Photovoltaic power generation control and real-time energy dispatching system along urban highways

Abstract

The present invention discloses a photovoltaic power generation control and real-time energy dispatching system along an urban highway, which relates to the technical field of distributed energy management, and includes an agent construction module, an energy management module, a collaborative adjustment module, and a control dispatching module. The present invention constructs photovoltaic units, load units, and energy storage units along the urban highway through an autonomous agent model, monitors power generation capacity data, power demand data, and energy storage power data in real time, and adopts the MQTT message transmission protocol for data sharing, defines ecological relationships and flow paths, optimizes energy distribution using a genetic algorithm, measures the level of cooperation between agents through pheromones, distributes initial pheromone concentrations and simulates their volatilization effects, adjusts the power generation priority of photovoltaic units according to pheromone concentrations, optimizes the supply of loads and energy storage units, realizes automation and intelligent dispatching of the system, can continuously optimize energy allocation strategies according to real-time data, and enhances intelligent decision-making capabilities.

Description

Technical Field

[0001] The present invention relates to the technical field of distributed energy management, and in particular to a photovoltaic power generation control and real-time energy dispatching system along urban highways. Background Art

[0002] Urbanization has led to a sharp increase in electricity demand, especially in urban areas, where various industries, businesses and daily life are increasingly dependent on electricity. At the same time, environmental issues such as climate change and air pollution are becoming increasingly prominent, prompting the search for more sustainable and environmentally friendly energy solutions. Photovoltaic power generation, as a clean and renewable energy source, can not only effectively supplement the city's electricity demand, but also directly utilize the space along urban roads to convert natural resources into usable energy, thereby improving the city's energy security and environmental quality.

[0003] The existing technology has the following deficiencies: the existing energy management often relies on static scheduling algorithms and centralized control, which makes it difficult to quickly respond to changes in electricity demand and fluctuations in photovoltaic power generation, resulting in insufficient or wasteful electricity supply, affecting the overall efficiency of the system; traditional scheduling methods often fail to fully consider the characteristics of renewable energy, resulting in the potential of photovoltaic power generation not being fully tapped, and it is easy for the power generation capacity to not match the actual demand, resulting in energy waste, and unable to make effective adjustments and optimizations according to the actual situation, resulting in uncoordinated system operation; traditional energy management has the problem of insufficient data sharing, resulting in poor information transmission between units, affecting the timeliness and accuracy of decision-making.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide a photovoltaic power generation control and real-time energy dispatching system along urban highways to solve the problems in the above-mentioned background technology.

[0006] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a photovoltaic power generation control and real-time energy dispatching system along an urban highway, comprising an agent construction module, an energy management module, a collaborative adjustment module and a control dispatching module;

[0007] Agent building module: PV units, load units and energy storage units along urban roads are defined as autonomous agent models to monitor power generation capacity data, power demand data and energy storage power data in real time, and share data in a publish / subscribe mode through the MQTT message transmission protocol;

[0008] Energy management module: defines ecological relationships, flow paths and dynamic action relationships, builds an adaptive scheduling framework, and manages energy flows between autonomous agents of photovoltaic units, autonomous agents of load units and autonomous agents of energy storage units by randomly generating initial solution individuals and applying genetic algorithms to optimize energy division;

[0009] Collaboration regulation module: defines pheromones to measure the collaboration level among the autonomous agents of the photovoltaic unit, the load unit, and the energy storage unit, assigns the same initial pheromone concentration value, and defines a volatilization mechanism to simulate the volatilization effect of pheromones;

[0010] Control and dispatch module: adjust the power generation priority of the photovoltaic unit autonomous agent according to the pheromone concentration, and adjust the supply of the load unit autonomous agent and the energy storage unit autonomous agent.

[0011] Preferably, the photovoltaic units, load units and energy storage units along the urban roads are defined as autonomous agent models. The photovoltaic unit autonomous agent monitors the photovoltaic power generation capacity data in real time through light sensors. The load unit autonomous agent monitors the load power demand data in real time according to the actual power usage. The energy storage unit autonomous agent monitors the energy storage capacity data of the energy storage battery in real time. The MQTT message transmission protocol adopts a publish / subscribe mode, and the photovoltaic unit autonomous agent, the load unit autonomous agent and the energy storage unit autonomous agent send data through topics, and use topic subscription to receive data, so as to realize data sharing among the photovoltaic unit autonomous agent, the load unit autonomous agent and the energy storage unit autonomous agent.

[0012] Preferably, by defining the ecological relationship, flow path and dynamic action relationship between the photovoltaic unit autonomous agent, the load unit autonomous agent and the energy storage unit autonomous agent, an adaptive scheduling framework based on the Lotka-Volterra equation is constructed, and by randomly generating initial solution individuals and applying genetic algorithms to optimize energy division, efficient management of energy flow between photovoltaic, load and energy storage is achieved. The specific steps are:

[0013] S1. Define the boundaries of the agent relationship ecological model as the agent scope of the PV unit autonomous agent, the load unit autonomous agent, and the energy storage unit autonomous agent.

[0014] S2. Define the flow path of the ecological model as the process of data sharing among the autonomous agents of the photovoltaic unit, the load unit and the energy storage unit. Set the data transfer efficiency between different agents according to the transfer rules of ecological energy. Set the autonomous agent of the photovoltaic unit as the "prey", the autonomous agent of the load unit and the autonomous agent of the energy storage unit as the "predator". Use the Lotka-Volterra equation to describe the dynamic relationship between the autonomous agents. The specific formula is:

[0015]

[0016] in, Indicates power generation capacity data, represents the growth rate of power generation of the PV unit autonomous agent, represents the interaction coefficient between power generation capacity data and power demand data, represents the decay rate of the PV unit autonomous agent, L represents the power demand data, Indicates the influence coefficient of power generation capacity data on power demand data, represents the natural decay rate of electricity demand data, represents the conversion rate of electricity stored in the autonomous agent of the load unit, Indicates the energy storage capacity data. represents the efficiency provided by the PV unit autonomous agent to the energy storage unit autonomous agent, It represents the energy efficiency released by the energy storage unit autonomous agent to meet the energy consumption of the load unit autonomous agent. represents the decay rate of the energy storage unit autonomous agent, It represents the change process time of the PV unit autonomous agent, load unit autonomous agent and energy storage unit autonomous agent, and defines , , The solution is the energy balance point, which determines the dynamic equilibrium state between the autonomous agent of the photovoltaic unit, the autonomous agent of the load unit and the autonomous agent of the energy storage unit.

[0017] S3. Establish an optimal energy partitioning framework to simulate ecological energy allocation. Randomly generate initial solution individuals based on the power generation capacity data, power demand data and energy storage data according to the dynamic equilibrium state. Set a custom fitness function to calculate the fitness value of the optimal energy. Select the initial solution individuals with high fitness values. Use single-point crossover to use the energy balance point as the crossover point and perform cutting. Exchange the genes at the corresponding positions. Repeat iterations to generate offspring individuals with optimal energy partitioning. Calculate the fitness value cyclically. Define the fitness threshold as 0.05. Select offspring individuals with fitness values ​​lower than the fitness threshold for optimal energy allocation.

[0018] Preferably, pheromones are defined to measure the level of cooperation among the autonomous agents of the photovoltaic unit, the autonomous agents of the load unit, and the autonomous agents of the energy storage unit, and the same initial pheromone concentration value is assigned. A volatilization mechanism is defined to simulate the volatilization effect of pheromones. When the autonomous agent completes power generation or energy regulation once, the pheromone concentration is increased according to the degree of satisfying the autonomous agent of the load unit. The specific increase and update formula is:

[0019]

[0020] in, represents the pheromone concentration of autonomous agent i at time T, represents the pheromone concentration of autonomous agent i at time T-1, It represents the adjustment coefficient for controlling the incremental strength of pheromone. represents the actual energy generated by the agent during the period from T to T-1, It indicates the degree to which agent i meets the load demand.

[0021] Preferably, the power generation priority of the photovoltaic unit autonomous agent is adjusted according to the pheromone concentration, and the specific formula is:

[0022]

[0023] in, represents the power generation priority of the PV unit autonomous agent i, represents the weight coefficient of pheromone concentration, Represents the weight coefficient of the current load unit autonomous agent demand energy, It represents the current load demand energy of the PV unit autonomous agent i. According to the pheromone concentration and the power generation priority of the PV unit autonomous agent, the load unit autonomous agent and the energy storage unit autonomous agent supply are adjusted. The specific formula is:

[0024]

[0025] in, represents the energy provided by the PV unit autonomous agent e to the load unit autonomous agent or the energy storage unit autonomous agent f, represents the sum of pheromone concentrations of all autonomous agents at time T, represents the total load demand energy of the load unit autonomous agent and the energy storage unit autonomous agent j.

[0026] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0027] 1. Through the construction of an autonomous agent model, the photovoltaic unit, load unit and energy storage unit are effectively integrated to monitor and manage the power generation capacity, power demand and energy storage status of each agent in real time. The MQTT message transmission protocol is used to share data in a publish / subscribe mode, so that each agent can quickly and accurately obtain the required information, which can significantly improve the system's response speed to power supply and demand, and ensure that the photovoltaic unit can flexibly adjust the power generation priority according to the load demand in different time periods, thereby optimizing resource allocation. By introducing the Lotka-Volterra equation, the ecological relationship between photovoltaics, loads and energy storage can be dynamically simulated to ensure that the energy flow between each agent reaches the optimal state. The management method based on the ecological model not only improves the efficiency of energy use, but also reduces the energy consumption and cost of operation, and ultimately realizes the efficient use of renewable energy. The application of genetic algorithms makes the energy division process more intelligent and adaptive, and can continuously optimize the energy allocation strategy according to real-time data to ensure stable and efficient operation under different load demands. The adaptive scheduling framework provides an innovative solution for the management of renewable energy along urban roads, greatly improving the flexibility and reliability of energy management.

[0028] 2. By defining pheromones as an indicator to measure the level of collaboration among photovoltaic units, load units and energy storage units, it can effectively reflect the contribution and effect of each agent in meeting the load demand. The initial concentration of pheromones is the same, and the attenuation of pheromones is simulated through the volatilization mechanism to ensure that the collaborative relationship between agents can be dynamically adjusted. When the autonomous agent completes power generation or energy regulation, the update of the pheromone concentration is based on the degree to which it meets the load demand, so that agents with better performance can obtain more pheromones, thereby obtaining higher priority in subsequent decision-making. The pheromone-based collaborative mechanism not only improves the interactivity between agents, but also enhances the ability of intelligent decision-making. Through the adjustment of pheromone concentration, the autonomous agent of the photovoltaic unit can respond to the needs of the load unit first, thereby achieving the best match between load demand and power generation capacity, ensuring rapid adaptation and optimization of energy distribution under changing environmental conditions, and improving overall flexibility and adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0030] Figure 1 The present invention is a method flow chart of the photovoltaic power generation control and real-time energy dispatching system along urban highways.

[0031] Figure 2 It is a module schematic diagram of the photovoltaic power generation control and real-time energy dispatching system along the urban highway of the present invention. DETAILED DESCRIPTION

[0032] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0033] The present invention provides Figure 2 The photovoltaic power generation control and real-time energy dispatching system along the urban highway shown includes an agent construction module, an energy management module, a collaborative regulation module and a control dispatching module;

[0034] Agent building module: PV units, load units and energy storage units along urban roads are defined as autonomous agent models to monitor power generation capacity data, power demand data and energy storage power data in real time, and share data in a publish / subscribe mode through the MQTT message transmission protocol;

[0035] The photovoltaic units, load units and energy storage units along the urban roads are defined as autonomous agent models. The photovoltaic unit autonomous agent monitors the photovoltaic power generation capacity data in real time through light sensors, including output power, status and expected power generation. The load unit autonomous agent monitors the load power demand data in real time according to the actual power usage, including different types of power demand such as residential, commercial buildings and traffic lights. The energy storage unit autonomous agent monitors the energy storage power data of the energy storage battery in real time, where the charging and discharging status includes charging, discharging and standby, and the usage efficiency includes cycle efficiency and discharge depth. The MQTT message transmission protocol adopts the publish / subscribe mode, and the photovoltaic unit autonomous agent, load unit autonomous agent and energy storage unit autonomous agent send data through topics, and use topic subscription to receive data, so as to realize data sharing among the photovoltaic unit autonomous agent, load unit autonomous agent and energy storage unit autonomous agent.

[0036] Energy management module: defines ecological relationships, flow paths and dynamic action relationships, builds an adaptive scheduling framework, and manages energy flows between autonomous agents of photovoltaic units, autonomous agents of load units and autonomous agents of energy storage units by randomly generating initial solution individuals and applying genetic algorithms to optimize energy division;

[0037] By defining the ecological relationship, flow path and dynamic action relationship between the autonomous agents of photovoltaic units, load units and energy storage units, an adaptive scheduling framework based on the Lotka-Volterra equation is constructed. By randomly generating initial solution individuals and applying genetic algorithms to optimize energy division, efficient management of energy flow between photovoltaics, loads and energy storage is achieved. The specific steps are as follows:

[0038] S1. Define the boundaries of the agent relationship ecological model as the agent scope of the PV unit autonomous agent, the load unit autonomous agent, and the energy storage unit autonomous agent.

[0039] S2. Define the flow path of the ecological model as the process of data sharing among the photovoltaic unit autonomous agent, the load unit autonomous agent and the energy storage unit autonomous agent, which is used to simulate the conversion and distribution process of ecological energy. Set the data transfer efficiency between different agents according to the transfer rules of ecological energy. For example, the energy generated by the photovoltaic unit will be affected by environmental factors. Set the photovoltaic unit autonomous agent as the "prey", the load unit autonomous agent and the energy storage unit autonomous agent as the "predator", and use the Lotka-Volterra equation to describe the dynamic relationship between the autonomous agents. The specific formula is:

[0040]

[0041] in, Indicates power generation capacity data, represents the growth rate of power generation of the PV unit autonomous agent, represents the interaction coefficient between power generation capacity data and power demand data, represents the decay rate of the PV unit autonomous agent, L represents the power demand data, Indicates the influence coefficient of power generation capacity data on power demand data, represents the natural decay rate of electricity demand data, represents the conversion rate of electricity stored in the autonomous agent of the load unit, Indicates the energy storage capacity data. represents the efficiency provided by the PV unit autonomous agent to the energy storage unit autonomous agent, It represents the energy efficiency released by the energy storage unit autonomous agent to meet the energy consumption of the load unit autonomous agent. represents the decay rate of the energy storage unit autonomous agent, It represents the change process time of the PV unit autonomous agent, load unit autonomous agent and energy storage unit autonomous agent, and defines , , The solution is the energy balance point, which determines the dynamic equilibrium state between the autonomous agent of the photovoltaic unit, the autonomous agent of the load unit and the autonomous agent of the energy storage unit.

[0042] S3. Establish an optimal energy partitioning framework to simulate ecological energy allocation. Randomly generate initial solution individuals based on the power generation capacity data, power demand data and energy storage data according to the dynamic equilibrium state. Set a custom fitness function to calculate the fitness value of the optimal energy. Select the initial solution individuals with high fitness values. Use single-point crossover to use the energy balance point as the crossover point and perform cutting. Exchange the genes at the corresponding positions. Repeat iterations to generate offspring individuals with optimal energy partitioning. Calculate the fitness value cyclically. Define the fitness threshold as 0.05. Select offspring individuals with fitness values ​​lower than the fitness threshold for optimal energy allocation.

[0043] Collaboration regulation module: defines pheromones to measure the collaboration level among the autonomous agents of the photovoltaic unit, the load unit, and the energy storage unit, assigns the same initial pheromone concentration value, and defines a volatilization mechanism to simulate the volatilization effect of pheromones;

[0044] Preferably, pheromones are defined to measure the level of cooperation among the autonomous agents of the photovoltaic unit, the autonomous agents of the load unit, and the autonomous agents of the energy storage unit, and the same initial pheromone concentration value is assigned. A volatilization mechanism is defined to simulate the volatilization effect of pheromones. When the autonomous agent completes power generation or energy regulation once, the pheromone concentration is increased according to the degree of satisfying the autonomous agent of the load unit. The specific increase and update formula is:

[0045]

[0046] in, represents the pheromone concentration of autonomous agent i at time T, represents the pheromone concentration of autonomous agent i at time T-1, It represents the adjustment coefficient for controlling the incremental strength of pheromone. represents the actual energy generated by the agent during the period from T to T-1, It represents the degree to which autonomous agent i satisfies the autonomous agent of load unit.

[0047] Assume that there is an actual power generation of an autonomous agent in a certain period of time , the load demand of the load unit autonomous agent corresponding to the autonomous agent is 40kWh, then the satisfaction rate is: , setting the adjustment coefficient k=0.1, the pheromone increment is: , assuming that the initial pheromone concentration of autonomous agent i at time T is , then the updated pheromone concentration is: .

[0048] Control and dispatch module: adjust the power generation priority of the photovoltaic unit autonomous agent according to the pheromone concentration, and adjust the supply of the load unit autonomous agent and the energy storage unit autonomous agent;

[0049] The power generation priority of the photovoltaic unit autonomous agent is adjusted according to the pheromone concentration. The specific formula is:

[0050]

[0051] in, represents the power generation priority of the PV unit autonomous agent i, represents the weight coefficient of pheromone concentration, Represents the weight coefficient of the current load unit autonomous agent demand energy, It represents the current load demand energy of the photovoltaic unit autonomous agent i. According to the pheromone concentration and the power generation priority of the photovoltaic unit autonomous agent, the load unit autonomous agent and the energy storage unit autonomous agent supply are adjusted. The specific formula is:

[0052]

[0053] in, represents the energy provided by the PV unit autonomous agent e to the load unit autonomous agent or the energy storage unit autonomous agent f, represents the sum of pheromone concentrations of all autonomous agents at time T, represents the total load demand energy of the load unit autonomous agent and the energy storage unit autonomous agent j.

[0054] Assume that there is an autonomous agent with a pheromone concentration of , the sum of the pheromone concentrations of all autonomous agents at time T is and ,but , so autonomous agent e will provide 6.5 units of energy to the load unit autonomous agent or energy storage unit autonomous agent f.

[0055] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. Photovoltaic power generation control and real-time energy dispatching system along urban highways, characterized in that: It includes agent construction module, energy management module, collaborative regulation module and control scheduling module; Agent building module: PV units, load units and energy storage units along urban roads are defined as autonomous agent models to monitor power generation capacity data, power demand data and energy storage power data in real time, and share data in a publish / subscribe mode through the MQTT message transmission protocol; Energy management module: defines ecological relationships, flow paths and dynamic action relationships, builds an adaptive scheduling framework, and manages energy flows between autonomous agents of photovoltaic units, autonomous agents of load units and autonomous agents of energy storage units by randomly generating initial solution individuals and applying genetic algorithms to optimize energy division; The ecological relationship is to define the ecological model of agent relationship, whose boundaries are the agent ranges of the autonomous agent of the photovoltaic unit, the autonomous agent of the load unit, and the autonomous agent of the energy storage unit; The flow path is to define the flow path of the ecological model as a process of data sharing among the autonomous agent of the photovoltaic unit, the autonomous agent of the load unit and the autonomous agent of the energy storage unit; The dynamic interaction relationship is to set the data transfer efficiency between different agents according to the transfer rules of ecological energy, setting the photovoltaic unit autonomous agent as the "prey", and the load unit autonomous agent and energy storage unit autonomous agent as the "predator"; Collaboration regulation module: defines pheromones to measure the collaboration level among the autonomous agents of the photovoltaic unit, the load unit, and the energy storage unit, assigns the same initial pheromone concentration value, and defines a volatilization mechanism to simulate the volatilization effect of pheromones; Control and dispatch module: adjust the power generation priority of the photovoltaic unit autonomous agent according to the pheromone concentration, and adjust the supply of the load unit autonomous agent and the energy storage unit autonomous agent.

2. The photovoltaic power generation control and real-time energy dispatching system along urban highways according to claim 1 is characterized in that: In the agent construction module, the specific steps of establishing the agent relationship model are: defining the photovoltaic units, load units and energy storage units along the urban roads as autonomous agent models, the photovoltaic unit autonomous agent monitors the photovoltaic power generation capacity data in real time through the light sensor, the load unit autonomous agent monitors the load power demand data in real time according to the actual power usage, and the energy storage unit autonomous agent monitors the energy storage power data of the energy storage battery in real time.

3. The photovoltaic power generation control and real-time energy dispatching system along urban highways according to claim 1 is characterized in that: In the energy management module, an adaptive scheduling framework based on the Lotka-Vol terra equation is constructed, and its specific formula is: Among them, P represents the power generation capacity data, α represents the power generation growth rate of the photovoltaic unit autonomous agent, β represents the interaction coefficient between the power generation capacity data and the power demand data, ε1 represents the decay rate of the photovoltaic unit autonomous agent, L represents the power demand data, δ represents the influence coefficient of the power generation capacity data on the power demand data, γ represents the natural decay rate of the power demand data, θ1 represents the conversion rate of power stored in the load unit autonomous agent, S represents the energy storage power data, μ represents the efficiency of the photovoltaic unit autonomous agent provided to the energy storage unit autonomous agent, ξ represents the energy efficiency released by the energy storage unit autonomous agent to meet the load unit autonomous agent, ε2 represents the decay rate of the energy storage unit autonomous agent, and t represents the change process time of the photovoltaic unit autonomous agent, the load unit autonomous agent and the energy storage unit autonomous agent.

4. The photovoltaic power generation control and real-time energy dispatching system along urban highways according to claim 1 is characterized in that: In the energy management module, the specific steps of applying the genetic algorithm to optimize the energy division are: randomly generate initial solution individuals according to the power generation capacity data, power demand data and energy storage data according to the dynamic equilibrium state, set a custom fitness function to calculate the fitness value of the optimal energy, select the initial solution individuals with high fitness values, use the energy balance point as the crossover point and cut it by single-point crossover, exchange the genes at the corresponding positions, repeatedly iterate to generate offspring individuals with optimal energy division, cyclically calculate the fitness value, define the fitness threshold as 0.05, and select offspring individuals with fitness values ​​lower than the fitness threshold for optimal energy allocation.

5. The photovoltaic power generation control and real-time energy dispatching system along urban highways according to claim 1 is characterized in that: In the energy management module, an optimal energy partitioning framework is established to simulate ecological energy allocation. The power generation capacity data, power demand data and energy storage power data are randomly generated into initial solution individuals according to the dynamic equilibrium state. A custom fitness function is set to calculate the fitness value of the optimal energy. The initial solution individuals with high fitness values ​​are selected, and the energy balance point is used as the crossover point and cut by using single-point crossover. The genes at the corresponding positions are exchanged, and the offspring individuals with optimal energy partition are generated by repeated iterations. The fitness values ​​are calculated cyclically, and the fitness threshold is defined as 0.

05. The offspring individuals with fitness values ​​lower than the fitness threshold are selected for optimal energy allocation.

6. The photovoltaic power generation control and real-time energy dispatching system along urban highways according to claim 1 is characterized by: In the collaborative regulation module, pheromones are defined to measure the level of collaboration among the autonomous agents of the photovoltaic unit, the autonomous agents of the load unit, and the autonomous agents of the energy storage unit, and the same initial pheromone concentration value is assigned. A volatilization mechanism is defined to simulate the volatilization effect of pheromones. When the autonomous agent completes power generation or energy regulation once, the pheromone concentration is increased according to the degree to which the autonomous agent of the load unit is satisfied.

7. The photovoltaic power generation control and real-time energy dispatching system along urban highways according to claim 6 is characterized by: The specific increasing and updating formula for increasing the pheromone concentration is: P i (T)=P i (T-1)+k*E i *R LoadMatching Among them, P i (T) represents the pheromone concentration of autonomous agent i at time T, P i (T-1) represents the pheromone concentration of autonomous agent i at time T-1, k represents the adjustment coefficient for controlling the pheromone increment intensity, E i represents the actual energy generated by the agent during the period from T to T-1, R LoadMatching It indicates the degree to which agent i meets the load demand.

8. The photovoltaic power generation control and real-time energy dispatching system along urban highways according to claim 1 is characterized by: In the control scheduling module, the power generation priority of the photovoltaic unit autonomous agent is adjusted according to the pheromone concentration, and the specific formula is: X j =P i (T)*ω1+C*ω2 Among them, X j represents the power generation priority of the PV unit autonomous agent i, ω1 represents the weight coefficient of the pheromone concentration, ω2 represents the weight coefficient of the current load unit autonomous agent required energy, and C represents the current load demand energy of the PV unit autonomous agent i.

9. The photovoltaic power generation control and real-time energy dispatching system along urban highways according to claim 1 is characterized by: In the control scheduling module, the autonomous agent supply of the load unit and the autonomous agent supply of the energy storage unit are adjusted according to the pheromone concentration and the power generation priority of the autonomous agent of the photovoltaic unit. The specific formula is: Among them, Y ef represents the energy provided by the PV unit autonomous agent e to the load unit autonomous agent or the energy storage unit autonomous agent f, represents the sum of pheromone concentrations of all autonomous agents at time T, D f represents the total load demand energy of the load unit autonomous agent and the energy storage unit autonomous agent j.

Images