost allocation data;

[0094] According to the influence weights of the future weather, the future grid load demand, the future grid equipment data, the future time, and the future energy market price on the future operating cost, the target operating cost is apportioned to obtain cost data of the future weather, the future grid load demand, the future grid equipment data, the future time, and the future energy market price in the target operating cost;

[0095] The cost change data is determined according to the future weather, the future grid load demand, the future grid equipment data, the future time, and the cost data of the future energy market price in the target operating cost.

[0096] In this embodiment, first, by comparing the future cost allocation data with the current cost allocation data, it is evaluated whether there is a significant cost change trend, and then it is determined whether the operation of the power grid needs to be regulated. If the forecast shows that the future cost will increase significantly, measures need to be taken for regulation. Next, based on the future cost allocation data, a target operating cost is set, and this target cost is intended to achieve cost savings by optimizing the operation of the power grid. Then, using the weights of the impact of each factor in the cost in the future, the target operating cost is allocated to each factor, and the specific allocation of each factor in the target operating cost is calculated. This step involves allocating the target cost according to the weight of each factor to ensure that the contribution of each factor to the target cost is reasonable. Finally, by comparing the allocation of each factor in the target operating cost in the future with the current cost allocation, the cost change data of the power grid is determined, which reveals the possible increase or decrease trend of the power grid cost and which factors have the greatest impact on the cost change.

[0097] The multi-scenario-based power grid quality and efficiency evaluation decision-making method of the present invention provides a clear cost control target and implementation path by pre-setting the target operating cost and allocating it to various influencing factors. It can adjust the power grid operation strategy in a targeted manner, such as optimizing power generation scheduling, adjusting load management measures or upgrading equipment to achieve cost savings and efficiency improvements.

[0098] In the embodiment of the present invention, judging whether it is necessary to regulate the operation of the power grid according to the future cost allocation data includes:

[0099] Determining the future operating cost according to the future cost allocation data;

[0100] Determining whether the future operating cost is less than or equal to a preset cost threshold;

[0101] If yes, it is determined that there is no need to regulate the operation of the power grid, and the future cost allocation data for the preset future time period is continuously acquired;

[0102] If not, it is determined that the operation of the power grid needs to be regulated.

[0103] In this embodiment, the future operating cost is calculated based on the future cost allocation data. This step involves summarizing the cost allocation of each factor in the future to obtain a total cost forecast value. Next, the future operating cost is compared with a preset cost threshold, where the cost threshold is a pre-set cost upper limit that represents the cost level that the grid operator considers acceptable. If the future operating cost is less than or equal to this threshold, the system determines that it is not necessary to regulate the operation of the grid, and continues to monitor and obtain the cost allocation data for the future time period to maintain continuous attention to the operation cost of the grid. On the contrary, if the future operating cost exceeds the preset threshold, the system will trigger a signal indicating that the operation of the grid needs to be regulated to avoid cost overruns. This may include measures such as adjusting the power generation plan, optimizing load management, adjusting the energy procurement strategy, or performing equipment maintenance and upgrades to reduce costs and ensure the economic operation of the grid. By setting a cost threshold and monitoring the future cost allocation data in real time, an automated cost control mechanism is provided. When the future cost forecast exceeds the threshold, the system can automatically identify it, which helps to avoid cost overruns and potential economic losses in a timely manner.

[0104] The multi-scenario-based power grid quality and efficiency evaluation decision-making method of the present invention facilitates a better understanding of cost dynamics by continuously monitoring future cost allocation data, thereby making more accurate and timely decisions. This proactive cost management method not only improves the economic efficiency of power grid operations, but also enhances the power grid's ability to respond to market and technological changes, providing a guarantee for the stability and sustainable development of the power grid.

[0105] In the embodiment of the present invention, the cost change data is determined according to the cost data of the future weather, the future grid load demand, the future grid equipment data, the future time, and the future energy market price in the target operating cost, including:

[0106] Determine the cost fluctuation data corresponding to the future weather, the future grid load demand, the future grid equipment data, the future time, and the future energy market price, respectively, according to the cost data of the future weather, the future grid load demand, the future grid equipment data, the future time, and the future energy market price in the target operating cost and the cost data in the current operating cost;

[0107] The cost fluctuation data of the future weather, the future grid load demand, the future grid equipment data, the future time and the future energy market price are used as the cost variation data.

[0108] In this embodiment, the forecast data of various factors related to the future, including weather, grid load demand, grid equipment data, time, and energy market prices, are first analyzed with the expected allocation in the target operating cost. These expected allocation data are obtained based on the operation scenario prediction model, reflecting the cost adjustment needs caused by changes in these factors in a certain period of time in the future. Next, these expected allocation data are compared with the actual allocation data in the current operating cost. Through this comparison, the extent of the increase or decrease in cost that each factor may cause in the future compared to the current can be specifically quantified. For example, if the future weather forecast shows extreme temperatures, it may mean that the use of heating and cooling equipment will increase greatly, which will affect the load demand and equipment operating efficiency, resulting in cost fluctuations. Through such analysis, the cost fluctuations corresponding to each factor can be calculated and summarized in detail, and finally a set of cost change data is obtained, which reflects the specific change trend of the grid operation cost caused by the changes in these key factors in the future.

[0109] The multi-scenario-based power grid quality and efficiency evaluation decision-making method of the present invention can significantly improve the economic benefits of power grid operation and the stability of the system through active cost management and regulation strategies, and ensure the security and sustainability of energy supply.

[0110] In an embodiment of the present invention, determining the control decision of the power grid according to the cost change data includes:

[0111] Inputting the future weather, the future grid load demand, the future grid equipment data, the future time, and the cost fluctuation data of the future energy market price into a deep learning network model;

[0112] Obtaining an estimated control cost of the power grid through the deep learning network model;

[0113] Determining whether the future operating cost is less than a preset cost threshold after the power grid is regulated according to the estimated regulation cost;

[0114] If so, the estimated regulation cost is used as the final regulation cost, and the regulation decision of the power grid is generated according to the final regulation cost.

[0115] In this embodiment, the cost change data of future weather, grid load demand, grid equipment data, time and energy market price are first input into the deep learning network model. This model may be a trained neural network that can process and analyze complex data relationships and predict the cost impact that grid control measures may bring. The model will calculate the expected control cost of the grid after taking different control measures based on the input cost change data. These measures may include adjusting power generation, optimizing load management, changing energy procurement strategies, or performing equipment maintenance and upgrades. Then, the expected control cost is compared with the preset cost threshold to evaluate whether the control measures can control future operating costs within an acceptable range. If the expected control cost indicates that the cost threshold requirements can be met after control, then this expected control cost will be adopted as the final control cost, and specific grid control decisions will be generated based on this, such as adjusting power generation plans, implementing demand response measures, or optimizing grid structure. If not, it means that the expected control cost does not meet the cost requirements, and the deep learning network model needs to be readjusted and a new expected control cost needs to be regenerated. If the expected control cost does not meet the cost requirements, the deep learning network model needs to be readjusted and a new expected control cost needs to be regenerated. This includes adjusting the model's parameters, adding more training data, and improving the model's algorithm. By continuously optimizing the deep learning network model, the model's prediction accuracy and reliability can be improved, thereby generating an estimated control cost that better meets cost requirements.

[0116] The multi-scenario-based power grid quality and efficiency evaluation decision-making method of the present invention uses a deep learning network model to predict the regulation cost, providing a powerful tool to evaluate and select the optimal regulation strategy. By accurately predicting the cost impact of regulation measures, it ensures that the power grid operates in the best economic and efficient state.

[0117] In an embodiment of the present invention, generating the control decision of the power grid according to the final control cost includes:

[0118] According to the final control cost, obtaining the control cost of all grid devices in the grid in the preset future time period;

[0119] A control decision of each of the grid devices is determined according to the control cost of each of the grid devices, and the control decisions of all the grid devices are used as the control decisions of the grid.

[0120] In this embodiment, a detailed cost analysis is performed based on the final control cost determined to ensure that the control costs that may be involved in each device in the power grid (including generators, transformers, transmission lines, etc.) in the preset future time period are obtained. This step requires a deep understanding of the operation mode of the power grid, the characteristics of the equipment and its impact on the overall efficiency of the power grid, so that the corresponding costs can be allocated for the operation and control of different equipment and parts. Next, the specific control costs of each power grid equipment are evaluated, and control decisions are made based on their cost-effectiveness, priority, and impact on the stability and safety of power grid operation. This may involve strategies such as adjusting the output power of certain equipment, changing the equipment maintenance plan, or optimizing the coordinated operation between equipment. The control decisions of all equipment are aggregated to form a global control strategy for the power grid, ensuring that the entire power grid can operate with the best cost-effectiveness and meet the power supply and demand in the future.

[0121] The multi-scenario-based power grid quality and efficiency evaluation decision-making method of the present invention can further reduce the operation and maintenance costs of the power grid and improve the economy and competitiveness of the power system by accurately controlling the regulation cost and implementing the optimal operation strategy for each device.

[0122] Combination Figure 2 As shown, the present invention also provides a power grid quality and efficiency evaluation decision system based on multiple scenarios, including:

[0123] a data acquisition unit, configured to determine a plurality of current operation scenarios, operation data, and current operation costs of the power grid according to the power grid operation environment and the power grid operation status, wherein the current operation scenario includes the current weather, the current time, and the current energy market price, and the power grid operation status includes the current power grid load demand and the current power grid equipment data;

[0124] a weight allocation unit, configured to determine, according to the current weather, the current grid load demand, the current grid equipment data, the current time, and the current energy market price, the influence weights of the current weather, the current grid load demand, the current grid equipment data, the current time, and the current energy market price on the current operating cost;

[0125] A first data processing unit is used to determine the current cost allocation data of the power grid according to the current weather, the current power grid load demand, the current power grid equipment data, the current time and the current energy market price, in combination with the influence weights corresponding to the current weather, the current power grid load demand, the current power grid equipment data, the current time and the current energy market price respectively;

[0126] A prediction unit, configured to obtain future cost allocation data for a preset future time period by running a scenario prediction model according to the current cost allocation data;

[0127] A second data processing unit, configured to obtain cost change data of the power grid according to the future cost allocation data and the current cost allocation data;

[0128] A decision-making unit is used to determine a control decision of the power grid according to the cost change data.

[0129] The power grid quality and efficiency evaluation decision-making method and system based on multiple scenarios of the present invention determine multiple current operation scenarios, operation data and current operation costs of the power grid according to the power grid operation environment and power grid operation conditions, and comprehensively consider multiple operation scenarios including weather conditions, time, energy market price, power grid load demand and number of power grid equipment to accurately reflect the actual operation status and cost influencing factors of the power grid, thereby improving the accuracy of cost allocation. A dynamic weight allocation strategy is adopted to dynamically analyze the influence weights of influencing factors according to different operation scenarios, so as to more flexibly adapt to changes in power grid operation and improve the applicability and effectiveness of decision-making. Combined with the operation scenario prediction model, according to the current cost allocation data, the future cost allocation data of the preset future time period is obtained through the operation scenario prediction model, which not only analyzes according to the current data, but also predicts the cost allocation situation in the future time period, provides forward-looking decision support for power grid management, and formulates more reasonable and effective power grid regulation decisions based on accurate cost allocation data and cost change analysis, optimizes power grid operation, reduces unnecessary economic expenditures, and improves the economic efficiency of power grid operation. Through accurate cost allocation and optimized control decisions, the present invention can effectively reduce unstable factors in power grid operation and reduce equipment failure rates, thereby improving the overall reliability of the power grid, providing refined and efficient decision-making support for power grid operations, and helping to achieve energy conservation and consumption reduction and reduce carbon emissions in the power grid.

[0130] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0131] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0132] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A decision-making method for power grid quality and efficiency evaluation based on multiple scenarios, characterized in that: include: Determine multiple current operation scenarios, operation data and current operation costs of the power grid according to the power grid operation environment and power grid operation status, wherein the current operation scenario includes current weather, current time and current energy market price, and the power grid operation status includes current power grid load demand and current power grid equipment data; According to the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price, determine the influence weights of the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price in the current operating cost respectively; wherein, specifically comprising: inputting the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price into the input layer of the quality and efficiency evaluation model; encoding the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price through the input layer to obtain corresponding data features, and inputting the data features into the convolution layer of the quality and efficiency evaluation model; processing the data features through the attention mechanism to obtain the attention weights corresponding to the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price; through the attention weights, obtaining the influence weights of the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price in the current operating cost respectively; According to the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price, combined with the influence weights corresponding to the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price, the current cost allocation data of the grid is determined; wherein, specifically including: mapping the influence weights corresponding to the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price to the current operating cost, and obtaining the proportion corresponding to each influence weight; determining the cost data of the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price in the current operating cost according to the product of the current operating cost and the proportion of each influence weight; using the cost data corresponding to the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price as the current cost allocation data of the grid; According to the current cost allocation data, the future cost allocation data of the preset future time period is obtained by running the scenario prediction model; which specifically includes: inputting the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price into the running scenario prediction model for prediction, and obtaining the future weather, future grid load demand, future grid equipment data, future time and future energy market price within the preset future time period; inputting the future weather, the future grid load demand, the future grid equipment data, the future time and the future energy market price into the quality and efficiency evaluation model, and determining the influence weights of the future weather, the future grid load demand, the future grid equipment data, the future time and the future energy market price on the future operating cost through the quality and efficiency evaluation model; and obtaining the cost data of the future weather, the future grid load demand, the future grid equipment data, the future time and the future energy market price in the preset future time period according to the proportion of the influence weights in the future operating cost; and determining the future cost allocation data according to the cost data; Obtaining cost change data of the power grid according to the future cost allocation data and the current cost allocation data; A control decision of the power grid is determined according to the cost change data.

2. The multi-scenario-based power grid quality and efficiency evaluation decision-making method according to claim 1 is characterized in that: The step of obtaining the cost change data of the power grid according to the future cost allocation data and the current cost allocation data includes: Determining whether it is necessary to regulate the operation of the power grid based on the future cost allocation data; If so, determining the target operating cost of the power grid in the preset future time period according to the future cost allocation data; According to the influence weights of the future weather, the future grid load demand, the future grid equipment data, the future time, and the future energy market price on the future operating cost, the target operating cost is apportioned to obtain cost data of the future weather, the future grid load demand, the future grid equipment data, the future time, and the future energy market price in the target operating cost; The cost change data is determined according to the future weather, the future grid load demand, the future grid equipment data, the future time, and the cost data of the future energy market price in the target operating cost.

3. The multi-scenario-based power grid quality and efficiency evaluation decision-making method according to claim 2 is characterized in that: The determining whether it is necessary to regulate the operation of the power grid based on the future cost allocation data includes: Determining the future operating cost according to the future cost allocation data; Determining whether the future operating cost is less than or equal to a preset cost threshold; If yes, it is determined that there is no need to regulate the operation of the power grid, and the future cost allocation data for the preset future time period is continuously acquired; If not, it is determined that the operation of the power grid needs to be regulated.

4. The multi-scenario-based power grid quality and efficiency evaluation decision-making method according to claim 3 is characterized in that: The determining the cost change data according to the cost data of the future weather, the future grid load demand, the future grid equipment data, the future time and the future energy market price in the target operating cost includes: Determine the cost fluctuation data corresponding to the future weather, the future grid load demand, the future grid equipment data, the future time, and the future energy market price, respectively, according to the cost data of the future weather, the future grid load demand, the future grid equipment data, the future time, and the future energy market price in the target operating cost and the cost data in the current operating cost; The cost fluctuation data of the future weather, the future grid load demand, the future grid equipment data, the future time and the future energy market price are used as the cost variation data.

5. The multi-scenario-based power grid quality and efficiency evaluation decision-making method according to claim 4 is characterized in that: Determining the control decision of the power grid according to the cost change data includes: Inputting the future weather, the future grid load demand, the future grid equipment data, the future time, and the cost fluctuation data of the future energy market price into a deep learning network model; Obtaining an estimated control cost of the power grid through the deep learning network model; Determining whether the future operating cost is less than a preset cost threshold after the power grid is regulated according to the estimated regulation cost; If so, the estimated regulation cost is used as the final regulation cost, and the regulation decision of the power grid is generated according to the final regulation cost.

6. The multi-scenario-based power grid quality and efficiency evaluation decision-making method according to claim 5 is characterized in that: Generating the regulation decision of the power grid according to the final regulation cost includes: According to the final control cost, obtaining the control cost of all grid devices in the grid in the preset future time period; A control decision of each of the grid devices is determined according to the control cost of each of the grid devices, and the control decisions of all the grid devices are used as the control decisions of the grid.

7. A multi-scenario-based power grid quality and efficiency evaluation decision system, characterized in that: include: a data acquisition unit, configured to determine a plurality of current operation scenarios, operation data, and current operation costs of the power grid according to the power grid operation environment and the power grid operation status, wherein the current operation scenario includes the current weather, the current time, and the current energy market price, and the power grid operation status includes the current power grid load demand and the current power grid equipment data; A weight allocation unit, for determining the influence weights of the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price on the current operating cost, respectively, according to the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price; wherein, specifically comprising: inputting the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price into the input layer of the quality and efficiency evaluation model; encoding the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price through the input layer to obtain corresponding data features, and inputting the data features into the convolution layer of the quality and efficiency evaluation model; processing the data features through the attention mechanism to obtain the attention weights corresponding to the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price; obtaining the influence weights of the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price in the current operating cost, respectively, through the attention weights; A first data processing unit is used to determine the current cost allocation data of the power grid according to the current weather, the current power grid load demand, the current power grid equipment data, the current time and the current energy market price, in combination with the influence weights corresponding to the current weather, the current power grid load demand, the current power grid equipment data, the current time and the current energy market price; wherein, specifically including: mapping the influence weights corresponding to the current weather, the current power grid load demand, the current power grid equipment data, the current time and the current energy market price to the current operating cost, and obtaining the proportion corresponding to each influence weight; determining the cost data of the current weather, the current power grid load demand, the current power grid equipment data, the current time and the current energy market price in the current operating cost according to the product of the current operating cost and the proportion of each influence weight; using the cost data corresponding to the current weather, the current power grid load demand, the current power grid equipment data, the current time and the current energy market price as the current cost allocation data of the power grid; A prediction unit is used to obtain future cost allocation data for a preset future time period through an operation scenario prediction model according to the current cost allocation data; specifically comprising: inputting the current weather, the current grid load demand, the current grid equipment data, the current time and the current energy market price into the operation scenario prediction model for prediction, and obtaining the future weather, future grid load demand, future grid equipment data, future time and future energy market price within the preset future time period; inputting the future weather, the future grid load demand, the future grid equipment data, the future time and the future energy market price into the quality and efficiency evaluation model, and determining the influence weights of the future weather, the future grid load demand, the future grid equipment data, the future time and the future energy market price on the future operating cost through the quality and efficiency evaluation model; and obtaining the cost data of the future weather, the future grid load demand, the future grid equipment data, the future time and the future energy market price in the preset future time period according to the proportion of the influence weights in the future operating cost; and determining the future cost allocation data according to the cost data; A second data processing unit, configured to obtain cost change data of the power grid according to the future cost allocation data and the current cost allocation data; A decision-making unit is used to determine a control decision of the power grid according to the cost change data.

Images