Electric energy meter centralized distribution management method and system, computer equipment and storage medium

Abstract

The invention provides an electric energy meter centralized distribution management method and system, computer equipment and a storage medium, and belongs to the technical field of inventory management. The method comprises the following steps: predicting the electric energy meter demand quantity of a subordinate purchasing unit in the same time period in the future; the method comprises the following steps: dynamically calculating a reference stock and a safe stock based on a demand quantity, forming a total stock quantity of a superior purchasing unit, taking a delivery quantity in a target time period as a decision variable, constructing a target function for minimizing logistics cost and / or stockout and overstock penalty, and solving the target function by adopting an optimization algorithm to obtain a stock quantity of the superior purchasing unit; and determining the electric energy meter delivery quantity of the superior purchasing unit to the subordinate purchasing unit in the target time period. Through data-driven prediction and intelligent optimization scheduling, accurate supply and demand matching of the electric energy meter is realized, the logistics cost is reduced, the emergency demand response capability is improved, and the method is suitable for efficient management of metering assets in the power industry.

Description

Technical Field

[0001] The present invention belongs to the technical field of inventory management, and particularly relates to a method, a system, a computer device and a storage medium for centralized distribution management of electric energy meters. Background Art

[0002] With the continuous development of the smart grid and the gradual improvement of the power user demand, electric energy meters play a key role in the meter installation, meter replacement and maintenance links of power companies in each city and county. Usually, the superior procurement unit (such as the provincial metering center) undertakes the responsibilities of unified procurement and centralized reserve of electric energy meters, and distributes them according to the actual needs of the subordinate procurement units (such as each subordinate procurement unit). However, the existing distribution management mode and inventory control often have the following problems:

[0003] Supply-demand imbalance: In the case of peak periods or sudden demands (such as centralized meter installation for new projects), the subordinate procurement units often suffer from shortages of electric energy meters; in the low-demand period, they may hoard a large amount of inventory, resulting in too high warehousing costs and capital occupation.

[0004] Lack of prediction and optimization means: Many units still rely on experience or extensive scheduling, insufficiently utilize historical demand data, and do not use effective algorithm models to optimize the distribution plan, resulting in frequent back-and-forth scheduling or emergency distribution situations. Summary of the Invention

[0005] In view of the deficiencies in the prior art, the present invention provides a method, a system, a computer device and a storage medium for centralized distribution management of electric energy meters.

[0006] In a first aspect, the present invention provides a method for centralized distribution management of electric energy meters, including:

[0007] Obtain the historical distribution volume, installation requirements, inventory consumption records and safety inventory requirements of electric energy meters between the superior procurement unit and the subordinate procurement units within a target time period, so as to predict the demand for electric energy meters of the subordinate procurement units in the future same period by using a time series model or a machine learning algorithm;

[0008] Determine the benchmark inventory and safety inventory of electric energy meters according to the demand for electric energy meters of the subordinate procurement units in the future same period, and take the sum of the benchmark inventory and the safety inventory of electric energy meters as the total inventory of electric energy meters required by the superior procurement unit in the future same period;

[0009] Taking the distribution volume within the target time period as a decision variable, construct an objective function for minimizing the logistics cost and / or the penalty for out-of-stock and overstock according to the electric energy meter inventory balance equation, the upper and lower limits of the electric energy meter inventory and the constraint of the total inventory of electric energy meters of the superior procurement unit;

[0010] An optimization algorithm is used to solve the objective function of minimizing the logistics cost and / or the penalties for out-of-stock and overstock, so as to determine the number of electricity meters distributed by the superior purchasing unit to the inferior purchasing unit within the target time period.

[0011] Optionally, based on the electricity meter demand of the inferior purchasing unit in the future same period, the benchmark inventory and safety inventory of the electricity meters are determined, and the sum of the benchmark inventory and the safety inventory of the electricity meters is used as the total inventory of electricity meters required by the superior purchasing unit in the future same period, including:

[0012] Calculate the benchmark inventory I of the electricity meters according to the following formula base :

[0013]

[0014] where L is the number of days for the superior purchasing unit to replenish the electricity meters; T is the number of days in the target time period; N is the total number of inferior purchasing units; D i,t is the predicted demand for electricity meters of the inferior purchasing unit i on the t-th day;

[0015] Calculate the safety inventory I of the electricity meters according to the following formula safe :

[0016]

[0017] where x is the safety factor; σ is the standard deviation of the historical demand residual or the prediction error.

[0018] Optionally, with the distribution volume within the target time period as the decision variable, according to the electricity meter inventory balance equation, the upper and lower limits of the electricity meter inventory, and the constraint of the total inventory of electricity meters of the superior purchasing unit, an objective function of minimizing the logistics cost and / or the penalties for out-of-stock and overstock is constructed, including:

[0019] Construct an expression for the electricity meter inventory balance equation:

[0020] I i,t = I i,t-1 + x i,t - D i,t ;

[0021] where I i,t is the inventory of electricity meters of the inferior purchasing unit i at the end of the t-th day; is the minimum value of the safety value of the electricity meter installation demand; is the maximum value of the safety value of the electricity meter installation demand; I i,t-1 is the inventory of electricity meters of the inferior purchasing unit i at the end of the (t - 1)-th day; x i,t represents the number of electricity meters distributed by the superior purchasing unit to the inferior purchasing unit i on the t-th day; Di,t is the predicted demand for electric energy meters of the lower-level purchasing unit i on the t-th day;

[0022] Construct the constraint on the total inventory of electric energy meters of the upper-level purchasing unit:

[0023]

[0024] where I prov,t-1 represents the available inventory of electric energy meters of the upper-level purchasing unit at the beginning of the t-th day;

[0025] Construct the objective function M for minimizing the logistics cost 1 expression:

[0026]

[0027] where T is the number of days in the target time period; N is the total number of lower-level purchasing units; C i is the unit transportation cost;

[0028] Construct the objective function M that simultaneously considers the shortage penalty and the excess inventory penalty 2 expression:

[0029]

[0030] where Penalty(I i,t ) represents the penalty for the inventory below or exceeding ; α is the first weight; β is the second weight.

[0031] Optionally, the first aspect further includes:

[0032] Execute the delivery according to the distribution quantity of electric energy meters from the upper-level purchasing unit to the lower-level purchasing unit within the target period, and obtain the actual arrival and inventory information of the electric energy meters fed back by the lower-level purchasing unit;

[0033] When the demand or inventory deviation of the lower-level purchasing unit exceeds the threshold, recalculate the demand prediction model and the safety inventory, and iteratively adjust the distribution plan.

[0034] In a second aspect, the present invention provides an electric energy meter centralized distribution management system, including:

[0035] The first acquisition module is used to acquire the historical distribution volume, installation requirements, inventory consumption records, and safety inventory requirements of electric energy meters between the upper-level purchasing unit and the lower-level purchasing unit within the target time period, so as to predict the demand for electric energy meters of the lower-level purchasing unit in the future same-period time period by using a time series model or a machine learning algorithm;

[0036] The first determination module is configured to determine the benchmark inventory and safety inventory of the electricity meters according to the electricity meter demand of the lower-level purchasing units in the same period in the future, and use the sum of the benchmark inventory and the safety inventory of the electricity meters as the total inventory of the electricity meters required by the upper-level purchasing unit in the same period in the future;

[0037] The construction module is configured to use the distribution volume in the target period as the decision variable, and construct an objective function for minimizing the logistics cost and / or the penalty for out-of-stock and overstock according to the electricity meter inventory balance equation, the upper and lower limits of the electricity meter inventory, and the constraint of the total inventory of the electricity meters of the upper-level purchasing unit;

[0038] The second determination module is configured to solve the objective function for minimizing the logistics cost and / or the penalty for out-of-stock and overstock by using an optimization algorithm to determine the distribution quantity of the electricity meters from the upper-level purchasing unit to the lower-level purchasing units in the target period.

[0039] Optionally, the first determination module includes:

[0040] The first calculation unit is configured to calculate the benchmark inventory I of the electricity meters according to the following formula base :

[0041]

[0042] where L is the number of days for the upper-level purchasing unit to replenish the electricity meters; T is the number of days in the target period; N is the total number of lower-level purchasing units; D i,t is the predicted demand for electricity meters of the lower-level purchasing unit i on the t-th day;

[0043] The second calculation unit is configured to calculate the safety inventory I of the electricity meters according to the following formula safe :

[0044]

[0045] where x is the safety factor; σ is the standard deviation of the historical demand residual or the prediction error.

[0046] Optionally, the construction module includes:

[0047] The first construction unit is configured to construct an expression of the electricity meter inventory balance equation:

[0048] I i,t = I i,t-1 + x i,t - D i,t ;

[0049] where I i,t is the inventory of the electricity meters of the lower-level purchasing unit i at the end of the t-th day; is the minimum value of the safety value of the electricity meter installation demand; is the maximum value of the safety value for the electricity meter installation requirement; I i,t-1 is the inventory of electricity meters of the lower-level purchasing unit i at the end of the (t - 1)-th day; x i,t represents the number of electricity meters distributed by the upper-level purchasing unit to the lower-level purchasing unit i on the t-th day; D i,t is the predicted demand for electricity meters of the lower-level purchasing unit i on the t-th day;

[0050] The second construction unit is used to construct the constraint on the total inventory of electricity meters of the upper-level purchasing unit:

[0051]

[0052] where I prov,t-1 represents the available inventory of electricity meters of the upper-level purchasing unit at the beginning of the t-th day;

[0053] The third construction unit is used to construct the objective function M for minimizing the logistics cost 1 expression:

[0054]

[0055] where T is the number of days in the target time period; N is the total number of lower-level purchasing units; C i is the unit transportation cost;

[0056] The fourth construction unit is used to construct the objective function M that simultaneously considers the shortage penalty and the excess inventory penalty 2 expression:

[0057]

[0058] where Penalty(I i,t ) represents the penalty for the inventory below or exceeding ; α is the first weight; β is the second weight.

[0059] Optionally, the second aspect further includes:

[0060] The second acquisition module is used to execute the delivery according to the number of electricity meters distributed by the upper-level purchasing unit to the lower-level purchasing unit within the target period, and acquire the actual arrival and inventory information of the electricity meters fed back by the lower-level purchasing unit;

[0061] The adjustment module is used to recalculate the demand prediction model and the safety inventory and iteratively adjust the delivery plan when the electricity meter demand or inventory deviation of the lower-level purchasing unit exceeds the threshold.

[0062] In a third aspect, the present invention provides a computer device, including a processor and a memory; wherein, when the processor executes the computer program stored in the memory, the steps of the electric energy meter centralized distribution management method described in the first aspect are implemented.

[0063] In a fourth aspect, the present invention provides a computer-readable storage medium for storing a computer program; when the computer program is executed by a processor, the steps of the electric energy meter centralized distribution management method described in the first aspect are implemented.

[0064] The present invention provides an electric energy meter centralized distribution management method, system, computer device and storage medium. In the method, the demand is predicted based on a time series or a machine learning model, and combined with the analysis of the fluctuation range of the number of electric energy meters, the prediction accuracy of the electric energy meter demand is significantly improved; by dynamically calculating the benchmark inventory and the safety inventory, while ensuring the daily installation demand of the electric energy meters of the lower-level purchasing units, overstocking is avoided; by establishing a multi-constraint optimization model and introducing a logistics cost and / or a stock-out penalty and an overstock penalty function, the logistics cost and the inventory rationality are balanced, and an optimization algorithm is used to solve the problem, so as to achieve the global optimum of the distribution path and quantity. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only the embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0066] Figure 1 It is a schematic flowchart of an electric energy meter centralized distribution management method provided by an embodiment of the present invention;

[0067] Figure 2 It is a diagram of the original inventory and demand prediction results provided by an embodiment of the present invention;

[0068] Figure 3 It is a diagram of the optimized 7-day distribution quantity results provided by an embodiment of the present invention;

[0069] Figure 4 It is a schematic structural diagram of an electric energy meter centralized distribution management system provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0070] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0071] Example 1

[0072] As Figure 1 shown, this embodiment provides a centralized distribution management method for electric energy meters, including:

[0073] Step 101, obtain the historical distribution volume, installation requirements, inventory consumption records, and safety inventory requirements of electric energy meters between the superior purchasing unit and the subordinate purchasing unit within the target time period, so as to predict the demand for electric energy meters of the subordinate purchasing unit in the same future time period by using a time series model or a machine learning algorithm.

[0074] In this step, the superior purchasing unit can obtain the usage situation of electric energy meters of the subordinate purchasing unit in the past period (such as 6 months or 1 year) through the enterprise internal business management system (such as ERP system, warehouse management system WMS) or manual record forms, including historical distribution volume, daily installation requirements, inventory consumption records, and safety inventory requirements, etc.

[0075] Clean and statistically analyze the collected historical data, remove outliers and fill in missing values, and perform time series analysis according to seasonality or business rules.

[0076] If the demand data shows obvious seasonality, SARIMA (Seasonal ARIMA) or other machine learning models (such as LSTM, XGBoost) can be used for prediction; if the data is stable, ARIMA or exponential smoothing method can be used.

[0077] Through the above model, obtain the daily average demand for electric energy meters of the subordinate purchasing unit in the next future period (such as the next quarter or the next month), and the possible demand fluctuation range.

[0078] Step 102, determine the benchmark inventory and safety inventory of electric energy meters according to the demand for electric energy meters of the subordinate purchasing unit in the same future time period, and use the sum of the benchmark inventory and safety inventory of electric energy meters as the total inventory of electric energy meters required by the superior purchasing unit in the same future time period.

[0079] In this step, exemplarily, calculate the benchmark inventory I of the electric energy meter according to the following formula base , to represent the required reserve to cope with the consumption of L days at an average demand level:

[0080]

[0081] where L is the number of days for the superior purchasing unit to replenish the electric energy meters (required); T is the number of days in the target time period; N is the total number of subordinate purchasing units; D i,t is the predicted demand for electric energy meters of the i-th subordinate purchasing unit on the t-th day.

[0082] To resist demand fluctuations and inaccurate forecasts, additional safety stock needs to be added. The safety stock I of the electricity meters is calculated according to the following formula safe :

[0083]

[0084] Among them, x is the safety factor (such as 1.65, 1.96, etc., corresponding to different guarantee probabilities); σ is the standard deviation of historical demand residuals or forecast errors (the method of obtaining σ can be based on the variance estimation of demand from historical data or the statistics of forecast residuals).

[0085] Therefore, the total inventory I of electricity meters required by the superior procurement unit prov is initially set as:

[0086] I prov = I base + I safe .

[0087] In this embodiment, Iprov can be dynamically adjusted every certain period (such as weekly or monthly) according to the actual demand and forecast deviation to ensure that the inventory level is always close to the actual demand.

[0088] Step 103: Using the delivery volume within the target time period as the decision variable, construct an objective function that minimizes the logistics cost and / or the penalties for stockouts and overstocking, subject to the electricity meter inventory balance equation, the upper and lower limits of the electricity meter inventory, and the constraint of the total inventory of electricity meters of the superior procurement unit.

[0089] Exemplarily, this step includes:

[0090] Construct an expression for the electricity meter inventory balance equation:

[0091] I i,t = I i,t-1 + x i,t - D i,t .

[0092] Among them, I i,t is the inventory of electricity meters of the lower-level procurement unit i at the end of day t; is the minimum value of the safety value of the electricity meter installation demand; is the maximum value of the safety value of the electricity meter installation demand; I i,t-1 is the inventory of electricity meters of the lower-level procurement unit i at the end of day t-1; x i,t represents the number of electricity meters delivered by the superior procurement unit to the lower-level procurement unit i on day t; D i,t is the forecast demand for electricity meters of the lower-level procurement unit i on day t.

[0093] Construct the constraint on the total inventory of electric energy meters of the superior purchasing unit:

[0094]

[0095] Among them, I prov,t-1 represents the available inventory of electric energy meters of the superior purchasing unit at the beginning of the t-th day.

[0096] This step also includes transportation resource limitations (such as vehicle capacity, delivery batches, etc.), which can be introduced according to the actual business scenario, such as the maximum load capacity of the vehicle, the maximum number of daily deliveries, etc.

[0097] The preferred goal of this embodiment is: on the premise of ensuring that the subordinate purchasing units obtain sufficient electric energy meters on time, minimize the distribution cost or keep the inventory level of the subordinate purchasing units within a reasonable ratio range (or both).

[0098] Construct the objective function M for minimizing the logistics cost 1 The expression of:

[0099]

[0100] Among them, T is the number of days in the target time period; N is the total number of subordinate purchasing units; C i is the unit transportation cost.

[0101] Construct the objective function M that simultaneously considers the penalty for out-of-stock and the penalty for excessive inventory 2 The expression of:

[0102]

[0103] Among them, Penalty(I i,t ) represents the penalty for the inventory level lower than or exceeding ; α is the first weight; β is the second weight.

[0104] Step 104: Use an optimization algorithm to solve the objective function for minimizing the logistics cost and / or the penalty for out-of-stock and overstock to determine the distribution quantity of electric energy meters from the superior purchasing unit to the subordinate purchasing units within the target time period.

[0105] On the premise of knowing the available inventory of the superior purchasing unit, transport a certain number of electric energy meters to the subordinate purchasing units every day (or each scheduling cycle) to keep it at a reasonable inventory ratio (that is, meet the minimum installation requirements and prevent the inventory from accumulating excessively in the short term).

[0106] After establishing the objective function, use a feasible optimization algorithm to solve it. The examples are as follows:

[0107] 1), Genetic Algorithm (GA)

[0108] Coding: Combine the distribution plan {xi,t} for a period of time (or one day) as a chromosome.

[0109] Fitness function: Use the negative value or its reciprocal corresponding to the objective function (such as transportation cost + backorder penalty) as the fitness.

[0110] Crossover and mutation: Perform crossover and mutation on each gene in the chromosome (corresponding to the distribution volume of the lower-level purchasing unit) to generate new solutions.

[0111] Constraint repair: If a solution that violates the inventory upper / lower limit or transportation capacity constraint appears, repair it.

[0112] 2), Integer Linear Programming (MILP)

[0113] For problems with limited scale, the above objectives and constraints can be directly modeled as integer linear programming, and commercial solvers (such as CPLEX, Gurobi) or open-source solvers (such as CBC, GLPK) can be used for exact solution.

[0114] 3), Other heuristic or meta-heuristic algorithms

[0115] Such as Particle Swarm Optimization (PSO), Simulated Annealing (SA), Tabu Search (TS), etc. This embodiment does not limit the specific optimization algorithm, and can be selected according to actual business needs.

[0116] This embodiment does not limit the use of a certain optimization algorithm. As long as it can meet the constraints and the optimization objectives of this embodiment, it can be used as a feasible alternative. For example:

[0117] Incorporate the inventory upper and lower limits into the dynamic programming framework; use reinforcement learning algorithms to make decisions step by step in a simulated environment; use heuristic rules (such as "fill the most urgent lower-level purchasing unit first") for "greedy" scheduling.

[0118] In order to truly implement the daily (or per-period) distribution plan and make adjustments when the demand forecast or inventory situation changes, the centralized distribution management method for electric energy meters provided in this embodiment further includes executing shipments according to the number of electric energy meters distributed by the upper-level purchasing unit to the lower-level purchasing unit within the target period, and obtaining the actual arrival and inventory information of the electric energy meters fed back by the lower-level purchasing unit.

[0119] When the deviation of the electric energy meter demand or inventory of the lower-level purchasing unit exceeds the threshold, recalculate the demand forecast model and safety inventory, and iteratively adjust the distribution plan.

[0120] Exemplarily, execute the distribution plan: According to the distribution list and quantity obtained by the optimization algorithm, the superior procurement unit arranges personnel or vehicles to execute the delivery; after the subordinate procurement unit receives the electricity meters, it feeds back the actual received quantity and the updated inventory quantity to the information management system.

[0121] Inventory monitoring and exception handling: If the inventory of a certain subordinate procurement unit is close to the lower limit or there is a sudden increase in demand, this embodiment can give it priority in the next round of calculations for distribution processing.

[0122] If the available inventory of the superior procurement unit is insufficient, update the procurement or replenishment quantity through the calculation process in step 101, and adjust its safety inventory and benchmark inventory in a timely manner.

[0123] Rolling prediction and adjustment: After a period of time, this embodiment re-collects the actual demand, distribution, and inventory data, and corrects the demand prediction model to reduce the prediction error.

[0124] At the same time, regularly recalculate the total inventory or safety inventory to ensure that the inventory always closely matches the actual demand, and use the latest data in the distribution plan (step 104) of the next cycle.

[0125] To make the solution of the present invention clearer, the embodiments of the present invention further disclose specific examples.

[0126] The Shanxi Metrology Center is responsible for centralized procurement and storage of electricity meters, and then distributes them on demand to power companies in various cities and counties in the province (such as Taiyuan City, Datong City, Linfen City, and Yuncheng City) to meet the daily meter installation and maintenance needs of each place. To improve inventory management efficiency and reduce logistics costs, optimization is required in the following three stages:

[0127] According to step 101, within the Shanxi Metrology Center, obtain the electricity meter-related data for the past 12 months (assumed to be the previous natural year) through the enterprise management system (such as ERP, WMS):

[0128] 1) Daily distribution volume: That is, the quantity of electricity meters shipped by the provincial metrology center to power companies in various cities and counties in the province.

[0129] 2) Installation demand: The actual number of meters installed by power companies in various cities and counties or the meter installation application volume submitted by users.

[0130] 3) Inventory consumption record: The remaining inventory after daily receipt and installation and use by power companies in various cities and counties.

[0131] 4) Safety inventory demand: The emergency reserve quantity for peak periods, policy fluctuations, etc.

[0132] In this embodiment, the historical demands of each city or county company are modeled one by one. Considering the obvious seasonal and phased fluctuations, the SARIMA (Seasonal ARIMA) model is selected for prediction, and finally the demand sequence of meter usage of each city and county company in Shanxi Province in the past year (365 days in total) is formed.

[0133] Calculate the total inventory of the provincial metering center, the benchmark inventory I base , set the prediction period T = 90 days, calculate the sum of the demands of all city and county companies in the next quarter, and obtain the summary Then the daily average demand I total is about 1000 units per day. In the case of a replenishment cycle of 15 days, I base = 15000 (units).

[0134] To prevent sudden increases in demand, prediction errors, or transportation delays, this embodiment selects z = 1.65 (corresponding to a service level of approximately 95%), and statistics show that the overall demand standard deviation σ ≈ 200 units per day, I safe ≈ 1277 (units)

[0135] Therefore, the provincial metering center needs to initially stockpile I prov ≈ 16277 (units) at the beginning of the next quarter.

[0136] In step S101, the available inventory currently owned by the Shanxi Provincial Metering Center has been obtained (for example, the initial total inventory of 16277 units is calculated), and the demand for the next quarter has been predicted. For demonstration purposes, the daily delivery plan is calculated within a shorter time window of one week below.

[0137] As Figure 2 shown, it is the delivery demand situation of the city. Taking maximizing the reasonable inventory within 7 days as the goal, through the genetic algorithm, the delivery quantities to 4 companies within 7 days are packed into a chromosome, which actually contains 7×4 = 28 genes. After iterative solution, the GA output result is as Figure 3 shown. In actual implementation, after the algorithm obtains the specific daily delivery quantities to each company, it can directly connect to the enterprise internal shipping scheduling system to generate outbound documents and transportation plans.

[0138] In summary, this embodiment provides a centralized delivery management method for electric energy meters. By integrating historical demand prediction and intelligent optimization scheduling technologies, it provides an efficient and dynamic solution for the centralized delivery management of electric energy meters, with the following significant advantages:

[0139] Precise supply-demand matching to reduce inventory costs: Based on time series and machine learning models to predict demand, combined with seasonal correction and fluctuation range analysis, significantly improve the accuracy of demand forecasting. By dynamically calculating the benchmark inventory and safety inventory, while ensuring the daily installation needs of lower-level purchasing units, avoid excessive hoarding.

[0140] Intelligent scheduling optimization to improve logistics efficiency: By establishing a multi-constraint optimization model (including inventory balance equations, transportation resource limitations, etc.), and using genetic algorithms or integer programming to solve, achieve the global optimum of distribution routes and quantities.

[0141] Dynamic closed-loop adjustment to enhance risk resistance: By real-time monitoring inventory and demand data, trigger a rolling correction mechanism. When the demand deviation exceeds the threshold, automatically update the prediction model and re-optimize the distribution plan to ensure a rapid response to sudden demands (such as policy changes or engineering emergencies).

[0142] Multi-objective collaborative optimization to balance service and cost: By introducing shortage penalty and overstock penalty functions, balance logistics costs and inventory rationality. The inventory level of lower-level purchasing units is always maintained within the safety threshold, while avoiding the problem of capital occupation caused by excessive inventory.

[0143] Strong scalability, suitable for multiple scenarios: The system supports flexible configuration of prediction models (such as LSTM, SARIMA) and optimization algorithms (genetic algorithms, integer programming), and can adapt to different scales of power companies and seasonal fluctuation scenarios. In addition, the modular design is convenient for integration with existing ERP and WMS systems, with low implementation costs and high promotion value.

[0144] This embodiment combines data-driven decision-making with intelligent algorithms, solves the problem of extensive scheduling in traditional distribution management, constructs a highly elastic and low-cost metering asset distribution system for the power industry, and significantly improves resource utilization efficiency and service quality.

[0145] Embodiment 2

[0146] Based on the same inventive concept as Embodiment 1, this embodiment provides a centralized distribution management system for electric energy meters. Since the principle of solving problems by this system is similar to that of the aforementioned centralized distribution management method for electric energy meters, the implementation of this system can refer to the implementation of the centralized distribution management method for electric energy meters.

[0147] As Figure 4 shown, the centralized distribution management system for electric energy meters includes:

[0148] The first acquisition module 10 is configured to acquire the historical delivery volume, installation requirements, inventory consumption records, and safety inventory requirements of the electricity meters between the superior purchasing unit and the subordinate purchasing unit within the target time period, so as to predict the demand for electricity meters of the subordinate purchasing unit in the future same-period time period by using a time series model or a machine learning algorithm.

[0149] The first determination module 20 is configured to determine the benchmark inventory and safety inventory of the electricity meters according to the demand for electricity meters of the subordinate purchasing unit in the future same-period time period, and use the sum of the benchmark inventory and the safety inventory of the electricity meters as the total inventory of electricity meters required by the superior purchasing unit in the future same-period time period.

[0150] The construction module 30 is configured to use the delivery volume within the target time period as a decision variable, and construct an objective function for minimizing the logistics cost and / or shortage and overstock penalty according to the electricity meter inventory balance equation, the upper and lower limits of the electricity meter inventory, and the constraint of the total inventory of electricity meters of the superior purchasing unit.

[0151] The second determination module 40 is configured to solve the objective function for minimizing the logistics cost and / or shortage and overstock penalty by using an optimization algorithm, so as to determine the delivery quantity of electricity meters from the superior purchasing unit to the subordinate purchasing unit within the target time period.

[0152] Exemplarily, the first determination module includes:

[0153] The first calculation unit is configured to calculate the benchmark inventory I of the electricity meters according to the following formula base :

[0154]

[0155] where L is the number of days for the superior purchasing unit to replenish the electricity meters; T is the number of days of the target time period; N is the total number of subordinate purchasing units; D i,t is the predicted demand for electricity meters of the subordinate purchasing unit i on the t-th day.

[0156] The second calculation unit is configured to calculate the safety inventory I of the electricity meters according to the following formula safe :

[0157]

[0158] where x is the safety factor; σ is the standard deviation of the historical demand residual or the prediction error.

[0159] Exemplarily, the construction module includes:

[0160] The first construction unit is configured to construct an expression of the electricity meter inventory balance equation:

[0161] I i,t = I i,t-1+x i,t -D i,t 。

[0162] Among them, I i,t is the inventory of electric energy meters at the end of the t-th day for the lower-level purchasing unit i; is the minimum value of the safety value of the installation demand of electric energy meters; is the maximum value of the safety value of the installation demand of electric energy meters; I i,t-1 is the inventory of electric energy meters at the end of the (t - 1)-th day for the lower-level purchasing unit i; x i,t represents the number of electric energy meters distributed by the upper-level purchasing unit to the lower-level purchasing unit i on the t-th day; D i,t is the predicted demand for electric energy meters of the lower-level purchasing unit i on the t-th day.

[0163] The second construction unit is used to construct the constraint on the total inventory of electric energy meters of the upper-level purchasing unit:

[0164]

[0165] Among them, I prov,t-1 represents the available inventory of electric energy meters at the beginning of the t-th day for the upper-level purchasing unit.

[0166] The third construction unit is used to construct the objective function M for minimizing the logistics cost 1 of the expression:

[0167]

[0168] Among them, T is the number of days in the target time period; N is the total number of lower-level purchasing units; C i is the unit transportation cost;

[0169] The fourth construction unit is used to construct the objective function M that simultaneously considers the shortage penalty and the overstock penalty 2 of the expression:

[0170]

[0171] Among them, Penalty(I i,t ) represents the penalty for the inventory that is lower than or exceeds ; α is the first weight; β is the second weight.

[0172] Exemplarily, the electric energy meter centralized distribution management system provided in this embodiment further includes:

[0173] The second acquisition module is used to execute the delivery according to the number of electric energy meters distributed by the upper-level purchasing unit to the lower-level purchasing unit within the target period, and acquire the actual arrival and inventory information of the electric energy meters fed back by the lower-level purchasing unit.

[0174] An adjustment module, configured to recalculate the demand forecasting model and the safety inventory and iteratively adjust the distribution plan when the electricity meter demand or inventory deviation of the subordinate purchasing unit exceeds the threshold.

[0175] For the more specific working processes of the above-mentioned various modules, reference can be made to the corresponding content disclosed in Embodiment 1, and details will not be elaborated here.

[0176] Embodiment 3

[0177] This embodiment provides a computer device, including a processor and a memory; wherein, when the processor executes the computer program stored in the memory, the steps of the electricity meter centralized distribution management method described in Embodiment 1 are implemented.

[0178] For the more specific process of the above method, reference can be made to the corresponding content disclosed in Embodiment 1, and details will not be elaborated here.

[0179] Embodiment 4

[0180] This embodiment provides a computer-readable storage medium for storing a computer program; when the computer program is executed by a processor, the steps of the electricity meter centralized distribution management method described in Embodiment 1 are implemented.

[0181] For the more specific process of the above method, reference can be made to the corresponding content disclosed in Embodiment 1, and details will not be elaborated here.

[0182] Embodiment 5

[0183] This embodiment provides a computer program product, including computer-executable instructions or a computer program. When the computer-executable instructions or the computer program are executed by a processor, the steps of the electricity meter centralized distribution management method described in Embodiment 1 are implemented.

[0184] For the more specific process of the above method, reference can be made to the corresponding content disclosed in Embodiment 1, and details will not be elaborated here.

[0185] In this specification, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts among the embodiments can be referred to each other. For the systems, devices, storage media, and computer program products disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and the relevant parts can be referred to the description of the method part.

[0186] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solutions in the embodiments of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

[0187] In some embodiments, the computer-executable instructions can be in the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and can be deployed in any form, including being deployed as an independent program or being deployed as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0188] As an example, the computer-executable instructions may or may not correspond to files in a file system, and can be stored as part of a file that stores other programs or data. For example, they can be stored in one or more scripts in a Hyper Text Markup Language (HTML) document, stored in a single file dedicated to the program being discussed, or stored in multiple cooperating files (for example, files that store one or more modules, subroutines, or code portions).

[0189] As an example, the computer-executable instructions can be deployed to execute on one electronic device, or on multiple electronic devices located at one location, or on multiple electronic devices distributed at multiple locations and interconnected through a communication network.

[0190] The present invention has been described in detail above in conjunction with specific embodiments and exemplary examples, but these descriptions should not be construed as limiting the present invention. Those skilled in the art understand that without departing from the spirit and scope of the present invention, various equivalent substitutions, modifications, or improvements can be made to the technical solutions and their implementation manners of the present invention, and these all fall within the scope of the present invention. The protection scope of the present invention is subject to the appended claims.

Claims

1. A method for centralized distribution management of electric energy meters, characterized in that: include: Obtain the historical distribution volume, installation requirements, inventory consumption records, and safety inventory requirements of electric energy meters between the upper-level purchasing unit and the lower-level purchasing unit during the target time period, so as to use time series models or machine learning algorithms to predict the demand for electric energy meters of the lower-level purchasing unit during the same period in the future; Determine the baseline inventory and safety inventory of electric energy meters based on the demand for electric energy meters by the subordinate purchasing unit in the same period in the future, and use the sum of the baseline inventory and safety inventory of electric energy meters as the total inventory of electric energy meters required by the superior purchasing unit in the same period in the future; Taking the delivery quantity within the target time period as the decision variable, according to the energy meter inventory balance equation, the upper and lower limits of the energy meter inventory and the total inventory constraints of the energy meter of the superior purchasing unit, the objective function of minimizing the logistics cost and / or the out-of-stock and over-stock penalties is constructed; An optimization algorithm is used to solve the objective function of minimizing logistics costs and / or out-of-stock and overstock penalties to determine the number of electricity meters delivered by the superior purchasing unit to the subordinate purchasing unit within the target time period.

2. The centralized distribution management method of electric energy meters according to claim 1, characterized in that: The method of determining the base stock and safety stock of electric energy meters according to the demand of electric energy meters of the subordinate purchasing unit in the same period of time in the future, and taking the sum of the base stock and safety stock of electric energy meters as the total stock of electric energy meters required by the superior purchasing unit in the same period of time in the future, includes: The base stock of the energy meter is calculated according to the following formula: base : Where L is the number of days for the upper-level purchasing unit to supplement the electric energy meter; T is the number of days in the target time period; N is the total number of lower-level purchasing units; D i,t Forecast demand for the electric energy meter of subordinate purchasing unit i on day t; Calculate the safety stock I of the energy meter according to the following formula safe : Where x is the safety factor and σ is the standard deviation of the historical demand residual or forecast error.

3. The centralized distribution management method of electric energy meters according to claim 1, characterized in that: The objective function of minimizing logistics costs and / or out-of-stock and over-stock penalties is constructed by taking the delivery volume within the target time period as the decision variable and according to the electric energy meter inventory balance equation, the upper and lower limits of the electric energy meter inventory and the total inventory constraints of the electric energy meter of the superior purchasing unit, including: Construct the energy meter inventory balance equation expression: I i,t =I i,t-1 +x i,t -D i,t ; Among them, I i,t is the inventory of electric energy meters of subordinate purchasing unit i at the end of day t; The minimum value of the safety value required for the installation of the electric energy meter; The maximum value of the safety value required for the installation of the electric energy meter; I i,t-1 is the inventory of electric energy meters of the subordinate purchasing unit i at the end of day t-1; x i,t represents the number of electric energy meters delivered by the superior purchasing unit to the subordinate purchasing unit i on day t; D i,t Forecast demand for the electric energy meter of subordinate purchasing unit i on day t; Construct the total inventory constraint of the electric energy meter of the superior purchasing unit: Among them, I prov,t-1 It represents the available inventory of electric energy meters of the superior purchasing unit at the beginning of day t; Construct the expression of the objective function M1 that minimizes logistics costs: Where T is the number of days in the target time period; N is the total number of subordinate purchasing units; C i is the unit transportation cost; Construct the expression of the objective function M2 that considers both out-of-stock penalty and excess inventory penalty: Among them, Penalty (I i,t ) indicates that it is lower than or more The inventory is penalized; α is the first weight; β is the second weight.

4. The centralized distribution management method of electric energy meters according to claim 1, characterized in that: Also includes: Execute delivery according to the quantity of electric energy meters delivered by the superior purchasing unit to the subordinate purchasing unit within the target period, and obtain the actual arrival and inventory information of the electric energy meters fed back by the subordinate purchasing unit; When the electricity meter demand or inventory deviation of the subordinate purchasing unit exceeds the threshold, the demand forecast model and safety stock are recalculated, and the distribution plan is iteratively adjusted.

5. A centralized distribution management system for electric energy meters, characterized in that: include: The first acquisition module is used to obtain the historical distribution volume, installation requirements, inventory consumption records and safety inventory requirements of electric energy meters between the upper-level purchasing unit and the lower-level purchasing unit in the target time period, so as to use the time series model or machine learning algorithm to predict the demand volume of electric energy meters of the lower-level purchasing unit in the same period in the future; The first determination module is used to determine the baseline inventory and safety inventory of the electric energy meter according to the demand of the electric energy meter of the subordinate purchasing unit in the same period of time in the future, and use the sum of the baseline inventory and the safety inventory of the electric energy meter as the total inventory of the electric energy meter required by the superior purchasing unit in the same period of time in the future; A construction module is used to construct an objective function that minimizes logistics costs and / or out-of-stock and overstock penalties based on the energy meter inventory balance equation, the energy meter inventory upper and lower limits, and the total inventory constraints of the energy meter of the superior purchasing unit, taking the delivery volume within the target time period as the decision variable; The second determination module is used to solve the objective function of minimizing logistics costs and / or out-of-stock and overstock penalties using an optimization algorithm to determine the number of electric energy meters delivered by the superior purchasing unit to the subordinate purchasing unit within the target time period.

6. The centralized distribution management system for electric energy meters according to claim 5, characterized in that: The first determining module comprises: The first calculation unit is used to calculate the benchmark inventory I of the electric energy meter according to the following formula base : Where L is the number of days for the upper-level purchasing unit to supplement the electric energy meter; T is the number of days in the target time period; N is the total number of lower-level purchasing units; D i,t Forecast demand for the electric energy meter of subordinate purchasing unit i on day t; The second calculation unit is used to calculate the safety stock I of the electric energy meter according to the following formula safe : Where x is the safety factor and σ is the standard deviation of the historical demand residual or forecast error.

7. The centralized distribution management system for electric energy meters according to claim 5, characterized in that: The building blocks include: The first building block is used to construct the energy meter inventory balance equation expression: I i,t =I i,t-1 +x i,t -D i,t ; Among them, I i,t is the inventory of electric energy meters of subordinate purchasing unit i at the end of day t; The minimum value of the safety value required for the installation of the electric energy meter; The maximum value of the safety value required for the installation of the electric energy meter; I i,t-1 is the inventory of electric energy meters of the subordinate purchasing unit i at the end of day t-1; x i,t represents the number of electric energy meters delivered by the superior purchasing unit to the subordinate purchasing unit i on day t; D i,t Forecast demand for the electric energy meter of subordinate purchasing unit i on day t; The second construction unit is used to construct the total inventory constraint of the electric energy meter of the upper-level purchasing unit: Among them, I prov,t-1 It represents the available inventory of electric energy meters of the superior purchasing unit at the beginning of day t; The third building block is used to construct the expression of the objective function M1 that minimizes the logistics cost: Where T is the number of days in the target time period; N is the total number of subordinate purchasing units; C i is the unit transportation cost; The fourth building block is used to construct the expression of the objective function M2 that considers both out-of-stock penalty and excess inventory penalty: Among them, Penalty (I i,t ) indicates that it is lower than or more The inventory is penalized; α is the first weight; β is the second weight.

8. The centralized distribution management system for electric energy meters according to claim 1, characterized in that: Also includes: The second acquisition module is used to execute delivery according to the number of electric energy meters delivered by the superior purchasing unit to the subordinate purchasing unit within the target period, and obtain the actual arrival and inventory information of the electric energy meters fed back by the subordinate purchasing unit; The adjustment module is used to recalculate the demand forecast model and safety inventory and iteratively adjust the distribution plan when the electricity meter demand or inventory deviation of the subordinate purchasing unit exceeds the threshold.

9. A computer device, characterized in that: It comprises a processor and a memory; wherein, when the processor executes the computer program stored in the memory, it implements the steps of the electric energy meter centralized distribution management method described in any one of claims 1-4.

10. A computer-readable storage medium, characterized in that: Used to store computer programs; when the computer programs are executed by the processor, the steps of the centralized distribution management method of electric energy meters described in any one of claims 1 to 4 are implemented.

Images