Logistics model optimization method and system based on integrated energy system

Abstract

The application belongs to the technical field of electricity, and discloses a logistics model optimization method and system based on a comprehensive energy system, the method comprising: acquiring climate characteristic data and historical logistics data of a target region; establishing a logistics prediction model within a scheduling period based on the climate characteristic data and the historical logistics data; dividing the scheduling period into multiple sub-periods, and sequentially rolling optimization of the logistics prediction model in each sub-period based on a time window to obtain an intermediate optimization model; and optimizing the intermediate optimization model with logistics cost as a constraint condition to obtain a final optimization model. The method solves the problem of poor reliability and economy of existing island logistics supply.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of electrical technology, in particular to a logistics model optimization method and system based on a comprehensive energy system. BACKGROUND

[0002] In recent years, China has paid more and more attention to the development and utilization of comprehensive energy resources. The rich resources of island comprehensive energy systems can provide energy supply for island residents and improve their living standards.

[0003] The current main resource supply mode of the island comprehensive energy system is to supply goods (fuel, vegetables, daily necessities) from the mainland to the ocean island by cargo ship. During transportation, the supply cycle and quantity of the cargo ship must meet the supply balance of the fuel reserves, living material reserves and other conditions of the island comprehensive energy system, and a certain margin is left. In addition, it is also affected by factors such as climate conditions, off-shore prices, etc.

[0004] Therefore, it has become a problem to be solved by those skilled in the art to provide a comprehensive energy system logistics optimization method and system based on model prediction in order to improve the reliability and economy of island logistics supply. SUMMARY

[0005] The embodiments of the present application provide a comprehensive energy system logistics optimization method and system based on model prediction to at least partially solve the problem of poor reliability and economy of existing island logistics supply. In order to have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not a general review, nor is it intended to determine key / important components or delineate the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.

[0006] According to a first aspect of the embodiments of the present application, a logistics model optimization method based on a comprehensive energy system is provided, and the method comprises:

[0007] Obtaining climate feature data and historical logistics data of a target area;

[0008] Establishing a logistics prediction model within a scheduling period based on the climate feature data and the historical logistics data;

[0009] Dividing the scheduling period into multiple sub-periods, and sequentially rolling optimization of the logistics prediction model in each sub-period based on a time window to obtain an intermediate optimization model;

[0010] Optimizing the intermediate optimization model with logistics cost as a constraint condition to obtain a final optimization model.

[0011] Further, the scheduling period is one year, and the logistics prediction model is an annual logistics scheduling optimization model, and an annual logistics scheduling result is output by the annual logistics scheduling optimization model.

[0012] The sub-periods include each quarter and each month, and the annual logistics scheduling optimization model is sequentially and rollingly optimized in each sub-period based on a time window to obtain an intermediate optimization model, and the method specifically includes:

[0013] A first time window is set, and a quarterly logistics rolling optimization model is constructed based on the first time window, and the logistics prediction model is optimized once by the quarterly logistics rolling optimization model.

[0014] A second time window is set, and a monthly logistics rolling optimization model is constructed based on the second time window, and the logistics prediction model is optimized twice by the monthly logistics rolling optimization model.

[0015] Further, a logistics prediction model in the scheduling period is established based on climate feature data and historical logistics data, and the method specifically includes:

[0016] A target function is established with the lowest total logistics cost in a year as a constraint condition, and the target function is as follows:

[0017] obj = min (l1 + l2 + l3)

[0018] Wherein, l1 is a raw material purchase cost;

[0019] l2 is a cargo ship rental and maintenance cost;

[0020] l3 is a material storage cost in a target region.

[0021] Further, the raw material purchase cost l1 is calculated by the following formula:

[0022]

[0023] Wherein, T is a scheduling period;

[0024] λ1(t) is a fuel price at t time;

[0025] P c (t) is a fuel purchase amount at t time.

[0026] Further, the material storage cost l3 in the target region is calculated by the following formula:

[0027]

[0028] Wherein, Q(t) is a fuel storage amount of an oil depot on an island at t time;

[0029] λ2 is the storage price of the oil depot unit oil quantity;

[0030] C1 is the fixed storage cost of fuel oil.

[0031] Further, the quarterly logistics rolling optimization model is:

[0032] Q (t+Γ) = Q * (t+Γ), t = 0, 1, 2,..., T-Γ

[0033] Wherein, Γ is the first time window;

[0034] Q * (t), t = 1, 2,..., T is the fuel storage optimization result in the logistics prediction model.

[0035] Further, the once optimization using the quarterly logistics rolling optimization model specifically includes:

[0036] The once optimization is performed in a rolling optimization manner;

[0037] In the first rolling optimization, the optimization range of the first time window is t = 1, 2,..., Γ-1, Γ, and satisfies Q(Γ) = Q * (Γ), and the results of the decision variables at t = 1, 2,..., Γ-1, Γ are obtained, and the optimization result of the decision variable at t = 1 is used to cover the optimization result at t = 1 in the annual logistics scheduling optimization model;

[0038] The first time window is moved backward by a preset number of steps, and the second optimization is started, and the second optimization result is used as a cover value to cover the annual logistics scheduling result at t = 2;

[0039] Similarly, the annual logistics scheduling results at t = 3,..., T-Γ are modified respectively;

[0040] In the last rolling optimization, the optimization range of the first time window is t = T-Γ = 1, T-Γ+2,..., T-1, T, and satisfies Q(T) = Q * (T), and after optimization, the results of the decision variables at t = T-Γ = 1, T-Γ+2,..., T-1, T are obtained, at this time, the rolling optimization result completely covers the annual logistics optimization scheduling result, and the first time window is no longer moved backward, and the once optimization is ended.

[0041] Further, the monthly rolling model is:

[0042]

[0043] Wherein, φ is the second time window;

[0044] The fuel storage optimization result in the seasonal logistics scheduling.

[0045] Further, the logistics cost is taken as a constraint condition including the fuel loading and unloading amount conservation constraint condition of the cargo ship, and the fuel loading and unloading amount conservation constraint condition of the cargo ship is obtained according to the following formula:

[0046]

[0047]

[0048] Wherein, P c (t) is the oil purchase amount or the fuel loading amount, P d (t) is the fuel unloading amount, is the maximum fuel loading amount in the preset period, is the maximum fuel unloading amount in the preset period, I 11 (t) represents the state of the cargo ship on the continent, I NN (t) represents the state of the cargo ship on the island.

[0049] Further, the logistics cost is taken as a constraint condition including the cargo ship navigation constraint condition, and the cargo ship navigation constraint condition is obtained according to the following formula:

[0050] P v (t) = u v (t) · (E(t) + E0)

[0051] Wherein, P v (t) is the fuel consumption amount at a time t in the navigation process;

[0052] E(t) is the fuel loading amount of the cargo ship at the time t;

[0053] E0 is the fixed weight of the cargo ship itself;

[0054] u v (t) is the navigation flag bit.

[0055] Further, the logistics cost is taken as a constraint condition including the fuel storage amount balance constraint condition of the cargo ship, and the fuel storage amount balance constraint condition of the cargo ship is obtained according to the following formula:

[0056] E(t) = E(t-1) + P c (t) - P d (t)

[0057] E(0) = E(T)

[0058]

[0059] Wherein, E maxthe maximum cargo capacity of the cargo ship;

[0060] E(t) is the fuel loading amount of the cargo ship at time t;

[0061] E(t-1) is the fuel loading amount of the cargo ship at time t-1;

[0062] P c (t) is the fuel purchase amount or the fuel charging amount;

[0063] P d (t) is the fuel unloading amount.

[0064] Further, the logistics cost is taken as a constraint condition, including a space-time sequence consistency constraint condition of the cargo ship, and the space-time sequence consistency constraint condition of the cargo ship includes at least one of:

[0065] a state uniqueness constraint condition at any time;

[0066] a space state continuity constraint condition, including a departure constraint condition, a return constraint condition, an initial state constraint condition and a final state constraint condition.

[0067] Further, the logistics cost is taken as a constraint condition, including an island fuel supply balance constraint condition, and the island fuel supply balance constraint condition is obtained according to the following formula:

[0068] Q(t) = Q(t-1) + P d (t) - P load (t)

[0069] Q(0) = Q(T1)

[0070]

[0071] wherein Q(t) is the fuel inventory amount on the island at time t;

[0072] Q(t-1) is the fuel inventory amount on the island at time t-1;

[0073] P d (t) is the fuel unloading amount of the cargo ship at the target island at time t;

[0074] P load (t) is the fuel consumption amount at the target island at time t;

[0075] Q min represents the minimum fuel inventory amount of the island;

[0076] Q max represents the maximum fuel inventory amount of the island.

[0077] According to a second aspect of the embodiments of the present application, a logistics model optimization system based on an integrated energy system is provided for implementing the method as described above.

[0078] In some embodiments, the system comprises:

[0079] a data acquisition unit configured to acquire climate feature data and historical logistics data of a target region;

[0080] a model construction unit configured to establish a logistics prediction model within a scheduling period based on the climate feature data and the historical logistics data;

[0081] a first model optimization unit configured to divide the scheduling period into a plurality of sub-periods, and sequentially rollingly optimize the logistics prediction model in each sub-period based on a time window to obtain an intermediate optimization model;

[0082] a second model optimization unit configured to optimize the intermediate optimization model with logistics cost as a constraint condition to obtain a final optimization model.

[0083] According to a third aspect of the embodiments of the present application, a computer device is provided.

[0084] In some embodiments, the computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0085] According to a fourth aspect of the embodiments of the present application, a computer readable storage medium is provided.

[0086] In some embodiments, the computer storage medium comprises one or more program instructions for executing the method as described above.

[0087] The technical solutions provided by the embodiments of the present application can include the following beneficial effects:

[0088] The logistics model optimization method based on an integrated energy system provided by the present application can solve the problem of poor reliability and economy of existing island logistics supply by rolling optimization of the logistics prediction model with different span sub-periods as constraint conditions, and further optimization of the model after rolling optimization with logistics cost as a constraint condition to obtain a final optimization model, so that the final optimization model has high accuracy and ensures that the model output result has high economic applicability.

[0089] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0090] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0091] Figure 1 A flowchart illustrating a specific implementation of the logistics model optimization method provided by the present invention;

[0092] Figure 2 This is a schematic diagram illustrating the operating principle of quarterly scheduling MPC.

[0093] Figure 3 A schematic diagram of the annual-quarterly-month logistics scheduling plan for the island's integrated energy system;

[0094] Figure 4 This is a schematic diagram of ship navigation in one embodiment;

[0095] Figure 5 for Figure 4 A schematic diagram illustrating the variation pattern of island fuel storage capacity in the embodiment;

[0096] Figure 6 for Figure 4 A schematic diagram illustrating the variation pattern of island fuel storage capacity in the embodiment;

[0097] Figure 7 This is a structural block diagram of a specific embodiment of the logistics model optimization system provided by the present invention;

[0098] Figure 8 This is a structural diagram of the computer device provided by the present invention. Detailed Implementation

[0099] The following description and drawings are illustrative of specific embodiments thereof and are not intended to limit the scope of the embodiments. Parts and features of some embodiments can be included or substituted in or for parts and features of other embodiments. The scope of the embodiments encompassed herein includes the whole scope of the claims together with all available equivalents of the claims. In this document, the terms "first", "second", etc. are used merely to distinguish one element from another, and do not require or imply any actual relationship or order between the elements. In fact, the first element can be referred to as the second element, and vice versa. Also, the terms "comprises", "comprising", or any other variations thereof are intended to cover a non-exclusive inclusion, such that a structure, device, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such structure, device, or apparatus. Without further limitation, an element defined by an "includes a" statement does not exclude the presence of additional identical elements in the structure, device, or apparatus that includes the element. Various embodiments are described in progressive stages, each of which focuses on the differences from other embodiments, and the same or similar parts between various embodiments can be referred to each other.

[0100] The terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, as used herein, indicate relative positions or orientation relationships based on the positions or orientation relationships shown in the drawings, and are only used for the convenience of description herein and simplification of description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In the description herein, unless otherwise specified and limited, the terms "mount", "connect", "connection" should be understood broadly, for example, it can be a mechanical connection or an electrical connection, it can be a communication between two elements inside, it can be a direct connection, or an indirect connection through an intermediate medium, and the specific meaning of the above terms can be understood by those skilled in the art according to the specific circumstances.

[0101] In this document, the term "multiple" means two or more, unless otherwise specified.

[0102] In this document, the character " / " represents an "or" relationship between the objects before and after it. For example, A / B means: A or B.

[0103] In this document, the term "and / or" is a description of the relationship between the objects, which means that there can be three relationships. For example, A and / or B means: A or B, or, A and B, the three relationships.

[0104] In order to improve the reliability and economy of logistics supply prediction during island resource replenishment, the application provides a logistics model optimization method based on a comprehensive energy system, so as to improve the reliability and economy of island logistics supply by formulating a reasonable island comprehensive energy system logistics planning optimization method and supply strategy.

[0105] Please refer to Figure 1 , Figure 1 The flowchart of a specific embodiment of the logistics model optimization method provided by the application is shown in the figure.

[0106] In a specific embodiment, the logistics model optimization method based on a comprehensive energy system provided by the application comprises the following steps:

[0107] S1: Obtain the climate characteristic data and historical logistics data of the target area; based on the climate characteristics of the island comprehensive energy system and the historical logistics data, the material demand and natural conditions of the dispatching period formed in the future period of time can be predicted. In actual use, the dispatching period can be annual, quarterly or monthly, and can also be set to a longer time or a shorter time according to needs. In order to facilitate description and to facilitate the actual use, this embodiment takes one year as an example.

[0108] In some use scenarios, the dispatching period T is one year. In this scenario, based on the data of resource reserves and demand prediction of the system in the future one year and the data of mainland material off-shore price prediction, the global optimization is carried out with the lowest total logistics cost (purchase + transportation) in a year as the target, combined with the transportation capacity of the ship and the resource reserve requirements of the island.

[0109] When the dispatching period is set to one year, the following objective function is established with the lowest total logistics cost in a year as the constraint condition:

[0110] obj = min (l1 + l2 + l3) Formula (1)

[0111] Wherein, l1 is the raw material purchase cost;

[0112] l2 is the lease and maintenance cost of the cargo ship;

[0113] l3 is the material storage cost in the target area.

[0114] In the above formula (1), the raw material purchase cost l1 is calculated by formula (2):

[0115]

[0116] Wherein, T is the dispatching period;

[0117] λ1(t) is the fuel price at time t;

[0118] P c (t) is the amount of fuel purchased at time t.

[0119] In formula (1), l2 is the lease maintenance cost of the cargo ship (constant), and l3 is the storage cost of materials on the island. The storage cost l3 is the cost incurred by the enterprise to maintain inventory, such as warehouse rental, handling fees, insurance premiums, interest on occupied funds, etc. The storage cost l3 can be divided into variable cost and fixed cost:

[0120]

[0121] wherein Q(t) is the fuel storage amount of the oil depot on the island at time t;

[0122] λ2 is the storage price per unit of oil of the oil depot;

[0123] C1 is the fixed storage cost of fuel.

[0124] S2: Establish a logistics prediction model within the dispatching period based on climate feature data and historical logistics data. Based on the prediction data, the logistics plan for the next year can be roughly planned with the goal of minimizing the annual system logistics cost.

[0125] In the above steps, the annual logistics can be roughly planned through the annual logistics prediction model,

[0126] However, the logistics scheduling strategy formulated by annual global optimization has high economic efficiency. However, due to the large time scale, the prediction accuracy of fuel demand and price and other factors is low, so the logistics plan often cannot be well executed in actual situations. In order to improve the feasibility and accuracy of the logistics plan of the island integrated energy system, the dispatching period can be subdivided into multiple sub-periods with decreasing span.

[0127] S3: Divide the dispatching period into multiple sub-periods, and sequentially rollingly optimize the logistics prediction model in each sub-period based on a time window to obtain an intermediate optimization model.

[0128] Still taking the above use scenario as an example, when the dispatching period is a year, i.e., the above logistics prediction model is a year logistics scheduling optimization model, the year logistics scheduling result is output through the year logistics scheduling optimization model, at this time, the sub-periods include each quarter and each month, and the year logistics scheduling optimization model is sequentially rollingly optimized based on a time window in each sub-period to obtain an intermediate optimization model, specifically including:

[0129] A first time window is set, and a quarterly logistics rolling optimization model is constructed based on the first time window, and the logistics prediction model is optimized once through the quarterly logistics rolling optimization model;

[0130] A second time window is set, and a monthly logistics rolling optimization model is constructed based on the second time window, and the logistics prediction model is secondarily optimized through the monthly logistics rolling optimization model.

[0131] In this way, through the above steps, on the basis of annual global optimization, logistics quarterly and monthly rolling optimization is realized by using model predictive control (MPC), so as to realize one-time optimization of the model in a rolling optimization manner.

[0132] In principle, based on the MPC modeling method, the MPC operation principle of the island comprehensive energy system logistics scheduling year-quarter-month is as shown in Figure 2 . Figure 2 The input data of the square in the t period is the actual system data, which is used to determine the actual operation strategy; the input data of the square in other periods is the predicted value of the system, which is used to participate in optimization and auxiliary decision-making; the output data of the square in other periods is not used as the actual control parameter of the system; the arrow is used to record the state of the system at the end of each t period, and is used as the initial data of the next optimization. Combined with the prediction of climate conditions, fuel prices, island fuel demand and other factors in the future n time periods, and the current t period ship and island resource reserve state, the logistics scheduling plan from t to t+n time periods is optimized. However, only the strategy of the t time period is actually executed. In the next each time period, the above process is repeated again to rollingly optimize the control strategy of each time period.

[0133] In the quarterly and monthly MPC control, the output instructions from the previous layer logistics scheduling plan are introduced respectively, so as to ensure that the final logistics scheduling plan has high feasibility and economy, as shown in Figure 3 .

[0134] Based on the above MPC control principle, the quarterly logistics rolling optimization model is:

[0135] Q(t+Γ)=Q * (t+Γ),t=0,1,2,...,T-Γ Formula (4)

[0136] Wherein, Γ is the first time window;

[0137] Q * (t),t=1,2,...,T is the fuel storage optimization result in the logistics prediction model.

[0138] That is, when the quarterly logistics scheduling rolling optimization model is constructed with a time window of Γ, the quarterly scheduling rolling optimization process takes the fuel storage on the island in the annual scheduling result as a reference. The Q* (t), t = 1, 2, …, T represent the fuel storage optimization results in annual logistics scheduling, providing guidance for island fuel storage in quarterly scheduling, and satisfying the above formula (4).

[0139] Further, the quarterly logistics rolling optimization model is used to perform the optimization once, which specifically includes:

[0140] The rolling optimization is used to perform the optimization once;

[0141] In the first rolling optimization, the optimization range of the first time window is t = 1, 2, …, Γ-1, Γ, and Q(Γ) = Q * (Γ) is satisfied, and the results of the decision variables at t = 1, 2, …, Γ-1, Γ are obtained, and the optimization results of the decision variables at t = 1 are used to cover the optimization results at t = 1 in the annual logistics scheduling optimization model;

[0142] The first time window is moved backward by a preset number of steps, and the second optimization is started, and the second optimization results are used as covering values to cover the annual logistics scheduling results at t = 2;

[0143] In this way, the annual logistics scheduling results at t = 3, …, T-Γ are modified respectively;

[0144] In the last rolling optimization, the optimization range of the first time window is t = T-Γ = 1, T-Γ+2, …, T-1, T, and Q(T) = Q * (T) is satisfied, and after optimization, the results of the decision variables at t = T-Γ = 1, T-Γ+2, …, T-1, T are obtained, at this time, the rolling optimization results completely cover the annual logistics optimization scheduling results, and the first time window is no longer moved backward, and the optimization once is ended.

[0145] In the monthly logistics scheduling rolling optimization model, the time window is set as Φ, and the monthly logistics scheduling rolling optimization model takes the results of the quarterly logistics scheduling rolling optimization model as a reference. The following formula is used to represent the fuel storage optimization results in quarterly logistics scheduling.

[0146] Since the total cost is minimized as the target in the annual scheduling plan and the quarterly scheduling plan, in the monthly logistics scheduling plan, the scheduling plan in a short time scale already has good economy, but the balance of materials in a short time scale is difficult to achieve, therefore, in the monthly logistics scheduling plan, the rolling optimization scheduling is performed with the minimum deviation between the actual material storage amount and the predicted material storage amount as the target.

[0147] The monthly rolling model is:

[0148] ​

[0149] wherein φ is the second time window; is the fuel storage optimization result in the seasonal logistics scheduling. The detailed rolling optimization process is similar to the quarterly rolling optimization process, and the rolling is performed T-Φ+1 times, and the constraint conditions are the same.

[0150] Based on the above-mentioned annual-seasonal-month three-layer logistics scheduling model, in some embodiments, the method provided by the present application takes the logistics cost as a constraint condition in the scheduling period to obtain a more optimal logistics supply strategy.

[0151] S4: optimizing the intermediate optimization model by taking the logistics cost as a constraint condition to obtain a final optimization model.

[0152] Specifically, taking the logistics cost as a constraint condition includes a fuel loading and unloading amount conservation constraint condition of the cargo ship, and the fuel loading and unloading amount conservation constraint condition of the cargo ship is obtained according to the following formula:

[0153]

[0154]

[0155] wherein P c (t) is the oil purchase amount or the oil loading amount, P d (t) is the fuel unloading amount, is the maximum fuel loading amount in the preset period, is the maximum fuel unloading amount in the preset period, I 11 (t) and I NN (t) are state variables, wherein I 11 (t) represents the state of the cargo ship at the continent 1, and I NN (t) represents the state of the cargo ship at the island 2.

[0156] Taking the logistics cost as a constraint condition includes a cargo ship navigation constraint condition, and the cargo ship navigation constraint condition is obtained according to the following formula:

[0157] P v (t) = u v (t) · (E(t) + E0) Formula (8)

[0158] wherein P v (t) is the fuel consumption amount at a time t in the navigation process;

[0159] E(t) is the fuel loading amount of the cargo ship at the time t;

[0160] E0 is the fixed weight of the cargo ship itself;

[0161] u v(t) is the sailing flag.

[0162] When the ship's speed and design parameters are constant, P v (t) and the ship's load E(t)+E0 are approximately linearly related as shown in equation (8).

[0163] Since the cargo ship is considered to be running in constant power mode, and the cargo ship tonnage is small, the fuel consumption is less, so the fuel consumption of the cargo ship is not considered to be included in the fuel reserve of the logistics transportation, that is:

[0164]

[0165] Specifically, equation (9) is the definition of variable u v (t) u v (t) is the sailing flag, which represents that the ship is in the process of sailing at time t. A 0-1 state variable I ij i,j∈N is used to represent the state of the cargo ship at a certain time, when I 11 (t) = 1 represents that the ship is at port 1, and I 11 (t) = 0 represents that the cargo ship is not in this state at this time; similarly, when I ij (t) = 1 represents that the ship is running on the ij section of the route at this time, and I ij (t) = 0 represents that the cargo ship is not running on this route at this time.

[0166] Further, the logistics cost is taken as a constraint condition, including the cargo ship oil storage balance constraint condition, which is obtained according to the following equation:

[0167] E(t) = E(t-1) + P c (t) - P d (t) equation (10)

[0168] E(0) = E(T) equation (11)

[0169]

[0170] Where E max is the maximum cargo capacity of the cargo ship;

[0171] E(t) is the fuel loading of the cargo ship at time t;

[0172] E(t-1) is the fuel loading of the cargo ship at time t-1;

[0173] P c (t) is the oil purchase or charging amount;

[0174] P d (t) is the fuel unloading amount.

[0175] Formula (11) means that the amount of oil stored in the cargo ship at the initial moment is the same as the amount of oil stored at the final moment.

[0176] Furthermore, incorporating logistics costs as a constraint includes a spatiotemporal sequence consistency constraint for cargo ships, which includes at least one of the following:

[0177] The constraint on the uniqueness of the state at any given time is obtained through the following formula:

[0178]

[0179] The meaning of formula (13) is the uniqueness at any given time, that is, the cargo ship can only be in one position at a given time, and will not be in multiple positions at the same time. A 0-1 state variable I is used. ij Let i,j∈N represent the state of the cargo ship at a certain moment, when I 11 (t) = 1 represents the ship anchoring on land 1, I 11 If (t) = 0, it means the cargo ship is not in this state at this time; similarly, when I ij (t) = 1 represents the ship traveling on the ij-th segment of the course at this moment, I ij If (t) = 0, it means that the cargo ship is not traveling on this route at this time.

[0180] The spatial state continuity constraints include departure constraints, return constraints, initial state constraints, and final state constraints.

[0181] The departure constraints are as follows:

[0182]

[0183] The return-to-home constraints are:

[0184]

[0185] The initial state constraints are:

[0186]

[0187] The final state constraint is:

[0188]

[0189] Considering that the ship operates in constant power mode, the inter-island transfer time is mainly determined by the voyage distance, such as Figure 4 As shown, in the above formulas (14)-(17), the voyage between the mainland and the island is divided into n-1 segments, using 0-1 state variables I. ij Let i,j∈N represent the state of the cargo ship at a certain moment, when I11 (t) = 1 means the ship is at continent 1, I 11 (t) = 0 means the ship is not in this state at this time; similarly, when I ij (t) = 1 means the ship is on the i-th segment of the route at this time, I ij (t) = 0 means the ship is not on this route at this time.

[0190] Further, the logistics cost is taken as a constraint condition, including the island fuel supply balance constraint condition, which is obtained according to the following formula:

[0191] Q(t) = Q(t-1) + P d (t) - P load (t) formula (18)

[0192] Q(0) = Q(T1) formula (19)

[0193]

[0194] Wherein, Q(t) is the fuel inventory on the island at time t;

[0195] Q(t-1) is the fuel inventory on the island at time t-1;

[0196] P d (t) is the fuel unloading amount of the ship at the target island at time t;

[0197] P load (t) is the fuel consumption at the target island at time t;

[0198] Q min represents the minimum fuel inventory on the island;

[0199] Q max represents the maximum fuel inventory on the island.

[0200] The meaning of formula (19) is that the fuel inventory on the island at the initial time is the same as the fuel inventory at the termination time.

[0201] The implementation process and effect comparison of the method will be discussed below in combination with a specific embodiment.

[0202] The running cost result is shown in Table 1, and it can be seen that under the island logistics scheduling strategy, the total logistics cost is $1,723,364, of which the ship leasing cost is $56,000. Since this simulation does not consider the fuel consumption of the ship during the voyage in the fuel logistics scheduling, the actual total logistics cost should be slightly higher than the calculated total logistics cost.

[0203] Table 1 Year-Quarter-Month logistics scheduling plan economic indicators

[0204] Parameter Value Parameter Value Annual lease times (times) 4 Cargo ship lease cost ($) 56,000 Annual fuel purchase cost ($) 1,667,364 Total logistics transportation cost ($) 1,723,364

[0205] The economic comparison of each scheme is as follows:

[0206] By analyzing the existing island logistics supply mode, the economic indicators are calculated, which further embodies the superiority of the proposed scheduling strategy.

[0207] 1) Scheme one: regular supply

[0208] Consider the case where the cargo ship regularly transports fuel to the island to meet the island's fuel demand. According to the calculation, the annual fuel consumption of the island is about 4640 tons, and the maximum load of the cargo ship is 1600 tons. Considering the minimum reserve capacity of the island's fuel storage and the uneven distribution of fuel load, the minimum number of trips of the cargo ship in a year is specified as 4 times, and the following cargo ship supply plan is developed: Mainland (February 25) → Remote Island (March 1) → Mainland (March 6), Mainland (May 27) → Remote Island (June 1) → Mainland (June 6), Mainland (August 27) → Remote Island (September 1) → Mainland (September 6), Mainland (November 27) → Remote Island (December 1) → Mainland (December 6)

[0209] The annual fuel storage change rule of the island under this strategy is shown in Figure 5 , and the economic indicators are shown in Table 2:

[0210] Table 2 Economic indicators of regular supply logistics scheduling plan

[0211] Parameter Value Parameter Value Annual lease times (times) 4 Cargo ship lease cost ($) 56,000 Annual fuel purchase cost ($) 1,961,063 Total logistics transportation cost ($) 2,017,063

[0212] 2) Scheme two: quantitative supply

[0213] In addition to developing a regular island logistics scheduling plan, the quantitative mode of logistics scheduling plan is also one of the common supply methods. Consider the case where the cargo ship supplies fuel with the maximum load when the fuel storage on the island is below a certain level (for example, 20%). Through calculation, the corresponding island fuel storage change rule is shown in Figure 6 .

[0214] Under this mode, the cargo ship's supply plan is: Mainland (March 15) → Remote Island (March 20) → Mainland (March 25), Mainland (September 5) → Remote Island (September 10) → Mainland (September 15), Mainland (December 10) → Remote Island (December 15) → Mainland (December 20).

[0215] The economic indicator analysis is shown in Table 3:

[0216] Table 3 quantifies the economic indicators of the replenishment logistics scheduling plan

[0217] Parameter Value Parameter Value Annual lease times (times) 3 Cargo ship lease cost ($) 42,000 Annual fuel purchase cost ($) 1,904,954 Total logistics transportation cost ($) 1,946,954

[0218] By comparison, it can be found that the total logistics transportation cost ($2,017,063, $1,946,954) in the logistics scheduling plan under scheme one and scheme two is higher than the logistics cost ($1,723,364) under the proposed strategy, further proving that the proposed logistics transportation strategy of the island comprehensive energy system has high economic benefits and can play a certain guiding role in actual application.

[0219] It can be seen that the logistics model optimization method based on the comprehensive energy system provided by the present application has high accuracy and ensures that the output results of the model have high economic applicability. Thus, the problem of poor reliability and economy of the existing island logistics supply is solved.

[0220] According to a second aspect of an embodiment of the present application, a logistics model optimization system based on a comprehensive energy system is provided for implementing the method as described above.

[0221] In some embodiments, as shown in Figure 7 The system comprises:

[0222] A data acquisition unit 100 is configured to acquire climate characteristic data and historical logistics data of a target region.

[0223] A model construction unit 200 is configured to establish a logistics prediction model within a scheduling period based on the climate characteristic data and the historical logistics data.

[0224] A first model optimization unit 300 is configured to divide the scheduling period into multiple sub-periods and sequentially rollingly optimize the logistics prediction model in each sub-period based on a time window to obtain an intermediate optimization model.

[0225] A second model optimization unit 400 is configured to optimize the intermediate optimization model by taking logistics cost as a constraint condition to obtain a final optimization model.

[0226] In one embodiment, a computer device, which can be a server, is provided, and an internal structure diagram of the computer device can be as shown in Figure 8As shown in the figure. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The non-volatile storage medium stores an operating system, a computer program and a model prediction. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The model prediction of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with the external terminal through the network connection. The computer program is executed by the processor to realize the steps in the above method embodiments.

[0227] Those skilled in the art can understand that, Figure 8 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0228] In one embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to realize the steps in the above method embodiments.

[0229] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to realize the steps in the above method embodiments.

[0230] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiments. Among them, any reference to memory, storage, model prediction or other media used in the embodiments provided by the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0231] The present application is not limited to the structures described above and shown in the drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the present application is only limited by the appended claims.

Claims

1. A logistics model optimization method based on an integrated energy system, characterized in that, The method includes: Acquire climate characteristic data and historical logistics data for the target area; Establish a logistics forecasting model for the scheduling cycle based on climate characteristic data and historical logistics data; The scheduling cycle is divided into multiple sub-cycles, and the logistics prediction model is sequentially optimized in each sub-cycle based on a time window to obtain an intermediate optimized model. The intermediate optimization model is optimized using logistics costs as a constraint to obtain the final optimization model; The scheduling cycle is one year, and the logistics prediction model is an annual logistics scheduling optimization model. The annual logistics scheduling results are output through the annual logistics scheduling optimization model. The sub-cycles include each quarter and each month. The annual logistics scheduling optimization model is sequentially optimized within each sub-cycle based on time windows to obtain an intermediate optimization model, specifically including: A first time window is set, and a quarterly logistics rolling optimization model is constructed based on the first time window. The logistics forecasting model is then optimized once using the quarterly logistics rolling optimization model. A second time window is set, and a monthly logistics rolling optimization model is constructed using the second time window. The logistics prediction model is then optimized a second time using the monthly logistics rolling optimization model. A logistics forecasting model for the scheduling cycle is established based on climate characteristic data and historical logistics data, specifically including: Using the minimum total annual logistics cost as a constraint, the following objective function is established: ， in, Cost of purchasing raw materials; For the cost of leasing and maintaining cargo ships; The cost of storing materials within the target area; The quarterly logistics rolling optimization model is as follows: ， in, This is the first time window; The results of fuel storage optimization in the logistics forecasting model; The monthly logistics rolling optimization model is as follows: ， Where φ is the second time window; The results of fuel storage optimization in seasonal logistics scheduling.

2. The logistics model optimization method based on an integrated energy system according to claim 1, characterized in that, Calculate the cost of the raw materials using the following formula. : ， Where T is the scheduling period; Let be the fuel price at time t; Let t be the amount of fuel purchased at time t.

3. The logistics model optimization method based on an integrated energy system according to claim 2, characterized in that, Calculate the material storage cost within the target area using the following formula. : ， in, Let be the amount of fuel stored in the oil depot on the island at time t; The storage price per unit volume of oil in the oil depot; Fixed storage costs for fuel.

4. The logistics model optimization method according to claim 1, characterized in that, Using the aforementioned quarterly logistics rolling optimization model, an optimization specifically includes: The first optimization is performed using a rolling optimization approach. During the first rolling optimization, the optimization range of the first time window is: And satisfy and obtained The results of each decision variable at the scale are calculated, and the optimization results of the decision variables at t=1 are covered by the optimization results at t=1 in the annual logistics scheduling optimization model. The first time window is pushed forward by a preset number of steps, and the second optimization begins. The result of the second optimization is used as the coverage value to cover the annual logistics scheduling result at t=2. And so on, completing the tasks for each... Correction of annual logistics scheduling results at any given time; During the final scroll optimization, the optimization range of the first time window was: And satisfy After optimization, the following was obtained: The results of each decision variable at the scale are then used to completely cover the annual logistics optimization scheduling results with the rolling optimization results. The first time window is no longer shifted, and one optimization cycle ends.

5. The logistics model optimization method according to claim 1, characterized in that, Incorporating logistics costs as a constraint, including the constraint on the conservation of fuel charge / discharge volume for cargo ships, the following formula is used to derive the constraint on the conservation of fuel charge / discharge volume for cargo ships: ， ， in, For the amount of oil purchased or added, This refers to the amount of fuel unloaded. This represents the maximum fuel load within a preset time period. This represents the maximum fuel unloading volume within a preset time period. This indicates the status of the cargo ship while it is on the mainland. This indicates the status of a cargo ship when it is on an island.

6. The logistics model optimization method according to claim 1, characterized in that, Including cargo ship navigation constraints as a constraint condition, the cargo ship navigation constraints are obtained using the following formula: ， in, This represents the fuel consumption at a certain moment t during the voyage; Let be the amount of fuel loaded on the cargo ship at time t; The fixed weight of the cargo ship itself; This is a navigation marker.

7. The logistics model optimization method according to claim 1, characterized in that, Incorporating logistics costs as a constraint, including the balance constraint of cargo ship oil storage, the balance constraint of cargo ship oil storage is obtained according to the following formula: ， ， ， in, This refers to the maximum cargo capacity of the cargo ship. Let be the amount of fuel loaded on the cargo ship at time t; This represents the amount of fuel oil loaded on the cargo ship at time t-1. For the amount of oil purchased or the amount of oil added; This refers to the amount of fuel unloaded.

8. The logistics model optimization method according to claim 1, characterized in that, Incorporating logistics costs as a constraint includes a spatiotemporal sequence consistency constraint for cargo ships, which includes at least one of the following: Constraints on the uniqueness of the state at any given time; The spatial state continuity constraints include departure constraints, return constraints, initial state constraints, and final state constraints.

9. The logistics model optimization method according to claim 1, characterized in that, Incorporating logistics costs as a constraint, including the island fuel supply balance constraint, the island fuel supply balance constraint is obtained using the following formula: ， ， ， in, Let t be the amount of fuel inventory on the island. This represents the fuel inventory on the island at time t-1. Let t be the amount of fuel unloaded by the cargo ship at the target island at time t. Let be the fuel consumption at the target island at time t; This indicates the minimum fuel inventory level on the island. This indicates the island's maximum fuel inventory.

10. A logistics model optimization system based on an integrated energy system, used to implement the method as described in any one of claims 1-9, characterized in that, The system includes: The data acquisition unit is used to acquire climate characteristic data and historical logistics data for the target area. The model building unit is used to establish a logistics prediction model for the scheduling cycle based on climate characteristic data and historical logistics data. The first model optimization unit is used to divide the scheduling cycle into multiple sub-cycles and sequentially optimize the logistics prediction model in each sub-cycle based on a time window to obtain an intermediate optimized model. The second model optimization unit is used to optimize the intermediate optimization model with logistics cost as a constraint to obtain the final optimization model. The scheduling cycle is one year, and the logistics prediction model is an annual logistics scheduling optimization model. The annual logistics scheduling results are output through the annual logistics scheduling optimization model. The sub-cycles include each quarter and each month. The annual logistics scheduling optimization model is sequentially optimized within each sub-cycle based on time windows to obtain an intermediate optimization model, specifically including: A first time window is set, and a quarterly logistics rolling optimization model is constructed based on the first time window. The logistics forecasting model is then optimized once using the quarterly logistics rolling optimization model. A second time window is set, and a monthly logistics rolling optimization model is constructed using the second time window. The logistics prediction model is then optimized a second time using the monthly logistics rolling optimization model. A logistics forecasting model for the scheduling cycle is established based on climate characteristic data and historical logistics data, specifically including: Using the minimum total annual logistics cost as a constraint, the following objective function is established: ， in, Cost of purchasing raw materials; For the cost of leasing and maintaining cargo ships; The cost of storing materials within the target area; The quarterly logistics rolling optimization model is as follows: ， in, This is the first time window; The results of fuel storage optimization in the logistics forecasting model; The monthly logistics rolling optimization model is as follows: ， Where φ is the second time window; The results of fuel storage optimization in seasonal logistics scheduling.

11. The logistics model optimization system based on an integrated energy system according to claim 10, characterized in that, Calculate the cost of the raw materials using the following formula. : ， Where T is the scheduling period; Let be the fuel price at time t; Let t be the amount of fuel purchased at time t.

12. The logistics model optimization system based on an integrated energy system according to claim 11, characterized in that, Calculate the material storage cost within the target area using the following formula. : ， in, Let be the amount of fuel stored in the oil depot on the island at time t; The storage price per unit volume of oil in the oil depot; Fixed storage costs for fuel.

13. The logistics model optimization system based on an integrated energy system according to claim 10, characterized in that, Using the aforementioned quarterly logistics rolling optimization model, an optimization specifically includes: The first optimization is performed using a rolling optimization approach. During the first rolling optimization, the optimization range of the first time window is: And satisfy and obtained The results of each decision variable at the scale are calculated, and the optimization results of the decision variables at t=1 are covered by the optimization results at t=1 in the annual logistics scheduling optimization model. The first time window is pushed forward by a preset number of steps, and the second optimization begins. The result of the second optimization is used as the coverage value to cover the annual logistics scheduling result at t=2. And so on, completing the tasks for each... Correction of annual logistics scheduling results at any given time; During the final scroll optimization, the optimization range of the first time window was: And satisfy After optimization, the following was obtained: The results of each decision variable at the scale are then used to completely cover the annual logistics optimization scheduling results with the rolling optimization results. The first time window is no longer shifted, and one optimization cycle ends.

14. The logistics model optimization system based on an integrated energy system according to claim 10, characterized in that, Incorporating logistics costs as a constraint, including the constraint on the conservation of fuel charge / discharge volume for cargo ships, the following formula is used to derive the constraint on the conservation of fuel charge / discharge volume for cargo ships: ， ， in, For the amount of oil purchased or added, This refers to the amount of fuel unloaded. This represents the maximum fuel load within a preset time period. This represents the maximum fuel unloading volume within a preset time period. This indicates the status of the cargo ship while it is on the mainland. This indicates the status of a cargo ship when it is on an island.

15. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-9.

16. A computer-readable storage medium, characterized in that, The computer storage medium contains one or more program instructions for performing the method as described in any one of claims 1-9.

Images