Intelligent city resource scheduling method

Abstract

The invention belongs to the technical field of smart cities, and particularly relates to a smart city resource scheduling method. Comprising the steps of monitoring various resource states and demands of a city in real time, establishing a scheduling model which comprehensively considers resource availability, demand emergency degree, fairness and efficiency, solving an optimal allocation scheme through an improved particle swarm optimization algorithm, and executing and adjusting the scheme. The method can comprehensively and accurately monitor resources, is scientific in scheduling, improves the resource utilization efficiency, adapts to dynamic changes, and improves the overall benefits of a city. Specifically, accurate scheduling can be carried out according to monitoring data of different resources such as traffic and energy, and waste is reduced; a multi-factor model is integrated, so that resource allocation is more reasonable; the optimization algorithm can quickly find an optimal scheme; optimal resource allocation is ensured through dynamic adjustment; therefore, the urban operation efficiency and the sustainable development capability are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of smart cities, and in particular relates to a smart city resource scheduling method. Background Art

[0002] With the acceleration of urbanization and the continuous advancement of science and technology, the construction of smart cities has become an important trend in the development of today's society. In smart cities, the reasonable scheduling and allocation of various resources is crucial to improving the operating efficiency of the city, ensuring the quality of life of residents and promoting the sustainable development of the city. However, there are some problems with the current urban resource scheduling methods. In terms of traffic resources, traditional traffic management methods often find it difficult to accurately grasp traffic flow and congestion in real time, resulting in unreasonable allocation of traffic resources and increasingly serious traffic congestion problems. In terms of energy resources, it is difficult to achieve a dynamic balance between energy supply and demand, and energy shortages or waste are prone to occur. In terms of water resources, the uneven distribution and waste of water resources are relatively common, and there is a lack of effective means of water resource scheduling. In terms of public service resources, there is a large gap between the demand and supply of public services, which makes it difficult to meet the diverse needs of residents. Summary of the invention

[0003] In response to the above-mentioned technical problems existing in urban resource scheduling, the present invention proposes a method that utilizes advanced sensor technology, data acquisition and processing technology, and optimization algorithm to achieve real-time monitoring and dynamic scheduling of various resources in the city, improve resource utilization efficiency, and ensure the normal operation and sustainable development of the city.

[0004] In order to achieve the above object, the technical solution adopted by the present invention comprises the following steps:

[0005] S1. First, comprehensively monitor the usage status and demand of various resources in the city in real time. For traffic resources, sensors and cameras installed on the road are used to collect traffic flow data in real time. t , vehicle speed data V t and road congestion index C t ; For energy resources, with the help of smart meters and sensors, the energy consumption rate E is monitored in real time c and supply rate E s ; For public service resources, the demand for public service resources N is counted in real time through citizen feedback and service agency data channels d and the number of services currently available N a ;

[0006] S2. Secondly, a resource scheduling model is established based on the monitoring data. The model comprehensively considers the availability of resources, the urgency of demand, the fairness and efficiency of resource allocation. Assuming the resource availability coefficient is A, the urgency of demand coefficient is U, the fairness coefficient is F, and the efficiency coefficient is E, the total objective function is Z = α × A + β × U + γ × F + δ × E, where α, β, γ, δ are the weight values ​​of each coefficient, and α + β + γ + δ = 1;

[0007] S3, then solve the resource scheduling model through the improved particle swarm optimization algorithm to determine the optimal resource allocation plan, and find the resource allocation plan that makes the objective function optimal through continuous iterative optimization;

[0008] S4. Finally, the resource allocation plan is executed, and the resource allocation effect is monitored in real time. The resource scheduling model and allocation plan are adjusted and optimized according to the feedback information.

[0009] Preferably, establishing the resource scheduling model in step S2 specifically includes the following contents:

[0010] S21. First, determine the calculation method of resource availability coefficient A. For traffic resources, A can be determined by the ratio of road capacity to actual traffic flow. Among them C 理论通行能力 is the theoretical maximum capacity of the road, ρ is the vehicle density coefficient; for energy resources Where ε is the energy reserve safety factor; for public service resources Where λ is the public service resource buffer coefficient;

[0011] S22. Secondly, the measurement standard of the demand urgency coefficient U is clarified, and different urgency levels are set according to different resource types and actual conditions. For traffic resources, when the road congestion index exceeds a certain threshold, the demand urgency is high; for energy resources, when the energy supply is insufficient and is about to affect the operation of important facilities, the demand urgency is high; for public service resources, when it involves emergency medical and safety needs, the demand urgency is high; the demand urgency coefficient U∈[0,1] can be quantified by setting a numerical range, and the higher the value, the higher the demand urgency;

[0012] S23, then define the calculation method of the fairness coefficient F. For traffic resources, fairness can take into account the differences in traffic accessibility in different regions. Where n is the number of regions, T i is the average commuting time in area i, T max is the maximum average commuting time in all regions. The fairness of energy resources can be reflected in the difference in energy supply stability among different users. Where m is the number of users, E var,jis the energy volatility of user j; for the fairness of public service resources, the differences in the availability of public services for different groups can be considered Where q is the number of groups, S var,l is the volatility of public service resource availability for group l;

[0013] S24. Finally, the calculation of the efficiency coefficient E is explained. The efficiency of traffic resources can be measured by the ratio of traffic flow to road capacity and the average speed of vehicles. Where V 标准 is the standard vehicle speed; energy resource efficiency is determined by the ratio of energy output to input Where ω is the energy output efficiency coefficient, ξ is the energy input cost coefficient; the efficiency of public service resources is measured by the response time and service quality of public services. Where T 响应 is the public service response time, S 质量 Score the quality of public services.

[0014] Preferably, the step S3 solves the resource scheduling model by improving the particle swarm algorithm to determine the optimal resource allocation scheme as follows:

[0015] S31. First, the improved particle swarm algorithm is used to solve the problem. A group of particles is initialized. Each particle represents a possible resource allocation scheme. The particle position vector X i =(x i1 ,x i2 ,...,x in ), where n is the number of resource types, x ij represents the allocation value of the i-th particle on the j-th resource, and the particle's velocity vector V i =(v i1 ,v i2 ,...,v in ) is used to control the update of particles;

[0016] S32, then define the fitness function, and take the total objective function Z=α×A+β×U+γ×F+δ×E of the resource scheduling model as the fitness function;

[0017] S33, followed by particle position and velocity update, in each iteration, the particle velocity and position are updated according to the following formula Where t is the current iteration number, ω is the inertia weight, c1, c2 are learning factors, r1, r2 are random numbers in the interval [0, 1], pbest ij is the value of the individual optimal position of the ith particle in the jth dimension, gbest ij is the value of the global optimal position of the entire particle swarm in the jth dimension;

[0018] S34, then introduce a dynamic adjustment strategy, dynamically adjust the inertia weight ω, learning factors c1, c2 as the number of iterations increases, to improve the algorithm's search ability and convergence speed, and use a linear decreasing method to adjust the inertia weight where ω max ,ω min are the maximum and minimum values ​​of the inertia weight, t is the current iteration number, T max is the maximum number of iterations;

[0019] S35. Finally, determine the termination condition of the algorithm. The algorithm terminates when one of the following conditions is met: the maximum number of iterations is reached; the fitness value change of the particle swarm is less than a certain threshold; a resource allocation scheme that meets specific requirements is found, and the final global optimal position is the optimal resource allocation scheme.

[0020] Preferably, the operation of adjusting and optimizing the resource scheduling model and allocation plan according to the feedback information in step S4 is to send the resource allocation plan to the relevant resource management departments and service agencies, which are responsible for the specific implementation. At the same time, an evaluation index system for the resource allocation effect is established, such as the timeliness and satisfaction of resource allocation. By real-time monitoring of these indicators, problems in resource allocation can be discovered in time, and weight values ​​and optimization algorithm parameters can be adjusted according to the feedback information to continuously improve the resource scheduling model and allocation plan.

[0021] Compared with the prior art, the advantages and positive effects of the present invention are: real-time and comprehensive monitoring of various resources, more accurate data, providing a reliable basis for resource scheduling, and avoiding unreasonable allocation. The improved particle swarm algorithm is used to quickly find the optimal allocation plan, adapt to dynamic changes, and improve scheduling accuracy and efficiency. DETAILED DESCRIPTION

[0022] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described below in conjunction with embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0023] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways than those described herein. Therefore, the present invention is not limited to the specific embodiments of the following disclosure.

[0024] Embodiment,In the rapidly developing smart cities, problems such as traffic congestion, imbalance in energy supply and demand, uneven distribution of water resources, and unreasonable allocation of public service resources are becoming increasingly prominent, and a smart city resource scheduling method is urgently needed to improve the current situation.

[0025] Taking the dispatch of energy resources as an example, the first step is real-time monitoring. Smart meters and sensors are installed in commercial areas, industrial areas, and residential areas to collect the energy consumption rate of each area in real time. For example, the commercial area records the power consumption of large shopping malls, office buildings, etc. once an hour; the industrial area continuously monitors the energy consumption of factory equipment; and the residential area counts household electricity consumption in real time. At the same time, the status of the energy supply side is monitored, such as the output power of the power station and the load of the power grid.

[0026] In order to improve the overall efficiency of energy utilization, a resource scheduling model is established to allocate excess energy to the peak demand area or period when energy demand is low according to the energy consumption monitoring data of different regions in energy resource scheduling. Calculate the resource availability coefficient A, and the current total energy supply rate is E s = 2000 kWh / h. The energy consumption of the commercial area is E c1 = 600 kWh / h, industrial area is E c2 =900 kWh / h, E for residential areas c3 =500 kWh / h, energy reserve safety factor ε = 150, then the resource availability coefficient When the difference between the energy supply rate and the consumption rate is less than a certain threshold, the demand urgency increases. If the difference is less than 150 kWh / h, the demand urgency coefficient is set to 0.7. The current difference is 0, so the demand urgency coefficient U = 0.7; by counting the fluctuations in electricity consumption in each area over a period of time, the energy supply fluctuation rate E of the commercial area is calculated. var,1 =0.12, energy supply volatility E in industrial areas var,2 =0.18, energy supply volatility E in residential areas var,3 =0.1, then the fairness coefficient Next, we will explain the efficiency coefficient E. The energy output efficiency coefficient ω=0.85, and the energy input cost coefficient ξ=100. Then the efficiency coefficient Finally, an initial value of the weight is given as α=0.3, β=0.3, γ=0.2, δ=0.2, then the total objective function Z=α×A+β×U+γ×F+δ×E, where α, β, γ, δ are the weight values ​​of each coefficient.

[0027] Next, in order to achieve the optimal resource allocation plan, the present invention uses an improved particle swarm optimization algorithm to solve the resource scheduling model to determine the optimal resource allocation plan. Through continuous iterative optimization, the resource allocation plan that makes the objective function optimal is found. The improved particle swarm algorithm is used for solving. Initialize a group of particles, each particle represents a possible energy allocation plan, and the particle position vector can be expressed as X i =(x i1 ,x i2 ,x i3), where x i1 represents the energy distribution in the commercial area, x i2 Represents the energy distribution of the industrial area x i3 Represents the energy distribution in the residential area, the particle velocity vector V i =(v i1 ,v i2 ,...,v in ) is used to control the update of particles; then the total objective function of the resource scheduling model Z = α × A + β × U + γ × F + δ × E is used as the fitness function to evaluate the quality of the solution represented by the particle; followed by the particle position and speed update. In each iteration, the particle speed and position are updated according to the following formula Where t is the current iteration number, ω is the inertia weight, c1, c2 are learning factors, r1, r2 are random numbers in the interval [0, 1], pbest ij is the value of the individual optimal position of the ith particle in the jth dimension, gbest ij is the value of the global optimal position of the entire particle swarm in the jth dimension; then a dynamic adjustment strategy is introduced to dynamically adjust the inertia weight ω and learning factors c1, c2 as the number of iterations increases to improve the algorithm's search ability and convergence speed, and the inertia weight is adjusted in a linear decreasing manner where ω max ,ω min are the maximum and minimum values ​​of the inertia weight, t is the current iteration number, T max is the maximum number of iterations; finally, the algorithm termination condition is determined. When the maximum number of iterations is reached, a resource allocation solution that meets specific requirements is found.

[0028] After optimization, the following optimal energy allocation scheme is predicted: The energy allocation for commercial areas is 550 kWh / h. Commercial areas usually have a large energy demand during daytime working hours. This allocation can meet the electricity demand for lighting, air conditioning, electronic equipment, etc. in commercial places such as shopping malls and office buildings. At the same time, commercial areas are encouraged to adopt energy-saving equipment and intelligent energy management systems to further improve energy utilization efficiency. The energy allocation for industrial areas is 850 kWh / h. The operation of factory equipment, production and processing in industrial areas require a lot of energy. This allocation not only ensures the normal production of the factory, but also promotes the energy optimization and upgrading of industrial areas, such as the use of efficient motors and energy-saving production processes to reduce energy consumption. The energy allocation for residential areas is 600 kWh / h. The energy in residential areas is mainly used for home lighting, home appliance use, heating, etc. A reasonable allocation can guarantee the daily life needs of residents, and at the same time promote smart home systems so that residents can better manage home energy use and achieve energy saving and consumption reduction.

[0029] Finally, the optimal energy allocation plan is sent to the power management department, who is responsible for adjusting the output power of the substation to achieve reasonable power supply in different areas; real-time monitoring of energy allocation effects, such as observing voltage stability in each area, user satisfaction, etc. Based on feedback information, the resource scheduling model and algorithm parameters are dynamically adjusted to continuously optimize the energy allocation plan.

[0030] The above description is only a preferred embodiment of the present invention and does not limit the present invention in other forms. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A smart city resource scheduling method, characterized in that: The following steps are involved: S1. First, comprehensively monitor the usage status and demand of various resources in the city in real time. For traffic resources, sensors and cameras installed on the road are used to collect traffic flow data in real time. t , vehicle speed data V t and road congestion index C t ; For energy resources, with the help of smart meters and sensors, the energy consumption rate E is monitored in real time c and supply rate E s ; For public service resources, the demand for public service resources N is counted in real time through citizen feedback and service agency data channels d and the number of services currently available N a ; S2. Secondly, a resource scheduling model is established based on the monitoring data. The model comprehensively considers the availability of resources, the urgency of demand, the fairness and efficiency of resource allocation. Assuming the resource availability coefficient is A, the urgency of demand coefficient is U, the fairness coefficient is F, and the efficiency coefficient is E, the total objective function is Z = α × A + β × U + γ × F + δ × E, where α, β, γ, δ are the weight values ​​of each coefficient, and α + β + γ + δ = 1; S3, then solve the resource scheduling model through the improved particle swarm optimization algorithm to determine the optimal resource allocation plan, and find the resource allocation plan that makes the objective function optimal through continuous iterative optimization; S4. Finally, the resource allocation plan is executed, and the resource allocation effect is monitored in real time. The resource scheduling model and allocation plan are adjusted and optimized according to the feedback information.

2. A smart city resource scheduling method according to claim 1, characterized in that: The establishment of the resource scheduling model in step S2 specifically includes the following contents: S21. First, determine the calculation method of resource availability coefficient A. For traffic resources, A can be determined by the ratio of road capacity to actual traffic flow. Among them C 理论通行能力 is the theoretical maximum capacity of the road, ρ is the vehicle density coefficient; for energy resources Where ε is the energy reserve safety factor; for public service resources Where λ is the public service resource buffer coefficient; S22. Secondly, the measurement standard of the demand urgency coefficient U is clarified, and different urgency levels are set according to different resource types and actual conditions. For traffic resources, when the road congestion index exceeds a certain threshold, the demand urgency is high; for energy resources, when the energy supply is insufficient and is about to affect the operation of important facilities, the demand urgency is high; For public service resources, when it comes to urgent medical and safety needs, the urgency of the demand is high; The demand urgency coefficient U∈[0,1] can be quantified by setting a numerical interval, where a higher value indicates a higher demand urgency; S23, then define the calculation method of the fairness coefficient F. For traffic resources, fairness can take into account the differences in traffic accessibility in different regions. Where n is the number of regions, T i is the average commuting time in area i, T max is the maximum average commuting time in all regions. The fairness of energy resources can be reflected in the difference in energy supply stability among different users. Where m is the number of users, E var,j is the energy volatility of user j; for the fairness of public service resources, the differences in the availability of public services for different groups can be considered Where q is the number of groups, S var,l is the volatility of public service resource availability for group l; S24. Finally, the calculation of the efficiency coefficient E is explained. The efficiency of traffic resources can be measured by the ratio of traffic flow to road capacity and the average speed of vehicles. Where V 标准 is the standard vehicle speed; energy resource efficiency is determined by the ratio of energy output to input Where ω is the energy output efficiency coefficient, ξ is the energy input cost coefficient; The efficiency of public service resources is measured by the response time and service quality of public services. Where T 响应 is the public service response time, S 质量 Score the quality of public services.

3. A smart city resource scheduling method according to claim 1, characterized in that: The step S3 solves the resource scheduling model by improving the particle swarm algorithm to determine the optimal resource allocation solution as follows: S31. First, the improved particle swarm algorithm is used to solve the problem. A group of particles is initialized. Each particle represents a possible resource allocation scheme. The particle position vector X i =(x i1 ,x i2 ,...,x in ), where n is the number of resource types, x ij represents the allocation value of the i-th particle on the j-th resource, and the particle's velocity vector V i =(v i1 ,v i2 ,...,v in ) is used to control the update of particles; S32, then define the fitness function, and take the total objective function Z=α×A+β×U+γ×F+δ×E of the resource scheduling model as the fitness function; S33, followed by particle position and velocity update, in each iteration, the particle velocity and position are updated according to the following formula Where t is the current iteration number, ω is the inertia weight, c1, c2 are learning factors, r1, r2 are random numbers in the interval [0, 1], pbest ij is the value of the individual optimal position of the ith particle in the jth dimension, gbest ij is the value of the global optimal position of the entire particle swarm in the jth dimension; S34, then introduce a dynamic adjustment strategy, dynamically adjust the inertia weight ω, learning factors c1, c2 as the number of iterations increases, to improve the algorithm's search ability and convergence speed, and use a linear decreasing method to adjust the inertia weight where ω max ,ω min are the maximum and minimum values ​​of the inertia weight, t is the current iteration number, T max is the maximum number of iterations; S35. Finally, determine the termination condition of the algorithm. The algorithm terminates when one of the following conditions is met: the maximum number of iterations is reached; the fitness value change of the particle swarm is less than a certain threshold; a resource allocation scheme that meets specific requirements is found, and the final global optimal position is the optimal resource allocation scheme.

4. A smart city resource scheduling method according to claim 1, characterized in that: The operation of adjusting and optimizing the resource scheduling model and allocation plan according to the feedback information in step S4 is to send the resource allocation plan to the relevant resource management departments and service agencies, which are responsible for the specific implementation. At the same time, an evaluation index system for the resource allocation effect is established, such as the timeliness and satisfaction of resource allocation. By real-time monitoring of these indicators, problems in resource allocation can be discovered in time, and weight values ​​and optimization algorithm parameters can be adjusted according to the feedback information to continuously improve the resource scheduling model and allocation plan.

Images