技术领域Technical Field
本发明涉及充电桩布局优化技术领域，具体涉及一种校园两轮电动车充电桩布局优化方法与系统。The present invention relates to the technical field of charging pile layout optimization, and in particular to a method and system for optimizing the layout of charging piles for two-wheeled electric vehicles on campus.
背景技术Background technique
随着两轮电动车在校内的普及，电动车充电桩布局建设尤其重要，许多校园的充电桩布局大多只考虑投资成本问题，并未考虑到电动车用户的利益和充电需求，充电桩的布置不符合用户的出行规律和充电特征。充电桩的不合理布局对于校内交通和充电效率都有很大影响，合理的安排充电桩的数量和位置能够将投资利益最大化，帮助师生快速的找到充电桩，减少充电等待时间并提高充电的效率，避免充电资源的浪费。With the popularity of two-wheeled electric vehicles on campus, the layout and construction of electric vehicle charging piles is particularly important. The layout of charging piles on many campuses mostly only considers the investment cost issue, and does not take into account the interests and charging needs of electric vehicle users. The layout of charging piles does not conform to the travel patterns and charging characteristics of users. The unreasonable layout of charging piles has a great impact on campus traffic and charging efficiency. Reasonable arrangement of the number and location of charging piles can maximize investment benefits, help teachers and students quickly find charging piles, reduce charging waiting time and improve charging efficiency, and avoid waste of charging resources.
在对投资成本和用户需求的多重考虑下，进行校内两轮电动车充电桩的布局优化有助于在平衡投资商和用户利益的同时满足用户的需求，规范校园交通，通过合理规划充电桩位置，可以引导电动车有序停放和充电，减少乱停乱放现象，提高校园道路通行效率。Taking into account investment costs and user needs, optimizing the layout of two-wheeled electric vehicle charging piles on campus can help balance the interests of investors and users while meeting user needs and regulating campus traffic. By rationally planning the location of charging piles, electric vehicles can be guided to park and charge in an orderly manner, reducing random parking and improving campus road traffic efficiency.
发明内容Summary of the invention
发明目的：针对背景技术中指出的问题，本发明公开一种校园两轮电动车充电桩再布局优化方法与系统，以总投资成本最小和用户充电成本最小为目标函数，利用了海象优化算法，对目标函数进行了两轮寻优，让优化后的选址方案在平衡投资商和用户利益的同时满足用户需求。Purpose of the invention: In response to the problems pointed out in the background technology, the present invention discloses a method and system for optimizing the re-layout of two-wheel electric vehicle charging piles on campus. The objective function is to minimize the total investment cost and the user charging cost. The walrus optimization algorithm is used to perform two rounds of optimization on the objective function, so that the optimized site selection plan can meet the user needs while balancing the interests of investors and users.
技术方案：本发明公开了一种校园两轮电动车充电桩再布局优化方法，包括：Technical solution: The present invention discloses a method for re-layout optimization of charging piles for two-wheeled electric vehicles on campus, comprising:
步骤(1)获取每日进出校园的两轮电动车数量，进出已有充电站的频次和用户使用校内充电桩位置分布数据；Step (1) obtaining the number of two-wheeled electric vehicles entering and leaving the campus every day, the frequency of entering and leaving existing charging stations, and the location distribution data of charging piles used by users on campus;
步骤(2)对获取的数据进行预处理和数据校准；Step (2) preprocessing and calibrating the acquired data;
步骤(3)构建以总投资成本最小和用户充电成本最小为目标函数，并根据预处理和校准后的数据确定选址方案的约束条件；Step (3) constructing an objective function with the minimum total investment cost and the minimum user charging cost, and determining the constraints of the site selection plan based on the preprocessed and calibrated data;
步骤(4)在满足约束条件下利用海象优化算法对总投资成本和用户充电成本最小分别为目标函数进行两轮寻优，在满足总投资成本最小且用户充电成本最小情况下，确定最佳两轮电动车充电桩布局方案，获取最终的充电桩位置及数量。Step (4) Under the constraint conditions, the walrus optimization algorithm is used to perform two rounds of optimization with the total investment cost and the user charging cost as the objective function respectively. Under the condition of minimizing the total investment cost and the user charging cost, the optimal two-wheel electric vehicle charging pile layout plan is determined to obtain the final charging pile location and number.
进一步地，所述步骤(2)对获取数据的预处理和数据校准，具体为：Furthermore, the step (2) of preprocessing and calibrating the acquired data is specifically as follows:
对步骤(1)中获取的数据采取读取、滤波、数据格式转换的预处理过程，并对预处理后的数据使用多维稳定性校准算法进行数据校准，对校准后的数据进行探索性分析，拟定充电桩选址方案并确定选址方案需满足的约束条件，所述约束条件即用户选取充电桩的偏好和需求，包括充电桩位置、用户寻找目标充电桩时间、用户排队等待时间。The data obtained in step (1) is preprocessed by reading, filtering, and data format conversion, and the preprocessed data is calibrated using a multidimensional stability calibration algorithm. The calibrated data is subjected to exploratory analysis to formulate a charging pile site selection plan and determine the constraints that the site selection plan must meet. The constraints are the user's preferences and needs for selecting charging piles, including the location of the charging pile, the time it takes the user to find the target charging pile, and the time the user waits in line.
进一步地，所述步骤(3)中以总投资成本最小构建目标函数具体为：Furthermore, the objective function constructed with the minimum total investment cost in step (3) is specifically:
包括两轮电动车充电桩的投资成本最小、充电桩线路布排成本最小和后期维护维修成本最小，目标函数表示如下：Including minimizing the investment cost of two-wheeled electric vehicle charging piles, minimizing the wiring cost of charging piles, and minimizing the subsequent maintenance and repair costs. The objective function is expressed as follows:
SPmin＝P1+P2+P3SPmin ＝P1 +P2 +P3
式中，SPmin表示总投资成本最小；P1表示充电桩投资成本；P2表示充电桩线路布排成本；P3表示后期维修维护成本；P1具体包括建设两轮电动车充电站的地皮投资成本、基于所需充电桩数量的投资成本、建设充电桩所需人工材料投资成本和电费投资成本；P2具体包括充电桩线路布排成本包括电缆电线投资成本；P3具体包括后期维修维护成本包括雇佣人工费成本、充电桩破损维修和定期维护成本，P1、P2、P3的具体表达式为：Wherein, SPmin indicates the minimum total investment cost; P1 indicates the investment cost of charging piles; P2 indicates the wiring cost of charging piles; P3 indicates the later repair and maintenance cost; P1 specifically includes the land investment cost for building a two-wheeled electric vehicle charging station, the investment cost based on the required number of charging piles, the investment cost of labor and materials required for building charging piles, and the investment cost of electricity; P2 specifically includes the wiring cost of charging piles, including the investment cost of cables and wires; P3 specifically includes the later repair and maintenance cost, including the cost of hiring labor, the cost of charging pile damage repair and regular maintenance. The specific expressions of P1 , P2 , and P3 are:
P2＝LSxianP2 ＝LSxian
P3＝Sp+Sxiu+OP3 =Sp +Sxiu +O
式中，N为优化后的充电桩总数量；r为折旧率；a为充电桩的使用年限；φ为电动车充电站内基础设施、道路和其他设施占地面积折算到充电桩面积的比例系数；Si为第i个充电桩的占地面积；Qi为第i个充电桩的单位土地价格；Spri为充电桩的采购单价；C为建设充电桩所需人工材料费成本；Sele为单个充电桩所需电费；L为所需电线总长度；Sxian为电线单价；Sp为雇佣人工费；Sxiu为充电桩维修费；O为充电桩定期维修成本。Wherein, N is the total number of charging piles after optimization; r is the depreciation rate; a is the service life of the charging pile; φ is the ratio coefficient of the area occupied by infrastructure, roads and other facilities in the electric vehicle charging station to the area of the charging pile;Si is the area occupied by the i-th charging pile;Qi is the unit land price of the i-th charging pile;Spri is the purchase price of the charging pile; C is the labor and material cost required to build the charging pile;Sele is the electricity cost required for a single charging pile; L is the total length of the required wire;Sxian is the unit price of the wire;Sp is the labor cost;Sxiu is the maintenance cost of the charging pile; O is the regular maintenance cost of the charging pile.
进一步地，所述步骤(3)中以用户充电成本最小构建目标函数具体为：Furthermore, in step (3), the objective function constructed with the minimum user charging cost is specifically:
包括用户寻找目标充电桩时间成本最少、用户充电费用成本最小和排队等待损耗成本最少，目标函数具体表达式为：The objective function includes minimizing the time cost of users looking for the target charging pile, minimizing the user charging cost, and minimizing the waiting loss cost. The specific expression of the objective function is:
Umin＝w1U1+w2U2+w3U3Umin = w1 U1 + w2 U2 + w3 U3
式中，Umin表示用户充电成本最小；U1表示用户寻找目标充电桩的时间；U2表示用户充电费用成本；U3表示用户排队等待损耗的成本；w1，w2，w3分别为U1，U2，U3对应的权重，权重由用户本身需求决定；In the formula, Umin indicates the minimum charging cost for the user; U1 indicates the time it takes for the user to find the target charging pile; U2 indicates the charging cost for the user; U3 indicates the cost of the user's waiting in line; w1 , w2 , w3 are the weights corresponding to U1 , U2 , and U3 respectively, and the weights are determined by the user's own needs;
所述用户寻找目标充电桩时间U1具体表达式如下：The specific expression of the timeU1 for the user to find the target charging pile is as follows:
式中，dm为用户到目标充电桩的路段m的长度；M为路段个数；υm为用户在路段m的平均速度；Tuser为用户在路段m的平均行驶时间；Where, dm is the length of the road section m from the user to the target charging pile; M is the number of road sections; υm is the average speed of the user on the road section m; Tuser is the average driving time of the user on the road section m;
所述用户充电费用成本U2具体表达式如下：The specific expression of the user charging costU2 is as follows:
U2＝ψhTδU2 = ψh Tδ
式中，ψh为充电桩的充电费用单价；T为充电时间；δ为用户充电次数；In the formula,ψh is the charging cost unit price of the charging pile; T is the charging time; δ is the number of times the user charges;
所述用户排队等待损耗成本U3具体表达式如下：The specific expression of the user queuing waiting loss cost U3 is as follows:
式中，H为用户到达目标充电桩时正在排队的H个其他用户，T前为排队的第h个用户所用充电时间；Th-1为用户到达目标充电桩时，正在充电的用户剩下所需使用充电桩的时间；Where H is the H other users who are queuing when the user arrives at the target charging pile, Tis the charging time used by the h-th user in the queue; Th-1 is the remaining time required for the user who is charging to use the charging pile when the user arrives at the target charging pile;
所述权重计算表达式如下：The weight calculation expression is as follows:
w1,w2,w3∈{0,1},w1+w2+w3＝1w1 ,w2 ,w3 ∈{0,1},w1 +w2 +w3 ＝1
权重大小由用户自身需求决定，也就是由用户选取充电桩的偏好和需求决定。The weight is determined by the user's own needs, that is, by the user's preferences and needs for selecting charging piles.
进一步地，所述步骤(4)中利用海象优化算法对目标函数进行寻优求解，具体为：Furthermore, in step (4), the objective function is optimized and solved using the walrus optimization algorithm, specifically:
步骤5.1：种群初始化并输入参数值，计算适应度并记录最佳位置，初始化和适应度函数值表达式如下：Step 5.1: Initialize the population and input parameter values, calculate the fitness and record the best position. The initialization and fitness function value expressions are as follows:
式中，X表示种群矩阵；F表示适应度函数值；Xi表示第i个成员；N表示种群大小；m表示维度；In the formula, X represents the population matrix; F represents the fitness function value;Xi represents the i-th member; N represents the population size; m represents the dimension;
步骤5.2：当危险信号过高，即Dangersignal≥1时，海象种群会进行迁徙行为，迁徙到更适合种群生存的地方，其位置更新公式、危险信号和与危险信号对应的安全信号表达式如下：Step 5.2: When the danger signal is too high, that is, Dangersignal ≥ 1, the walrus population will migrate to a place more suitable for the survival of the population. The position update formula, danger signal and safety signal corresponding to the danger signal are expressed as follows:
Safetysignal＝y3Safetysignal＝y3
式中，为i个个体在第j个维度上的更新位置；/>为当前位置；Migrationstep为海象运动的步长；/>为种群中随机选择的两个警惕者位置对应的迁移步长控制因子；A和G为危险因子；α随着迭代次数的增加，从1减小到0；y1，y2，y3是在[0,1]内的随机数；In the formula, is the updated position of the i-th individual in the j-th dimension;/> is the current position; Migrationstep is the step length of the walrus movement; /> is the migration step control factor corresponding to the two randomly selected vigilant positions in the population; A and G are risk factors; α decreases from 1 to 0 as the number of iterations increases; y1 , y2 , y3 are random numbers in [0,1];
步骤5.3：当危险信号较低，即Dangersignal<1且安全信号Safetysignal大于0.5时，海象种群会进行栖息行为，雄性为扩大搜索范围进行位置更新，雌性和幼年海象因为受到雄性海象和天敌的影响，更新其当前位置，其位置更新公式如下：Step 5.3: When the danger signal is low, that is, Dangersignal<1 and the safety signal Safetysignal is greater than 0.5, the walrus population will perform roosting behavior. Males will update their positions to expand the search range. Females and young walruses will update their current positions due to the influence of male walruses and natural enemies. The position update formula is as follows:
式中，为雄性海象位置；/>为领头雄性海象位置；I为幼年海象遇险系数，是[0,1]的随机数；B为参考安全位置；LF为基于Levy运动分布的随机数向量；In the formula, For male walrus position; /> is the position of the leading male walrus; I is the distress coefficient of the juvenile walrus, which is a random number in [0,1]; B is the reference safe position; LF is a random number vector based on Levy motion distribution;
步骤5.4：当安全信号小于0.5时，海象觅食时会受到天敌攻击，海象会采取逃跑行为，根据同伴发出的危险信号逃离当前活动区域，进行位置的更新，此行为发生在算法迭代后期，对种群有一定程度的扰动，有助于全局搜索，其位置更新公式如下：Step 5.4: When the safety signal is less than 0.5, the walrus will be attacked by natural enemies while foraging. The walrus will take escape behavior and escape from the current activity area according to the danger signal sent by its companions, and update its position. This behavior occurs in the late iteration of the algorithm, which has a certain degree of disturbance to the population and is helpful for global search. The position update formula is as follows:
式中，X1和X2为影响海象逃跑行为的两个权重；为第二只海象在当前迭代中的位置；b，e为逃跑系数；y4为[0,1]的随机数；In the formula,X1 andX2 are two weights that affect the walrus's escape behavior; is the position of the second walrus in the current iteration; b, e are escape coefficients; y4 is a random number in [0,1];
步骤5.5：根据上述步骤更新位置，寻找全局最优解，输出目标函数值并判断是否符合终止条件，若不满足，则重新计算适应度返回步骤5.1；若满足，则输出最优解，所述最优解即满足约束条件下的最小投资成本和最小用户充电成本，根据最小投资成本和最小用户充电成本进一步确定最终充电桩的建设位置、数量，完成充电桩的布局优化。Step 5.5: Update the position according to the above steps, find the global optimal solution, output the objective function value and determine whether it meets the termination conditions. If not, recalculate the fitness and return to step 5.1; if satisfied, output the optimal solution, which is the minimum investment cost and minimum user charging cost under the constraints. According to the minimum investment cost and the minimum user charging cost, further determine the final construction location and quantity of the charging piles to complete the layout optimization of the charging piles.
进一步地，所述步骤5.1中输入参数值具体如下：Furthermore, the input parameter values in step 5.1 are specifically as follows:
以总投资成本最小，所输入的参数值为：充电桩的投资成本P1、充电桩线路布排成本P2和后期维护维修成本P3；其对应的输入数据为P1、P2、P3对应下的已知数据，具体为充电桩的使用年限、比例系数、充电桩的占地面积、充电桩的单位土地价格、充电桩的采购单价、人工材料费成本、充电桩所需电费、电线总长度、电线单价、雇佣人工费以及充电桩维修费、充电桩定期维修成本；确定在总投资成本最小情况下的充电桩总数量；With the minimum total investment cost, the input parameter values are: the investment cost of the charging pileP1 , the wiring cost of the charging pileP2 and the subsequent maintenance and repair costP3 ; the corresponding input data are the known data corresponding toP1 ,P2 , andP3 , specifically the service life of the charging pile, the proportionality coefficient, the floor area of the charging pile, the unit land price of the charging pile, the purchase unit price of the charging pile, the labor and material cost, the electricity cost required for the charging pile, the total length of the wire, the unit price of the wire, the labor cost, the maintenance cost of the charging pile, and the regular maintenance cost of the charging pile; determine the total number of charging piles with the minimum total investment cost;
以用户充电成本最小，所输入的参数具体为：用户寻找目标充电桩时间成本U1、用户充电费用成本U2和排队等待损耗成本U3；其对应的输入数据为U1、U2和U3对应下的已知数据，具体为用户在路段m的平均行驶时间、路段个数、充电桩的充电费用单价、充电时间、用户充电次数、排队的第h个用户所用充电时间、用户到达目标充电桩时，正在充电的用户剩下所需使用充电桩的时间；确定在满足总投资成本最小且用户充电成本最小情况下的充电桩总数量以及充电桩位置；With the user charging cost minimized, the input parameters are specifically: the user's time cost for finding the target charging pile U1 , the user's charging cost U2 and the queuing waiting loss cost U3 ; the corresponding input data are the known data corresponding to U1 , U2 and U3 , specifically the average driving time of the user on road section m, the number of road sections, the charging cost unit price of the charging pile, the charging time, the number of user charging times, the charging time used by the h-th user in the queue, and the remaining time for the user who is charging to use the charging pile when the user arrives at the target charging pile; determine the total number of charging piles and the location of the charging piles under the condition of minimizing the total investment cost and minimizing the user's charging cost;
本发明还公开一种基于上述校园两轮电动车充电桩再布局优化方法的系统，包括数据监测采集模块、数据分析处理模块和布局优化模块；The present invention also discloses a system based on the above campus two-wheel electric vehicle charging pile re-layout optimization method, comprising a data monitoring and acquisition module, a data analysis and processing module and a layout optimization module;
所述数据监测采集模块，用于从校园图像监视器、打卡器和门禁器中获取每日进出校园的两轮电动车数量，进出充电站的频次和用户选取充电桩的偏好和需求分布点数据；The data monitoring and acquisition module is used to obtain the number of two-wheeled electric vehicles entering and leaving the campus every day, the frequency of entering and leaving the charging station, and the user's preference for selecting charging piles and the distribution point data of demand from the campus image monitor, time clock and access control device;
所述数据分析处理模块，用于对所述数据监测采集模块获取的数据进行预处理和数据校正，并对校准后的数据进行探索性数据分析，拟定选址方案；The data analysis and processing module is used to pre-process and calibrate the data acquired by the data monitoring and acquisition module, and to perform exploratory data analysis on the calibrated data to formulate a site selection plan;
所述布局优化模块，用于在充分考虑用户选择偏好和需求的情况下，分别以总投资成本和用户充电成本最小构建目标函数，并根据数据分析结果确定选址方案的约束条件，利用海象优化算法进行求解，实现对两轮电动车充电桩的布局优化。The layout optimization module is used to construct the objective function with the minimum total investment cost and user charging cost respectively, taking full consideration of user selection preferences and needs, and determine the constraint conditions of the site selection plan according to the data analysis results, and use the walrus optimization algorithm to solve it, so as to achieve the layout optimization of the two-wheel electric vehicle charging piles.
有益效果：Beneficial effects:
1、本发明结合校园图像监视器、打卡器和门禁器对电动车用户的日常停放点和选择偏好点进行了数据采集和分析，使得优化后的布局更加迎合用户的利益和需求；对采集的数据进行了预处理和校准，确保了数据的质量。1. The present invention combines campus image monitors, time clocks and access control devices to collect and analyze data on daily parking spots and preferred spots of electric vehicle users, so that the optimized layout better caters to the interests and needs of users; the collected data is preprocessed and calibrated to ensure the quality of the data.
2、本发明以投资总成本最小和用户充电成本最小构建目标函数，利用优化算法对目标函数进行了两轮优化，得到的最终选址方案平衡了投资商与用户之间的利益；目标函数的求解利用了较新的海象优化算法，具有很好的平衡能力和全局搜索能力。2. The present invention constructs the objective function by minimizing the total investment cost and the user charging cost, and uses the optimization algorithm to perform two rounds of optimization on the objective function. The final site selection plan balances the interests between investors and users. The solution of the objective function uses the newer walrus optimization algorithm, which has good balancing ability and global search ability.
3、本发明能够对校园两轮电动车充电桩的布局进行合理优化，实现两轮电动车的合理停放充电。3. The present invention can reasonably optimize the layout of charging piles for two-wheeled electric vehicles on campus, thereby achieving reasonable parking and charging of two-wheeled electric vehicles.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
图1为本发明的布局优化模块流程图。FIG1 is a flow chart of a layout optimization module of the present invention.
具体实施方式Detailed ways
下面结合附图对本发明的技术方案作进一步说明。The technical solution of the present invention is further described below in conjunction with the accompanying drawings.
本实施例提供了一种校园两轮电动车充电桩再布局优化方法，包括：This embodiment provides a method for optimizing the layout of charging piles for two-wheeled electric vehicles on campus, including:
(1)从校园图像监视器、打卡器和门禁器中获取每日进出校园的两轮电动车数量，进出充电站的频次和用户选取充电桩的偏好和需求分布点数据。(1) Obtain data on the number of two-wheeled electric vehicles entering and leaving the campus every day, the frequency of entering and leaving the charging station, and the user's preference and demand distribution point data for selecting charging piles from campus image monitors, time clocks, and access control devices.
(2)对获取的数据进行预处理和数据校准。对所述步骤(1)中获取的数据采取读取、滤波、数据格式转换一系列的预处理过程，并对预处理后的数据使用多维稳定性校准算法进行数据校准。对校准后的数据进行探索性分析，拟定充电桩选址方案并确定选址方案需满足的约束条件。约束条件即用户选取充电桩的偏好和需求，包括充电桩位置、用户寻找目标充电桩时间、用户排队等待时间。(2) Preprocessing and calibrating the acquired data. The data acquired in step (1) is preprocessed through a series of processes, including reading, filtering, and data format conversion, and the preprocessed data is calibrated using a multidimensional stability calibration algorithm. An exploratory analysis is performed on the calibrated data to formulate a charging pile site selection plan and determine the constraints that the site selection plan must meet. The constraints are the user's preferences and requirements for selecting charging piles, including the location of the charging pile, the time it takes for the user to find the target charging pile, and the time it takes the user to wait in line.
多维稳定性校准算法通过引入稳定性参数和准确性参数增强算法校准的精度和准确性，在对数据校准的过程中，对于时间复杂度优化，采用数值积分法，将连续的积分运算转化为离散的求和运算；对于空间复杂度优化，采用数据压缩法，将数据合并存储，实现传感器和图像数据的校准。The multi-dimensional stability calibration algorithm enhances the precision and accuracy of algorithm calibration by introducing stability parameters and accuracy parameters. In the process of data calibration, for time complexity optimization, the numerical integration method is used to convert continuous integration operations into discrete summation operations; for space complexity optimization, the data compression method is used to merge and store the data to realize the calibration of sensor and image data.
(3)对上述校准后的数据进行探索性数据分析，拟定选址方案，充分考虑用户选择偏好和需求，构建以总投资成本最小和用户充电成本最小为目标函数，并根据预处理和校准后的数据确定选址方案的约束条件。(3) Conduct exploratory data analysis on the calibrated data and formulate a site selection plan, taking into full account user preferences and needs, construct an objective function with the minimum total investment cost and the minimum user charging cost, and determine the constraints of the site selection plan based on the preprocessed and calibrated data.
以总投资成本最小构建目标函数具体为：The objective function constructed with the minimum total investment cost is as follows:
包括两轮电动车充电桩的投资成本最小、充电桩线路布排成本最小和后期维护维修成本最小，目标函数表示如下：Including minimizing the investment cost of two-wheeled electric vehicle charging piles, minimizing the wiring cost of charging piles, and minimizing the subsequent maintenance and repair costs. The objective function is expressed as follows:
SPmin＝P1+P2+P3SPmin ＝P1 +P2 +P3
式中，SPmin表示总投资成本最小；P1表示充电桩投资成本；P2表示充电桩线路布排成本；P3表示后期维修维护成本；In the formula, SPmin indicates the minimum total investment cost; P1 indicates the investment cost of the charging pile; P2 indicates the wiring cost of the charging pile; P3 indicates the subsequent repair and maintenance cost;
P1具体包括建设两轮电动车充电站的地皮投资成本、基于所需充电桩数量的投资成本、建设充电桩所需人工材料投资成本和电费投资成本；P2具体包括充电桩线路布排成本包括电缆电线投资成本；P3具体包括后期维修维护成本包括雇佣人工费成本、充电桩破损维修和定期维护成本，P1、P2、P3的具体表达式为：P1 specifically includes the land investment cost for building a two-wheeled electric vehicle charging station, the investment cost based on the number of charging piles required, the investment cost of labor and materials required for building charging piles, and the investment cost of electricity;P2 specifically includes the wiring cost of charging piles, including the investment cost of cables and wires;P3 specifically includes the later repair and maintenance cost, including the cost of hiring labor, the cost of charging pile damage repair and regular maintenance. The specific expressions ofP1 ,P2 , andP3 are:
P2＝LSxianP2 ＝LSxian
P3＝Sp+Sxiu+OP3 =Sp +Sxiu +O
式中，N为优化后的充电桩总数量；r为折旧率；a为充电桩的使用年限；φ为电动车充电站内基础设施、道路和其他设施。占地面积折算到充电桩面积的比例系数；Si为第i个充电桩的占地面积；Qi为第i个充电桩的单位土地价格；Spri为充电桩的采购单价；C为建设充电桩所需人工材料费成本；Sele为单个充电桩所需电费；L为所需电线总长度；Sxian为电线单价；Sp为雇佣人工费；Sxiu为充电桩维修费；O为充电桩定期维修成本。Where N is the total number of charging piles after optimization; r is the depreciation rate; a is the service life of the charging pile; φ is the infrastructure, roads and other facilities in the electric vehicle charging station. The ratio coefficient of the land area to the charging pile area;Si is the land area of the i-th charging pile;Qi is the unit land price of the i-th charging pile;Spri is the purchase price of the charging pile; C is the labor and material cost required to build the charging pile;Sele is the electricity cost required for a single charging pile; L is the total length of the required wire;Sxian is the unit price of the wire;Sp is the labor cost;Sxiu is the maintenance cost of the charging pile; O is the regular maintenance cost of the charging pile.
以用户充电成本最小构建目标函数具体为：The objective function constructed with the minimum user charging cost is as follows:
包括用户寻找目标充电桩时间最少、用户充电费用成本最小和排队等待损耗成本最少，目标函数具体表达式为：The objective function includes minimizing the time users spend searching for the target charging pile, minimizing the user charging cost, and minimizing the waiting cost. The specific expression of the objective function is:
Umin＝w1U1+w2U2+w3U3Umin = w1 U1 + w2 U2 + w3 U3
式中，Umin表示用户充电成本最小；U1表示用户寻找目标充电桩的时间；U2表示用户充电费用成本；U3表示用户排队等待损耗的成本；w1，w2，w3分别为U1，U2，U3对应的权重，权重由用户本身需求决定；In the formula, Umin indicates the minimum charging cost for the user; U1 indicates the time it takes for the user to find the target charging pile; U2 indicates the charging cost for the user; U3 indicates the cost of the user's waiting in line; w1 , w2 , w3 are the weights corresponding to U1 , U2 , and U3 respectively, and the weights are determined by the user's own needs;
所述用户寻找目标充电桩时间U1具体表达式如下：The specific expression of the timeU1 for the user to find the target charging pile is as follows:
式中，dm为用户到目标充电桩的路段m的长度；M为路段个数；υm为用户在路段m的平均速度；Tuser为用户在路段m的平均行驶时间；Where, dm is the length of the road section m from the user to the target charging pile; M is the number of road sections; υm is the average speed of the user on the road section m; Tuser is the average driving time of the user on the road section m;
所述用户充电费用成本U2具体表达式如下：The specific expression of the user charging costU2 is as follows:
U2＝ψhTδU2 = ψh Tδ
式中，ψh为充电桩的充电费用单价；T为充电时间；δ为用户充电次数；In the formula,ψh is the charging cost unit price of the charging pile; T is the charging time; δ is the number of times the user charges;
所述用户排队等待损耗成本U3具体表达式如下：The specific expression of the user queuing waiting loss cost U3 is as follows:
式中，H为用户到达目标充电桩时正在排队的H个其他用户，T前为排队的第h个用户所用充电时间；Th-1为用户到达目标充电桩时，正在充电的用户剩下所需使用充电桩的时间；Where H is the H other users who are queuing when the user arrives at the target charging pile, Tis the charging time used by the h-th user in the queue; Th-1 is the remaining time required for the user who is charging to use the charging pile when the user arrives at the target charging pile;
所述权重计算表达式如下：The weight calculation expression is as follows:
w1,w2,w3∈{0,1},w1+w2+w3＝1w1 ,w2 ,w3 ∈{0,1},w1 +w2 +w3 ＝1
权重大小由用户自身需求决定，也就是由用户选取充电桩的偏好和需求决定。The weight is determined by the user's own needs, that is, by the user's preferences and needs for selecting charging piles.
(4)在满足约束条件下利用海象优化算法对总投资成本和用户充电成本最小分别为目标函数进行两轮寻优，在满足总投资成本最小且用户充电成本最小情况下，确定最佳两轮电动车充电桩布局方案，获取最终的充电桩位置及数量。(4) Under the constraints, the walrus optimization algorithm is used to perform two rounds of optimization with the total investment cost and the user charging cost as the objective function. Under the conditions of minimizing the total investment cost and the user charging cost, the optimal two-wheel electric vehicle charging pile layout plan is determined to obtain the final charging pile location and number.
如附图1所示，利用海象优化算法对目标函数进行寻优求解，具体为：As shown in Figure 1, the objective function is optimized and solved using the walrus optimization algorithm, specifically:
海象种群行为会受危险信号和安全信号影响，信号的高低会决定海象是进行迁徙行为、栖息行为还是逃跑行为，从而更新其当前位置，寻找全局最优，海象优化算法求解过程如下：The behavior of walrus populations is affected by danger signals and safety signals. The level of the signal determines whether the walrus will migrate, roost, or escape, thereby updating its current position and finding the global optimum. The solution process of the walrus optimization algorithm is as follows:
步骤1：种群初始化并输入参数值，计算适应度并记录最佳位置，初始化和适应度函数值表达式如下：Step 1: Initialize the population and input parameter values, calculate the fitness and record the best position. The initialization and fitness function value expressions are as follows:
式中，X表示种群矩阵；F表示适应度函数值；Xi表示第i个成员；N表示种群大小；m表示维度。Where X represents the population matrix; F represents the fitness function value;Xi represents the i-th member; N represents the population size; and m represents the dimension.
以总投资成本最小，所输入的参数值为：充电桩的投资成本P1、充电桩线路布排成本P2和后期维护维修成本P3；其对应的输入数据为P1、P2、P3对应下的已知数据，具体为充电桩的使用年限、比例系数、充电桩的占地面积、充电桩的单位土地价格、充电桩的采购单价、人工材料费成本、充电桩所需电费、电线总长度、电线单价、雇佣人工费以及充电桩维修费、充电桩定期维修成本；确定在总投资成本最小情况下的充电桩总数量。With the minimum total investment cost, the input parameter values are: the investment cost of the charging pileP1 , the wiring cost of the charging pileP2 and the subsequent maintenance and repair costP3 ; the corresponding input data are the known data corresponding toP1 ,P2 , andP3 , specifically the service life of the charging pile, the proportional coefficient, the floor area of the charging pile, the unit land price of the charging pile, the purchase unit price of the charging pile, the labor and material cost, the electricity cost required for the charging pile, the total length of the wire, the unit price of the wire, the labor cost, the charging pile maintenance fee, and the regular maintenance cost of the charging pile; determine the total number of charging piles under the condition of the minimum total investment cost.
以用户充电成本最小，所输入的参数具体为：用户寻找目标充电桩时间成本U1、用户充电费用成本U2和排队等待损耗成本U3；其对应的输入数据为U1、U2和U3对应下的已知数据，具体为用户在路段m的平均行驶时间、路段个数、充电桩的充电费用单价、充电时间、用户充电次数、排队的第h个用户所用充电时间、用户到达目标充电桩时，正在充电的用户剩下所需使用充电桩的时间；确定在满足总投资成本最小且用户充电成本最小情况下的充电桩总数量以及充电桩位置。With the user charging cost minimized, the input parameters are specifically: the time costU1 of the user looking for the target charging pile, the user charging costU2 and the queuing loss costU3 ; the corresponding input data are the known data corresponding toU1 ,U2 andU3 , specifically the average driving time of the user on section m, the number of sections, the unit price of the charging cost of the charging pile, the charging time, the number of user charging times, the charging time used by the hth user in the queue, and the remaining time required for the user who is charging to use the charging pile when the user arrives at the target charging pile; determine the total number of charging piles and the locations of the charging piles under the condition of minimizing the total investment cost and minimizing the user charging cost.
步骤2：当危险信号过高，即Dangersignal≥1时，海象种群会进行迁徙行为，迁徙到更适合种群生存的地方，其位置更新公式、危险信号和与危险信号对应的安全信号表达式如下：Step 2: When the danger signal is too high, that is, Dangersignal ≥ 1, the walrus population will migrate to a place more suitable for the survival of the population. The position update formula, danger signal and safety signal corresponding to the danger signal are expressed as follows:
Safetysignal＝y3Safetysignal＝y3
式中，为i个个体在第j个维度上的更新位置；/>为当前位置；Migrationstep为海象运动的步长；/>为种群中随机选择的两个警惕者位置对应的迁移步长控制因子；A和G为危险因子；α随着迭代次数的增加，从1减小到0；y1，y2，y3是在[0,1]内的随机数。In the formula, is the updated position of the i-th individual in the j-th dimension;/> is the current position; Migrationstep is the step length of the walrus movement; /> is the migration step control factor corresponding to the positions of two randomly selected vigilant persons in the population; A and G are risk factors; α decreases from 1 to 0 as the number of iterations increases; y1 , y2 , y3 are random numbers in [0,1].
步骤3：当危险信号较低，即Dangersignal<1且安全信号Safetysignal大于0.5时，海象种群会进行栖息行为，雄性为扩大搜索范围进行位置更新，雌性和幼年海象因为受到雄性海象和天敌的影响，更新其当前位置，其位置更新公式如下：Step 3: When the danger signal is low, that is, Dangersignal<1 and the safety signal Safetysignal is greater than 0.5, the walrus population will perform roosting behavior. Males will update their positions to expand the search range. Females and young walruses will update their current positions due to the influence of male walruses and natural enemies. The position update formula is as follows:
式中，为雄性海象位置；/>为领头雄性海象位置；I为幼年海象遇险系数，是[0,1]的随机数；B为参考安全位置；LF为基于Levy运动分布的随机数向量；In the formula, For male walrus position; /> is the position of the leading male walrus; I is the distress coefficient of the juvenile walrus, which is a random number in [0,1]; B is the reference safe position; LF is a random number vector based on Levy motion distribution;
步骤4：当安全信号小于0.5时，海象觅食时会受到天敌攻击，海象会采取逃跑行为，根据同伴发出的危险信号逃离当前活动区域，进行位置的更新，此行为发生在算法迭代后期，对种群有一定程度的扰动，有助于全局搜索，其位置更新公式如下：Step 4: When the safety signal is less than 0.5, the walrus will be attacked by natural enemies while foraging. The walrus will flee and escape from the current activity area according to the danger signal sent by its companions, and update its position. This behavior occurs in the late stage of the algorithm iteration, which has a certain degree of disturbance to the population and is helpful for global search. The position update formula is as follows:
式中，X1和X2为影响海象逃跑行为的两个权重；为第二只海象在当前迭代中的位置；b，e为逃跑系数；y4为[0,1]的随机数；In the formula,X1 andX2 are two weights that affect the walrus's escape behavior; is the position of the second walrus in the current iteration; b, e are escape coefficients; y4 is a random number in [0,1];
步骤5：根据上述步骤更新位置，寻找全局最优解，输出目标函数值并判断是否符合终止条件，若不满足，则重新计算适应度返回步骤1；若满足，则输出最优解，最优解即满足约束条件下的最小投资成本和最小用户充电成本，根据最小投资成本和最小用户充电成本进一步确定最终充电桩的建设位置、数量，完成充电桩的布局优化。Step 5: Update the position according to the above steps, find the global optimal solution, output the objective function value and determine whether it meets the termination conditions. If not, recalculate the fitness and return to step 1; if satisfied, output the optimal solution. The optimal solution is the minimum investment cost and the minimum user charging cost under the constraints. According to the minimum investment cost and the minimum user charging cost, further determine the final construction location and quantity of charging piles to complete the layout optimization of charging piles.
上述校园两轮电动车充电桩再布局优化方法对应的校园两轮电动车充电桩布局优化系统，包括数据监测采集模块、数据分析处理模块和布局优化模块。各模块之间通过数字信号进行信息交互。The campus two-wheeled electric vehicle charging pile layout optimization system corresponding to the campus two-wheeled electric vehicle charging pile layout optimization method includes a data monitoring and acquisition module, a data analysis and processing module, and a layout optimization module. The modules exchange information through digital signals.
数据监测采集模块用于从校园图像监视器、打卡器和门禁器中获取每日进出校园的两轮电动车数量，进出充电站的频次和用户选取充电桩的偏好和需求分布点数据。The data monitoring and acquisition module is used to obtain the number of two-wheeled electric vehicles entering and leaving the campus every day, the frequency of entering and exiting the charging station, and the user's preference and demand distribution point data for selecting charging piles from campus image monitors, time clocks and access control devices.
数据分析处理模块用于对所述数据监测采集模块获取的数据进行预处理和数据校准，并对校准后的数据进行探索性数据分析，拟定选址方案。The data analysis and processing module is used to preprocess and calibrate the data acquired by the data monitoring and acquisition module, and to perform exploratory data analysis on the calibrated data to formulate a site selection plan.
布局优化模块用于在充分考虑用户选择偏好和需求的情况下，分别以总投资成本和用户充电成本最小构建目标函数，并根据数据分析结果确定选址方案的约束条件，利用海象优化算法进行求解，实现对两轮电动车充电桩的布局优化。The layout optimization module is used to construct the objective function with the minimum total investment cost and user charging cost respectively, taking full account of user selection preferences and needs, and determine the constraints of the site selection plan based on the data analysis results. It uses the walrus optimization algorithm to solve the problem and realize the layout optimization of two-wheel electric vehicle charging piles.
以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的技术人员应当理解：其依然可以对前述实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明实施例技术方案的精神和范围。The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410252240.4ACN118114826B (en) | 2024-03-05 | 2024-03-05 | Campus two-wheel electric vehicle charging pile re-layout optimization method and system |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410252240.4ACN118114826B (en) | 2024-03-05 | 2024-03-05 | Campus two-wheel electric vehicle charging pile re-layout optimization method and system |
| Publication Number | Publication Date |
|---|---|
| CN118114826Atrue CN118114826A (en) | 2024-05-31 |
| CN118114826B CN118114826B (en) | 2025-01-24 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410252240.4AActiveCN118114826B (en) | 2024-03-05 | 2024-03-05 | Campus two-wheel electric vehicle charging pile re-layout optimization method and system |
| Country | Link |
|---|---|
| CN (1) | CN118114826B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119005638A (en)* | 2024-10-21 | 2024-11-22 | 广州市交通规划研究院有限公司 | Front door space layout planning method and device based on motorcycle and electric vehicle pick-up and delivery study |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682765A (en)* | 2016-12-01 | 2017-05-17 | 四川大学 | Charging station optimization layout method and apparatus thereof |
| CN107886186A (en)* | 2017-10-16 | 2018-04-06 | 清华大学 | A kind of charging pile method to set up based on travelling data and Wei Nuotu zonings |
| US20210157312A1 (en)* | 2016-05-09 | 2021-05-27 | Strong Force Iot Portfolio 2016, Llc | Intelligent vibration digital twin systems and methods for industrial environments |
| CN115099462A (en)* | 2022-05-26 | 2022-09-23 | 南京邮电大学 | A method for optimal layout of electric vehicle charging station |
| CN115470600A (en)* | 2022-07-15 | 2022-12-13 | 广东工业大学 | Electric vehicle charging station planning method based on multi-objective optimization |
| CN117077985A (en)* | 2023-10-16 | 2023-11-17 | 浙江优能电力设计有限公司 | Electric vehicle charging pile planning method and system according to charging requirements |
| CN117557069A (en)* | 2024-01-10 | 2024-02-13 | 长峡数字能源科技(湖北)有限公司 | Charging pile site selection method and system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210157312A1 (en)* | 2016-05-09 | 2021-05-27 | Strong Force Iot Portfolio 2016, Llc | Intelligent vibration digital twin systems and methods for industrial environments |
| CN106682765A (en)* | 2016-12-01 | 2017-05-17 | 四川大学 | Charging station optimization layout method and apparatus thereof |
| CN107886186A (en)* | 2017-10-16 | 2018-04-06 | 清华大学 | A kind of charging pile method to set up based on travelling data and Wei Nuotu zonings |
| CN115099462A (en)* | 2022-05-26 | 2022-09-23 | 南京邮电大学 | A method for optimal layout of electric vehicle charging station |
| CN115470600A (en)* | 2022-07-15 | 2022-12-13 | 广东工业大学 | Electric vehicle charging station planning method based on multi-objective optimization |
| CN117077985A (en)* | 2023-10-16 | 2023-11-17 | 浙江优能电力设计有限公司 | Electric vehicle charging pile planning method and system according to charging requirements |
| CN117557069A (en)* | 2024-01-10 | 2024-02-13 | 长峡数字能源科技(湖北)有限公司 | Charging pile site selection method and system |
| Title |
|---|
| 杨锡运: "基于多源指标降维和WaoA-ELM模型的锂离子电池健康状态估计", 华北电力大学学报, 12 January 2024 (2024-01-12), pages 5 - 6* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119005638A (en)* | 2024-10-21 | 2024-11-22 | 广州市交通规划研究院有限公司 | Front door space layout planning method and device based on motorcycle and electric vehicle pick-up and delivery study |
| CN119005638B (en)* | 2024-10-21 | 2025-01-24 | 广州市交通规划研究院有限公司 | A method and device for planning the spatial layout in front of a school gate based on the theory of transportation by motorcycle and electric vehicles |
| Publication number | Publication date |
|---|---|
| CN118114826B (en) | 2025-01-24 |
| Publication | Publication Date | Title |
|---|---|---|
| CN111210633A (en) | A short-term traffic flow prediction method based on deep learning | |
| CN118114826A (en) | Campus two-wheel electric vehicle charging pile re-layout optimization method and system | |
| CN106897801A (en) | Method, device, equipment and storage medium that driver classifies | |
| CN113051811B (en) | A Multimodal Short-Term Traffic Congestion Prediction Method Based on GRU Network | |
| CN113222316A (en) | Change scene simulation method based on FLUS model and biodiversity model | |
| CN110164129A (en) | Single Intersection multi-lane traffic flow amount prediction technique based on GERNN | |
| CN112529305A (en) | Express item acquisition sequence prediction method based on deep learning | |
| CN114066503A (en) | A method for forecasting taxi demand based on constructing virtual service area | |
| CN113568068B (en) | Strong convection weather prediction method based on MPI parallel three-dimensional neural network | |
| CN116824861B (en) | Method and system for scheduling sharing bicycle based on multidimensional data of urban brain platform | |
| CN117830773A (en) | Fault prediction method, device, equipment and storage medium based on feature fusion | |
| CN112926809B (en) | Flight flow prediction method and system based on clustering and improved xgboost | |
| Ye et al. | Demand forecasting of online car‐hailing by exhaustively capturing the temporal dependency with TCN and Attention approaches | |
| CN118015832A (en) | A method for traffic volume prediction under adverse weather conditions | |
| CN116703005A (en) | User demand response potential prediction method and system | |
| CN115796023A (en) | A carbon quota-based power system scheduling method, device and equipment | |
| Zheng et al. | Improved iterative prediction for multiple stop arrival time using a support vector machine | |
| CN112288272B (en) | A method for compiling subway passenger flow regulation plan based on demand evolution and flow dissemination | |
| CN119494553A (en) | Logistics vehicle bill cost prediction method, device, equipment and storage medium | |
| CN110704789B (en) | Population dynamic measurement and calculation method and system based on 'urban superconcephalon' computing platform | |
| CN113947298B (en) | Vehicle-cargo matching method based on dual pointer network | |
| CN117674098A (en) | Multivariate load spatio-temporal probability distribution prediction method and system for different penetration rates | |
| CN111462483A (en) | A dynamic identification method for bridge overweight vehicles based on deep learning | |
| CN114330888B (en) | Order processing method, system and electronic equipment | |
| CN114493362B (en) | Electricity price adjustment method for distributed distribution network based on convolutional network and collaborative filtering |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |