Intelligent urban garbage treatment optimization scheduling method

Abstract

The invention discloses an intelligent urban garbage treatment optimization scheduling method, and relates to the technical field of intelligent urban garbage treatment and optimization scheduling, and the method comprises the steps: collecting garbage weight data of a garbage collection point, collecting real-time load data and position data of a garbage truck, and generating a garbage distribution map; based on garbage weight data in the garbage distribution map, an improved K-means clustering algorithm is adopted to divide garbage collection and transportation areas, and the garbage accumulation level of each area is calculated; based on the garbage accumulation level and the real-time load data, a multi-target genetic algorithm is adopted to calculate the shortest collection and transportation path of each area, and a garbage truck scheduling scheme is generated; and according to the garbage truck scheduling scheme, allocating garbage truck tasks, and carrying out cooperative scheduling on garbage trucks in adjacent areas based on the position data. According to the method, through cross-regional cooperative scheduling, the utilization rate of garbage truck resources is increased, the problem of overload or scheduling imbalance caused by excessive local garbage accumulation is reduced, and garbage collection and transportation are more elastic and adaptive.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent urban waste treatment and optimized scheduling, and particularly to an intelligent optimized scheduling method for urban waste treatment. Background Art

[0002] The traditional urban waste collection and transportation management mode mainly relies on manual experience and fixed routes for scheduling. This method has problems such as low collection and transportation efficiency, waste of human resources, and untimely monitoring of waste accumulation. In recent years, Internet of Things technology and artificial intelligence algorithms have been widely applied in the field of urban management. By deploying sensor devices at waste collection points, collecting data such as waste weight and vehicle location, and combining intelligent scheduling algorithms for waste collection and transportation optimization has become a research hotspot. Currently, domestic and foreign scholars have proposed various technical solutions such as path planning methods based on heuristic algorithms and waste generation prediction models based on spatio-temporal analysis. These solutions have improved the waste collection and transportation efficiency to a certain extent.

[0003] However, the existing waste collection and transportation scheduling schemes still have the following deficiencies: First, most schemes only consider the static distribution of waste collection points and fail to respond to the dynamic changes of waste accumulation in real time; Second, the existing regional division methods often use simple geographical partitioning and do not fully consider road network constraints and waste generation patterns; Third, the scheduling algorithms mainly focus on single-objective optimization, such as the shortest path or the fewest number of vehicles, and it is difficult to balance multiple scheduling objectives; Finally, there is a lack of collaborative scheduling mechanism between adjacent regions, resulting in unbalanced resource allocation between regions and affecting the overall collection and transportation efficiency. These problems seriously restrict the intelligent development of the urban waste collection and transportation system.

[0004] In view of the above problems, the present invention provides an intelligent optimized scheduling method for urban waste treatment. This method constructs a dynamic distribution map by real-time collecting waste weight data and vehicle location data, combines an improved K-means clustering algorithm for regional division and accumulation level calculation, and uses a multi-objective genetic algorithm to optimize the collection and transportation path, and realizes optimized resource allocation between regions through a collaborative scheduling mechanism. Summary of the Invention

[0005] In view of the problem that the existing waste collection and transportation regional division method lacks the ability of dynamic adjustment, the scheduling optimization method does not fully consider the waste vehicle load and the cross-regional collaborative mechanism, resulting in low collection and transportation efficiency and serious waste of resources, the present invention is proposed.

[0006] Therefore, the problem to be solved by the present invention is how to realize dynamic waste collection and transportation regional division and optimize the waste vehicle scheduling scheme based on waste distribution data and intelligent optimization algorithms, so as to improve the waste removal efficiency and reduce the operation cost.

[0007] To solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides an intelligent urban waste treatment optimization scheduling method,

[0009] which includes collecting waste weight data at waste collection points, collecting real-time load data and location data of waste trucks, and generating a waste distribution map; based on the waste weight data in the waste distribution map, using an improved K-means clustering algorithm to divide waste collection and transportation areas, and calculating the waste accumulation levels of each area; based on the waste accumulation levels and the real-time load data, using a multi-objective genetic algorithm to calculate the shortest collection and transportation paths for each area, and generating a waste truck scheduling plan; allocating waste truck tasks according to the waste truck scheduling plan, and performing collaborative scheduling on waste trucks in adjacent areas based on the location data.

[0010] As a preferred solution of the intelligent urban waste treatment optimization scheduling method of the present invention, where: allocating waste truck tasks according to the waste truck scheduling plan, and performing collaborative scheduling on waste trucks in adjacent areas based on the location data includes: based on the waste truck scheduling plan, extracting a scheduling instruction sequence for waste collection points from the Pareto optimal solution set; associating the scheduling instruction sequence with the location information of waste collection points in the waste distribution map to construct a task allocation feature vector; based on the task allocation feature vector, generating a collection and transportation path and a task list for the waste truck; based on the road network topology structure of the waste distribution map, extracting the real-time location data of waste trucks in adjacent areas to construct a cross-regional collaborative scheduling index; when the waste trucks in a certain area cannot completely handle the high accumulation situation, then according to the cross-regional collaborative scheduling index, automatically identify and call available waste trucks in adjacent areas for support; for cross-regional waste truck support, generating a collaborative scheduling instruction sequence and sending it to the relevant waste truck on-board terminal through a wireless transmission module; at the same time, real-time updating the running trajectories of the waste trucks for collaborative scheduling on the waste distribution map, and dynamically adjusting the waste collection progress according to the real-time load data.

[0011] As a preferred solution of the intelligent urban waste treatment optimization scheduling method described in the present invention, the method for generating the garbage truck scheduling plan is as follows: A scheduling feature vector is constructed by combining the garbage accumulation level and real-time load data, where the scheduling feature vector includes the spatial location information of the garbage collection points, the garbage accumulation level information, and the real-time load information of the garbage trucks; A chromosome coding rule is established based on the scheduling feature vector, where the chromosome coding length is equal to the number of garbage collection points to be served, and the gene position represents the access sequence number of the garbage collection points; Taking the minimization of the total path length and the maximization of the garbage accumulation level as the optimization objectives, a double-objective fitness function is constructed in combination with the real-time load data of the garbage trucks; Based on the double-objective fitness function, an improved genetic operator is used for population evolution, where the improved genetic operator includes an adaptive crossover operator based on the garbage accumulation level and a dynamic mutation operator; At the same time, an elite retention strategy and a tabu search mechanism are introduced during the population evolution process; The Pareto optimal solution set is obtained through the non-dominated sorting method, and the solution with the first path compression ratio is selected as the garbage truck scheduling plan; The garbage truck scheduling plan is converted into a garbage truck scheduling instruction sequence and sent to each garbage truck on-board terminal through a wireless transmission module, where the scheduling instruction sequence includes the access sequence number of the garbage collection points, the estimated arrival time, and the maximum loading capacity; At the same time, the running trajectory of the garbage truck is dynamically displayed on the garbage distribution map, and the garbage collection progress is updated according to the real-time load data.

[0012] As a preferred solution of the intelligent urban waste treatment optimization scheduling method described in the present invention, the elite retention strategy directly retains the individuals with the first fitness to the next generation, and the retention quantity is positively correlated with the garbage accumulation level; The tabu search mechanism is to record the access path and temporarily lift the tabu restriction when high-level garbage accumulation occurs to expand the search space.

[0013] As a preferred solution of the intelligent urban waste treatment optimization scheduling method described in the present invention, based on the garbage weight data in the garbage distribution map, an improved K-means clustering algorithm is used to divide the garbage collection and transportation areas, and the garbage accumulation level of each area is calculated, including: Extracting the spatial coordinates of the garbage collection points and the corresponding garbage weight data from the garbage distribution map to construct a feature vector matrix, and using the Z-score normalization method to normalize the feature vector matrix; Introducing an improved K-means clustering algorithm into the normalized feature vector matrix, optimizing the number of clustering clusters through the silhouette coefficient method, and calculating the distance between clusters in combination with the Mahalanobis distance constrained by the road network; Based on the distance between clusters, the urban area is divided into several garbage collection and transportation sub-areas, and at the same time, the garbage accumulation level within the garbage collection and transportation sub-areas is divided; Based on the result of the level division, the sub-area numbers and garbage accumulation levels are marked with different colors on the garbage distribution map, and the garbage accumulation intensity is reflected by the depth of the color.

[0014] As a preferred solution of the intelligent urban waste treatment optimization scheduling method described in the present invention, wherein: the method for dividing the waste accumulation level is as follows. When the waste growth rate at the waste collection points in this area is less than the first threshold and the average waste weight is less than the first preset average weight value, it is determined as the first-level accumulation; when the waste growth rate at the waste collection points in this area is between the first threshold and the second threshold and the average waste weight is between the first preset average weight value and the second preset average weight value, it is determined as the second-level accumulation; when the waste growth rate at the waste collection points in this area is between the second threshold and the third threshold and the average waste weight is between the second preset average weight value and the third preset average weight value, it is determined as the third-level accumulation; when the waste growth rate at the waste collection points in this area is greater than the third threshold and the average waste weight is equal to the third preset average weight value, it is determined as the fourth-level accumulation; when the waste growth rate at the waste collection points in this area is between the third threshold and the fourth threshold and this state has lasted for more than the set duration, it is determined as the fifth-level accumulation.

[0015] As a preferred solution of the intelligent urban waste treatment optimization scheduling method described in the present invention, wherein: the method for generating the waste distribution map is as follows. Install weight sensors at each waste collection point in the city, and at the same time install load sensors and GPS positioning modules on the garbage trucks; upload the waste weight data, the load data, and the position data to the data processing server through the wireless transmission module; establish an urban electronic map library in the data processing server, and match the waste weight data with the positions of the waste collection points in the electronic map library to generate a waste distribution heat map; superimpose the load data and the position data on the waste distribution heat map to form a waste distribution map including waste distribution and vehicle information.

[0016] In a second aspect, an embodiment of the present invention provides an intelligent urban waste treatment optimization scheduling system, which includes: a collection module for collecting the waste weight data of the waste collection points, and collecting the real-time load data and position data of the garbage trucks to generate a waste distribution map; a division module for dividing the waste collection and transportation areas based on the waste weight data in the waste distribution map by using an improved K-means clustering algorithm, and calculating the waste accumulation levels of each area; a generation module for calculating the shortest collection and transportation paths of each area by using a multi-objective genetic algorithm based on the waste accumulation levels and the real-time load data, and generating a garbage truck scheduling plan; a cooperative scheduling module for allocating garbage truck tasks according to the garbage truck scheduling plan and performing cooperative scheduling on the garbage trucks in adjacent areas based on the position data.

[0017] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor. The memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the intelligent urban waste treatment optimization scheduling method described in the first aspect of the present invention are implemented.

[0018] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, wherein: when the computer program instructions are executed by the processor, the steps of the intelligent urban waste treatment optimization scheduling method described in the first aspect of the present invention are implemented.

[0019] The beneficial effects of the present invention are as follows: By collecting the waste weight at waste collection points, the load capacity and location information of waste trucks in real time, a waste distribution map is constructed to provide data support for subsequent scheduling; Based on the improved K-means clustering algorithm, the waste collection and transportation areas are divided, and combined with the waste accumulation level, accurate area division is realized, improving the rationality of the collection and transportation plan; The multi-objective genetic algorithm is used to optimize the waste truck scheduling plan. While minimizing the collection and transportation path, the waste accumulation pressure is balanced, and the transportation efficiency is improved; Through cross-regional collaborative scheduling, when the local waste truck resources are insufficient, the available vehicles in adjacent regions are dynamically allocated to enhance the flexibility and emergency handling ability of the system; The scheduling plan is optimized through the elite retention strategy and the tabu search mechanism, and the waste collection progress is dynamically adjusted in combination with real-time data to achieve the intelligence, high efficiency and low cost of waste collection and transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings. Among them:

[0021] Figure 1 It is a flowchart of the intelligent urban waste treatment optimization scheduling method for Embodiment 1. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention will be described in detail below with reference to the drawings of the specification.

[0023] Many specific details are set forth in the following description in order to provide a thorough understanding of the present invention, but the present invention may be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0024] Second, the "one embodiment" or "embodiment" referred to herein means a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The "in one embodiment" that appears in different places in this specification does not all refer to the same embodiment, nor is it an embodiment that is separate or selectively mutually exclusive with other embodiments.

[0025] Embodiment 1

[0026] Referring to Figure 1 , which is the first embodiment of the present invention. This embodiment provides an intelligent urban waste treatment optimization scheduling method, including,

[0027] S1: Collect the waste weight data of waste collection points, and collect the real-time load data and location data of waste trucks to generate a waste distribution map;

[0028] Specifically, install weight sensors at each waste collection point in the city, and at the same time install load sensors and GPS positioning modules on waste trucks.

[0029] It should be noted that the weight sensor adopts a strain-type weighing structure, has a waterproof and dustproof function, and the measurement accuracy is ±0.5 kg; the weight sensor collects waste weight data every 10 minutes; the load sensor adopts a hydraulic weighing structure, and the measurement range is 0-10 tons; the positioning accuracy of the GPS positioning module is ±3 meters, and the real-time load data and location data of waste trucks are collected respectively.

[0030] Furthermore, upload the waste weight data, load data, and location data to the data processing server through a wireless transmission module; establish an urban electronic map library in the data processing server, and match the waste weight data with the locations of waste collection points in the electronic map library to generate a waste distribution heat map.

[0031] It should be noted that the wireless transmission module adopts 5G communication technology, and the data transmission delay is less than 100 ms; the electronic map library includes the road network topology structure and the distribution information of waste collection points; the waste distribution heat map marks the waste accumulation degree of different regions with gradient colors.

[0032] Even further, superimpose the load data and location data on the waste distribution heat map to form a waste distribution map including waste distribution and vehicle information.

[0033] S2: Based on the waste weight data in the waste distribution map, use an improved K-means clustering algorithm to divide the waste collection and transportation areas, and calculate the waste accumulation levels of each area.

[0034] Specifically, extract the spatial coordinates of the garbage collection points and the corresponding garbage weight data from the garbage distribution map, construct a feature vector matrix, and perform standardization processing on the feature vector matrix using the Z-score standardization method; introduce an improved K-means clustering algorithm to the standardized feature vector matrix, optimize the number of clustering clusters through the silhouette coefficient method, and calculate the distance between clusters by combining the Mahalanobis distance with road network constraints.

[0035] Preferably, the specific formula for the M×N feature vector matrix is as follows:

[0036]

[0037] where x i is the spatial abscissa of the i-th garbage collection point, y i is the spatial ordinate of the i-th garbage collection point, w i is the garbage weight of the i-th garbage collection point, v i is the garbage growth rate of the i-th garbage collection point, and t i is the nearest garbage collection time of the i-th garbage collection point.

[0038] It should be noted that the rows of the feature vector matrix represent the garbage collection points, that is, a specific garbage collection point in the city; each garbage collection point corresponds to a feature vector; the columns represent the spatial coordinates and garbage weight data of this garbage collection point, where the spatial coordinates are used to represent the geographical location of the garbage collection point in the city; the garbage weight data represents the current garbage weight of this garbage collection point.

[0039] Furthermore, based on the distance between clusters, divide the urban area into several garbage collection and transportation sub-areas, and at the same time divide the garbage accumulation levels within the garbage collection and transportation sub-areas.

[0040] It should be noted that the garbage collection and transportation sub-areas are assigned unique numbers; the garbage accumulation level is determined by the weighted average of the total garbage weight and the number of garbage collection points within the sub-area.

[0041] Even further, when the garbage growth rate of the garbage collection points in this area is less than the first threshold and the average garbage weight is less than the first preset average weight value, it is determined as a first-level accumulation; if there is a garbage accumulation in the adjacent area reaching the third-level accumulation or above, then reduce the garbage collection and transportation priority of this area and release the transportation capacity to support the high-accumulation areas; if the garbage growth rate in this area is always less than the first threshold in three consecutive monitoring periods, then merge it into the adjacent second-level accumulation to reduce scheduling redundancy.

[0042] Preferably, the scheduling rules for primary accumulation are as follows: empty-load supplementary collection and transportation: if the garbage truck returns empty due to route optimization, priority is given to arranging supplementary collection and transportation in this area; resource redistribution: if the garbage accumulation level in the adjacent area is relatively high, the garbage trucks in this area are scheduled to support, and dynamic adjustment is made in the garbage distribution map.

[0043] Specifically, when the garbage growth rate at the garbage collection points in this area is between the first threshold and the second threshold, and the average garbage weight is between the first preset average weight value and the second preset average weight value, it is determined as a secondary accumulation area; if there is garbage accumulation reaching level four or above in the adjacent area, and the garbage growth trend in this area is on the rise (for example, the growth rate exceeds the set ratio in the past six hours), it is automatically upgraded to level three accumulation, and the scheduling priority is adjusted; if the fluctuation range of the garbage accumulation at some garbage collection points in this area exceeds the set ratio within 24 hours, a dynamic collection and transportation task adjustment is triggered, and an adaptive scheduling strategy is adopted.

[0044] Preferably, the scheduling rules for secondary accumulation are as follows: intelligent task warning: if the growth rate at a certain garbage collection point in the area exceeds the set threshold for multiple consecutive cycles, an additional cleaning task is inserted in advance; route optimization: if the garbage growth rate in the adjacent area with level three or above accumulation is too fast, priority is given to adjusting some garbage trucks in this area to support, and the scheduling priority is dynamically adjusted according to historical data.

[0045] Furthermore, when the garbage growth rate at the garbage collection points in this area is between the second threshold and the third threshold, and the average garbage weight is between the second preset average weight value and the third preset average weight value, it is determined as level three accumulation; if the garbage accumulation situation in this area shows periodic fluctuations (for example, the ratio between the highest value and the lowest value of daily garbage accumulation exceeds the set range), it is determined as a key monitoring area, and the scheduling interval is adjusted; if the accumulation amount at a certain garbage collection point in this area exceeds the set threshold of level four accumulation in a short period of time, it is automatically set as a priority collection point, and an emergency scheduling is triggered.

[0046] Preferably, the scheduling rules for level three accumulation are as follows: dynamically adjust the collection and transportation frequency: in each scheduling cycle, predict the garbage accumulation situation in the next cycle according to historical data. If it is expected to exceed the set capacity percentage, an additional collection and transportation task is inserted in advance; load balancing: adopt an adaptive scheduling strategy. If there is still remaining garbage after the garbage truck is fully loaded, nearby garbage trucks with secondary accumulation are automatically called for support; dynamic route adjustment: if the garbage growth rate in this area has been continuously rising in the past multiple cycles and exceeds the set ratio, adjust the garbage truck route to give priority to covering high-accumulation points.

[0047] Further, when the garbage growth rate at the garbage collection points in this area is greater than the third threshold and the average garbage weight is equal to the third preset average weight value, it is determined as level-four accumulation; if the garbage accumulation time in this area exceeds the set maximum time limit and has not been cleared yet, a priority scheduling mechanism is triggered; if the accumulation amount at a certain garbage collection point in this area exceeds the percentage of the set maximum capacity in two consecutive monitoring cycles, it is automatically upgraded to level-five accumulation.

[0048] Preferably, the scheduling rules for level-four accumulation are as follows: increase the collection frequency: compared with the regular scheduling frequency, increase the collection frequency and call in the garbage trucks from adjacent level-two and level-three accumulations for support; emergency task allocation within the area: if a certain garbage collection point is about to reach the set proportion of the maximum capacity, insert a high-priority cleaning task; real-time data synchronization: if the accumulation level in this area continues to rise, notify the scheduling center for temporary adjustment and optimize task allocation.

[0049] Specifically, when the garbage growth rate at the garbage collection points in this area is between the third threshold and the fourth threshold and this state has lasted for more than the set duration, it is determined as level-five accumulation; if the garbage accumulation in this area has affected traffic, the environment or public safety (for example, the garbage has overflowed beyond the set distance from the collection point), an emergency response mechanism is triggered; if the garbage accumulation speed in this area has increased by more than the set proportion compared with the historical highest level, it is upgraded to an extreme situation response mode.

[0050] Preferably, the scheduling rules for level-five accumulation are as follows: trigger an emergency scheduling mechanism: call in multiple garbage trucks for combined collection and adjust the scheduling plan for the surrounding areas to ensure priority handling; adjust the path priority: dynamically adjust the scheduling path of the garbage trucks to bypass areas with low accumulation and go directly to level-five accumulation areas.

[0051] It should be noted that the first threshold is set based on the lowest change range of the garbage growth rate in combination with historical data to identify areas with low garbage accumulation and ensure reasonable resource allocation; the second threshold is based on the medium change range of the garbage growth rate and in combination with the fluctuation trend of the garbage weight to ensure dynamic scheduling of level-two accumulation areas; the third threshold is based on the high-growth interval of the garbage growth rate and in combination with periodic fluctuations to identify high-accumulation areas that need to be key monitored and optimize the collection frequency; the fourth threshold is based on the extremely high growth critical point of the garbage growth rate and in combination with the garbage accumulation duration to trigger an emergency scheduling mechanism to prevent excessive garbage accumulation from affecting the environment; the fifth threshold is based on the historical highest level of the garbage growth rate and in combination with factors such as public safety and traffic impact to trigger an extreme situation response mode to ensure priority cleaning.

[0052] Further, based on the result of the level division, different colors are used to mark the partition numbers and garbage accumulation levels on the garbage distribution map, and the intensity of garbage accumulation is reflected by the depth of the colors.

[0053] S3: Based on the garbage accumulation level and real-time load data, use the multi-objective genetic algorithm to calculate the shortest collection and transportation path for each area, and generate a garbage truck scheduling plan.

[0054] Specifically, combine the garbage accumulation level and real-time load data to construct a scheduling feature vector, where the scheduling feature vector includes the spatial location information of the garbage collection points, the garbage accumulation level information, and the real-time load information of the garbage truck; establish a chromosome coding rule based on the scheduling feature vector, where the chromosome coding length is equal to the number of garbage collection points to be served, and the gene position represents the access sequence number of the garbage collection points.

[0055] Furthermore, with the minimization of the total path length and the maximization of the garbage accumulation level as the optimization objectives, combine the real-time load data of the garbage truck to construct a two-objective fitness function.

[0056] It should be noted that the two-objective fitness function includes the path distance cost and the garbage accumulation level weighting coefficient.

[0057] Preferably, the specific formula of the two-objective fitness function is as follows:

[0058]

[0059] where d i,i+1 is the actual road distance from the i-th garbage collection point to the (i + 1)-th garbage collection point, C i is the path passing coefficient of the i-th garbage collection point to be served, L i is the accumulation level index value of the i-th garbage collection point to be served, W max is the maximum load of the vehicle, ω1 and ω2 are weight coefficients, and n is the total number of garbage collection points to be served.

[0060] Even further, based on the two-objective fitness function, use an improved genetic operator for population evolution. The improved genetic operator includes an adaptive crossover operator based on the garbage accumulation level and a dynamic mutation operator; at the same time, introduce an elite retention strategy and a tabu search mechanism during the population evolution process.

[0061] It should be noted that the adaptive crossover operator dynamically adjusts the crossover probability according to the garbage accumulation level, and the gene segments with high accumulation have a higher crossover probability; when a fifth-level accumulation occurs, the dynamic mutation operator is used to increase the mutation probability of the corresponding gene position to accelerate the optimization of the collection and transportation path.

[0062] Preferably, the elite retention strategy directly retains the individual with the first fitness to the next generation, and the retention quantity is positively correlated with the garbage accumulation level; the tabu search mechanism is to record the access path and temporarily lift the tabu restriction when high-level garbage accumulation appears to expand the search space.

[0063] Specifically, the Pareto optimal solution set is obtained through the non-dominated sorting method, and the solution with the first path compression ratio is selected as the garbage truck scheduling plan.

[0064] It should be noted that the Pareto optimal solution set includes multiple candidate solutions that satisfy the shortest path and the optimal garbage accumulation level.

[0065] Preferably, the garbage truck scheduling plan is converted into a garbage truck scheduling instruction sequence and sent to each garbage truck on-board terminal through a wireless transmission module, where the scheduling instruction sequence includes the access sequence number, the estimated arrival time, and the maximum load capacity of the garbage collection point.

[0066] Furthermore, the running track of the garbage truck is dynamically displayed on the garbage distribution map, and the garbage collection progress is updated according to the real-time load data.

[0067] It should be noted that when the garbage truck completes the cleaning task of the specified collection point, the garbage accumulation level and the garbage distribution map are automatically updated.

[0068] S4: Allocate garbage truck tasks according to the garbage truck scheduling plan, and perform collaborative scheduling on the garbage trucks in adjacent areas based on the location data.

[0069] Specifically, based on the garbage truck scheduling plan, the scheduling instruction sequence of the garbage collection point is extracted from the Pareto optimal solution set; the scheduling instruction sequence is associated with the location information of the garbage collection point on the garbage distribution map to construct a task allocation feature vector.

[0070] It should be noted that the task allocation feature vector includes the spatial coordinates of the garbage collection point, the garbage accumulation level, the estimated arrival time, the initial position coordinates of the garbage truck, and the remaining load capacity.

[0071] Furthermore, based on the task allocation feature vector, a collection and transportation path and a task list are generated for the garbage truck; based on the road network topology structure of the garbage distribution map, the real-time position data of the garbage trucks in adjacent areas is extracted to construct a cross-regional collaborative scheduling index.

[0072] Preferably, the task list includes the access sequence of the garbage collection point, the estimated stay time, the maximum load capacity of a single garbage collection point, and the total mileage of the garbage truck driving path; the cross-regional collaborative scheduling index includes the empty load rate of the garbage trucks between regions, the difference in garbage accumulation levels between regions, the optimal connectivity of the cross-regional path, and the remaining load capacity of the garbage truck.

[0073] Furthermore, when the garbage trucks in a certain area cannot completely handle the high accumulation situation, the available garbage trucks in adjacent areas are automatically identified and called for support according to the cross-regional collaborative scheduling index.

[0074] It should be noted that the support trigger conditions for calling available garbage trucks in adjacent areas for support include that the garbage accumulation level in the target area reaches level four or five, the remaining load capacity of the garbage trucks in the current area is insufficient, and there are empty or low-load garbage trucks in the adjacent area.

[0075] Specifically, for cross-regional garbage truck support, a collaborative scheduling instruction sequence is generated and sent to the relevant garbage truck on-board terminals through the wireless transmission module; at the same time, the running tracks of the garbage trucks under collaborative scheduling are updated in real time on the garbage distribution map, and the garbage collection progress is dynamically adjusted according to the real-time load data.

[0076] In summary, the present invention collects the garbage weight, the load and position information of garbage trucks at garbage collection points in real time, constructs a garbage distribution map, and provides data support for subsequent scheduling; divides the garbage collection and transportation areas based on the improved K-means clustering algorithm and combines the garbage accumulation level to achieve accurate area division and improve the rationality of the collection and transportation plan; optimizes the garbage truck scheduling plan using the multi-objective genetic algorithm, balances the garbage accumulation pressure while minimizing the collection and transportation path, and improves the transportation efficiency; through cross-regional collaborative scheduling, when the local garbage truck resources are insufficient, dynamically allocate available vehicles in adjacent areas to enhance the flexibility and emergency handling ability of the system; optimizes the scheduling plan through the elite retention strategy and the tabu search mechanism, and dynamically adjusts the garbage collection progress in combination with real-time data to achieve the intelligent, efficient and low-cost garbage collection and transportation.

[0077] Embodiment 2

[0078] This is the second embodiment of the present invention. This embodiment also provides an intelligent urban garbage treatment optimization scheduling system, including: a collection module, which is used to collect the garbage weight data of garbage collection points, and collect the real-time load data and position data of garbage trucks, and generate a garbage distribution map;

[0079] A division module, based on the garbage weight data in the garbage distribution map, divides the garbage collection and transportation areas using the improved K-means clustering algorithm, and calculates the garbage accumulation level of each area;

[0080] A generation module, based on the garbage accumulation level and the real-time load data, uses the multi-objective genetic algorithm to calculate the shortest collection and transportation path of each area, and generates a garbage truck scheduling plan;

[0081] A collaborative scheduling module, which is used to allocate garbage truck tasks according to the garbage truck scheduling plan, and perform collaborative scheduling on the garbage trucks in adjacent areas based on the position data.

[0082] It should be noted that the technical solution of the intelligent urban waste treatment optimization scheduling system belongs to the same concept as the technical solution of the above-mentioned intelligent urban waste treatment optimization scheduling method. For the details not described in detail in the technical solution of the intelligent urban waste treatment optimization scheduling system in this embodiment, reference can be made to the description of the technical solution of the above-mentioned intelligent urban waste treatment optimization scheduling method.

[0083] The above-mentioned each unit module can be embedded in the processor in the computer device in the form of hardware or be independent of it, or can be stored in the memory in the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to each above-mentioned module.

[0084] This embodiment also provides an electronic device, which includes a processor, a memory, a communication interface, a display screen and an input device 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 and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a carrier network, NFC (Near Field Communication) or other technologies. When the computer program is executed by the processor, it realizes a multi-task edge computing resource scheduling method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or can be a button, a trackball or a touchpad set on the shell of the computer device, or can also be an external keyboard, a touchpad or a mouse, etc.

[0085] This embodiment also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by the processor, it realizes the method proposed in the above-mentioned embodiment.

[0086] The storage medium proposed in this embodiment and the method proposed in the above-mentioned embodiment belong to the same inventive concept. For the technical details not described in detail in this embodiment, reference can be made to the above-mentioned embodiment, and this embodiment has the same beneficial effects as the above-mentioned embodiment.

[0087] From the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software and necessary general-purpose hardware. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disc of a computer, etc., and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the method of the embodiments of the present invention.

[0088] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

[0089] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application can be implemented in various computer languages.

[0090] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0091] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to work in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one or more processes and / or blocks Figure 1 in the process or processes and / or blocks Figure 1 specified in the block or blocks or multiple blocks.

[0092] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more processes and / or blocks Figure 1 in the process or processes and / or blocks Figure 1 specified in the block or blocks or multiple blocks.

[0093] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn of the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present application.

[0094] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. An intelligent optimization scheduling method for urban waste treatment, characterized in that: Including, Collecting the garbage weight data of garbage collection points, and collecting the real-time load data and location data of garbage trucks to generate a garbage distribution map; Based on the garbage weight data in the garbage distribution map, using an improved K-means clustering algorithm to divide the garbage collection and transportation areas, and calculating the garbage accumulation levels of each area; Based on the garbage accumulation levels and the real-time load data, using a multi-objective genetic algorithm to calculate the shortest collection and transportation paths for each area, and generating a garbage truck scheduling plan; Allocating garbage truck tasks according to the garbage truck scheduling plan, and performing cooperative scheduling on the garbage trucks in adjacent areas based on the location data.

2. The intelligent urban waste treatment optimization scheduling method according to claim 1, wherein: Allocating garbage truck tasks according to the garbage truck scheduling plan, and performing cooperative scheduling on the garbage trucks in adjacent areas based on the location data, including: Based on the garbage truck scheduling plan, extracting the scheduling instruction sequence of garbage collection points from the Pareto optimal solution set; Associating the scheduling instruction sequence with the location information of garbage collection points in the garbage distribution map to construct a task allocation feature vector; Based on the task allocation feature vector, generating a collection and transportation path and a task list for the garbage truck; Based on the road network topology structure of the garbage distribution map, extracting the real-time location data of garbage trucks in adjacent areas, and constructing a cross-regional cooperative scheduling index; When the garbage truck in a certain area cannot completely handle the high accumulation situation, then according to the cross-regional cooperative scheduling index, automatically identify and call the available garbage trucks in adjacent areas for support; For cross-regional garbage truck support, generating a cooperative scheduling instruction sequence, and sending it to the relevant garbage truck on-board terminals through a wireless transmission module; At the same time, the running tracks of the garbage trucks under cooperative scheduling are updated in real time on the garbage distribution map, and the garbage collection progress is dynamically adjusted according to the real-time load data.

3. The intelligent urban waste treatment optimization scheduling method according to claim 2, characterized in that: The method for generating the garbage truck scheduling plan is Combining the garbage accumulation level and the real-time load data to construct a scheduling feature vector, where the scheduling feature vector includes the spatial location information of garbage collection points, the garbage accumulation level information, and the real-time load information of garbage trucks; Based on the scheduling feature vector, establishing a chromosome encoding rule, where the chromosome encoding length is equal to the number of garbage collection points to be served, and the gene position represents the access sequence number of the garbage collection points; Taking the minimization of the total path length and the maximization of the garbage accumulation level as optimization objectives, and constructing a two-objective fitness function in combination with the real-time load data of garbage trucks; Based on the two-objective fitness function, using an improved genetic operator for population evolution, where the improved genetic operator includes an adaptive crossover operator based on the garbage accumulation level and a dynamic mutation operator; At the same time, introducing an elite retention strategy and a tabu search mechanism during the population evolution process; Obtaining the Pareto optimal solution set through non-dominated sorting, and selecting the solution with the first path compression ratio as the garbage truck scheduling plan; Converting the garbage truck scheduling plan into a garbage truck scheduling instruction sequence, and sending it to each garbage truck on-board terminal through a wireless transmission module, where the scheduling instruction sequence includes the access sequence number of garbage collection points, the estimated arrival time, and the maximum loading capacity; At the same time, the running tracks of the garbage trucks are dynamically displayed on the garbage distribution map, and the garbage collection progress is updated according to the real-time load data.

4. The intelligent urban waste treatment optimization scheduling method according to claim 3, wherein: The elite retention strategy directly retains the individuals with the first fitness to the next generation, and the retention quantity is positively correlated with the garbage accumulation level; the tabu search mechanism records the access paths and temporarily lifts the tabu restrictions when high-level garbage accumulation occurs to expand the search space.

5. The intelligent urban waste treatment optimization scheduling method according to claim 4, characterized in that: Based on the garbage weight data in the garbage distribution map, an improved K-means clustering algorithm is used to divide the garbage collection and transportation areas, and the garbage accumulation levels of each area are calculated, including: Extract the spatial coordinates of the garbage collection points and the corresponding garbage weight data from the garbage distribution map, construct a feature vector matrix, and perform standardization processing on the feature vector matrix using the Z-score standardization method; Introduce an improved K-means clustering algorithm to the standardized feature vector matrix, optimize the number of clustering clusters by the silhouette coefficient method, and calculate the distance between clusters in combination with the Mahalanobis distance with road network constraints; Based on the distance between clusters, divide the urban area into several garbage collection and transportation sub-areas, and at the same time divide the garbage accumulation levels within the garbage collection and transportation sub-areas; Based on the result of the level division, use differential colors to mark the sub-area numbers and garbage accumulation levels in the garbage distribution map, and reflect the garbage accumulation intensity through the depth of the colors.

6. The intelligent urban waste treatment optimization scheduling method according to claim 5, characterized in that: The method for dividing the garbage accumulation level is as follows: When the garbage growth rate of the garbage collection points in this area is less than the first threshold and the average garbage weight is less than the first preset average weight value, it is determined as the first-level accumulation; When the garbage growth rate of the garbage collection points in this area is between the first threshold and the second threshold, and the average garbage weight is between the first preset average weight value and the second preset average weight value, it is determined as the second-level accumulation; When the garbage growth rate of the garbage collection points in this area is between the second threshold and the third threshold, and the average garbage weight is between the second preset average weight value and the third preset average weight value, it is determined as the third-level accumulation; When the garbage growth rate of the garbage collection points in this area is greater than the third threshold and the average garbage weight is equal to the third preset average weight value, it is determined as the fourth-level accumulation; When the garbage growth rate of the garbage collection points in this area is between the third threshold and the fourth threshold and this state has lasted for more than the set duration, it is determined as the fifth-level accumulation.

7. The intelligent urban waste treatment optimization scheduling method according to claim 5, characterized in that: The method for generating the garbage distribution map is as follows: Install weight sensors at each garbage collection point in the city, and at the same time install load sensors and GPS positioning modules on the garbage trucks; Upload the garbage weight data, the load data, and the position data to the data processing server through a wireless transmission module; Establish an urban electronic map library in the data processing server, and match the garbage weight data with the positions of the garbage collection points in the electronic map library to generate a garbage distribution heat map; Overlay the load data and position data on the garbage distribution heat map to form a garbage distribution map including garbage distribution and vehicle information.

8. An intelligent urban waste treatment optimization scheduling system, based on the intelligent urban waste treatment optimization scheduling method according to any one of claims 1 to 7, characterized in that: Including: An acquisition module for acquiring the garbage weight data of the garbage collection points, and acquiring the real-time load data and position data of the garbage trucks to generate a garbage distribution map; A partitioning module that, based on the garbage weight data in the garbage distribution map, uses an improved K-means clustering algorithm to partition garbage collection and transportation areas and calculates the garbage accumulation levels of each area; A generation module that, based on the garbage accumulation levels and the real-time load data, uses a multi-objective genetic algorithm to calculate the shortest collection and transportation paths for each area and generates a garbage truck scheduling plan; A collaborative scheduling module that is used to allocate garbage truck tasks according to the garbage truck scheduling plan and perform collaborative scheduling on garbage trucks in adjacent areas based on the location data.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the intelligent urban garbage treatment and optimization scheduling method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the intelligent urban garbage treatment and optimization scheduling method according to any one of claims 1 to 7.

Images