An Edge Data Transmission Optimization Method Based on Energy Consumption Minimization and Load Balancing

Abstract

The present invention discloses an edge data transmission optimization method based on minimum energy consumption and load balancing, belonging to the technical field of edge computing, which is implemented through a system composed of a central control server, edge nodes, transmission links, and an SDN controller, and includes the following steps: S1, network topology modeling and data collection; S2, link selection optimization; S3, topology optimization and dynamic adjustment; S4, data transmission execution and control; S5, adaptive dynamic adjustment; S6, repeatedly execute the above S1 to S5. The present invention adopts a multi-objective reinforcement learning algorithm to achieve the joint optimization of minimum energy consumption and load balancing in edge data transmission; by dynamically adjusting the transmission links and shutting down redundant nodes and links, the overall energy consumption of the system is reduced; through link classification and load balancing optimization, the data transmission efficiency and network stability are improved; a heuristic factor and a Chebyshev scalarization function are introduced to accelerate the algorithm convergence speed.

Description

Technical Field

[0001] The present invention relates to the technical field of edge computing, and in particular to an edge data transmission optimization method based on energy consumption minimization and load balancing. Background Art

[0002] In the Internet of Things (IoT) environment, edge computing, as a distributed computing paradigm, aims to decentralize computing tasks from traditional cloud computing centers to edge nodes close to data sources. In this way, edge computing can significantly reduce data transmission latency, improve real-time response capabilities, and relieve the load on the central data center.

[0003] In the edge computing environment, the key challenge in data transmission is how to optimize network energy consumption and load distribution while meeting service quality requirements. The complexity of this multi-objective optimization problem lies in that energy consumption and load balancing are often conflicting: to achieve low energy consumption, it may be necessary to reduce the use of network devices, which may lead to excessive load on certain links or nodes; and to achieve load balancing, it may be necessary to activate more devices, thereby increasing energy consumption.

[0004] Although some studies have realized the conflict between energy consumption and load balancing and tried to combine them for optimization, most methods are still limited to taking one of the objectives as a constraint condition rather than true multi-objective optimization. For example, when performing load balancing, energy consumption minimization is taken as a fixed constraint condition, but it is not dynamically adjusted to adapt to the actual operation of the network. The result of this optimization strategy is that although load balancing can be achieved to a certain extent, in practical applications, the total energy consumption of the system is still difficult to reach the optimal value.

[0005] In addition, many existing optimization algorithms usually assume that the network topology and transmission requirements are static, that is, they do not change during the optimization process. However, in the edge computing environment, the network state and data transmission requirements are dynamically changing; IoT devices may generate different data transmission requirements at different time periods, and the network topology may also change due to device failures or the addition of new nodes. Static optimization algorithms are difficult to adapt to this dynamic environment and may lead to poor optimization effects or even fail to meet real-time requirements in practical applications.

[0006] Therefore, how to provide a transmission optimization method with multi-objective joint optimization and dynamic adaptability is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0007] The purpose of the present invention is to provide an edge data transmission optimization method based on energy consumption minimization and load balancing to solve the problems in the background art.

[0008] To achieve the above object, the present invention provides an edge data transmission optimization method based on energy consumption minimization and load balancing, including the following steps:

[0009] S1. Network topology modeling and data collection: The system conducts comprehensive topology modeling and data collection on the network status;

[0010] S2. Link selection optimization: Design the state space and action space, obtain the Pareto approximation set through Pareto optimization as the global optimal solution, construct a multi-objective reward function to classify each link selection strategy in the action space, introduce a heuristic factor to weight the result of the reward function, and use the Chebyshev scalarization function to comprehensively score and optimize multiple links to select the optimal link;

[0011] S3. Topology optimization and dynamic adjustment: The system dynamically shuts down redundant nodes and links based on the result of S2 to further optimize the network topology. At the same time, the central control server monitors and adjusts the link status in real time through the SDN controller; specifically:

[0012] 1) Node shutdown: Place the nodes without data transmission requirements in the low-power mode until there are new data transmission requirements;

[0013] 2) Link optimization: Shut down the ports that are not involved in the current data transmission link and reduce the power to save energy consumption;

[0014] At the same time, the system has the ability of dynamic adjustment: The central control server monitors and adjusts the link status in real time through the SDN controller. When the load of a certain link is too high, the system will automatically select a new link and divert part of the traffic to other links;

[0015] S4. Data transmission execution and control: After completing S3, the data transmission task is transmitted through the optimized link, and the SDN controller executes specific link configuration and bandwidth allocation to ensure the efficiency and stability of data transmission;

[0016] S5. Adaptive dynamic adjustment: The system automatically updates the Q value and the Pareto approximation set according to the change of the real-time network status and adjusts the transmission link;

[0017] S6. Repeat the execution of S1 to S5 in a loop.

[0018] Preferably, the specific steps of S1 are:

[0019] S11. Construct the minimum topology subset: The system analyzes according to the topology structure of the current network to determine the key links that support the minimum data transmission in the network. The key links are screened by the following conditions:

[0020] 1) Link bandwidth utilization: Prioritize the link with low bandwidth utilization, which can not only ensure data transmission requirements but also avoid congestion.

[0021] 2) Node processing capacity and energy consumption: Only activate the nodes with low computing load and low energy consumption, and avoid using high-energy-consuming edge nodes.

[0022] S12. Sending and receiving of probe packets: The central control server periodically sends probe packets to each edge node. Each probe packet records the sending timestamp. After the edge node returns the response packet, the central control server calculates the link delay according to the difference between the receiving time and the sending time.

[0023] S13. Monitoring of link bandwidth: Use the central control server to count the data volume transmitted on each link and calculate the bandwidth utilization according to the transmission time. For example, if a link transmits X bytes of data in a certain period of time and takes Y seconds, the bandwidth utilization of this link is X / Y.

[0024] S14. Node processing capacity and energy consumption: The central control server regularly monitors the resource usage conditions such as the CPU and memory of each edge node, collects the energy consumption data of the nodes, and evaluates the load conditions of each node to ensure that data transmission will not cause node overload.

[0025] Preferably, the specific steps of S2 are as follows:

[0026] S21. Construct a state space with the current network topology and resource usage obtained in S1 as state information. Each state includes: 1) The processing capacity and current load of each node; 2) The bandwidth utilization, transmission delay and energy consumption of each link; 3) The topology structure of the network.

[0027] S22. In each data transmission, the system will select one or more links to transmit data. The action of each state in the state space is to select different transmission links, and construct an action space with each link selection strategy as an action.

[0028] S23. Combine the multi-objective optimization and Q-learning methods to construct an energy consumption optimization reward function and a load balancing reward function respectively, and then construct a multi-objective reward function with energy consumption optimization and load balancing as reward factors. Classify the candidate links into four levels: high-priority low-load, high-priority high-load, low-priority low-load, and low-priority high-load according to the multi-objective reward function, and preferentially select the high-priority low-load links.

[0029] The reward factors are:

[0030] 1) Energy optimization: The lower the energy consumption of a link, the higher the reward value. The system preferentially selects links with low energy consumption for data transmission, aiming to minimize the overall network energy consumption;

[0031] 2) Load balancing: The more balanced the load distribution of a link, the higher the reward value. By introducing the congestion factor of the link, the system can identify links with lighter loads and preferentially select these links for transmission;

[0032] S24. Introduce a heuristic factor as the weighted proportionality coefficient of the multi-objective reward function obtained in S23, and use the weighted result as the value of the final multi-objective reward function to further guide the system to select the links in the global optimal solution and control the search of the solution space;

[0033] S25. Action selection: For the links selected in S24, use the link selection mechanism based on the Chebyshev scalarization function to select the link with the minimum energy consumption and the best load balancing after multiple iterations.

[0034] Preferably, the S21 - S25 constitute a multi-objective reinforcement learning algorithm.

[0035] Preferably, in S23, the specific steps of the multi-objective optimization method are as follows:

[0036] Consider the two objectives of minimizing energy consumption and load balancing simultaneously, and obtain the Pareto approximation set through Pareto optimization as the global optimal solution. In the actual optimization process, it is very difficult to find the exact optimal set, so the Pareto approximation set is used to represent the set close to the global optimal solution;

[0037] Suppose the network topology is represented by a directed graph G, G=(V, E, C), where V is the set of nodes, E is the set of links, and C is the set of link capacities;

[0038] Define the congestion factor θ e for link e ij as the ratio of the traffic f ij on the link to the capacity c ij and is expressed as:

[0039]

[0040] where d ∈ D represents any destination d in the set of transmission destinations D, represents the sum of the transmission traffic with d as the destination on link e ij ;

[0041] The two main objectives of data transmission optimization are to minimize the total energy consumption P total and to obtain the maximum congestion factor θ on all links for load balancing eThe minimum value, specifically:

[0042] 1) Minimize the total energy consumption P total , expressed as:

[0043]

[0044] In the formula, y i indicates whether node v i is active, indicates the energy consumption of node v i , x ij indicates whether link e ij is active, and respectively indicate the link energy consumption of nodes v i and v j ;

[0045] 2) Minimize the maximum congestion factor θ e , expressed as:

[0046]

[0047] In the formula, E is the set of links in the current network topology, and e is any link in E;

[0048] 3) When performing optimization, the following constraints also need to be satisfied:

[0049] Flow conservation constraint, the flow conservation constraint of any node i is expressed as:

[0050]

[0051] In the formula, t d indicates the total bandwidth demand of destination d, and DEM is the set of node pairs with transmission requirements in the current network topology. For example, <i, d> indicates that there is a transmission requirement on the node pair from node i to destination node d;

[0052] Link capacity constraint, the total flow of each link cannot exceed its capacity, expressed as:

[0053]

[0054] Node activation constraint, a node can be active only when all its incoming and outgoing links are active, expressed as:

[0055]

[0056] In the formula, M is a large number used to ensure that a node is active only when all its incoming and outgoing links are active.

[0057] Preferably, in S23, the energy consumption optimization reward function is:

[0058]

[0059] The load balancing reward function is:

[0060]

[0061] In the formula, l represents a link, res(l) is the remaining bandwidth of link l, dem(i) is the bandwidth demand of transmission requirement i, PH is the set of candidate links, β, β 1 and β 2 are proportionality coefficients for adjusting different target weights, r is the bandwidth remaining rate of the link, and the calculation formula is total(l) is the total bandwidth of the link, θ is the bandwidth utilization rate of the link, and the calculation formula is θ avg is the average bandwidth utilization rate of all selected links;

[0062] The multi-objective reward function is:

[0063]

[0064] For the four conditional parts in the multi-objective reward function, the condition "res(l) < d emi " corresponds to the link that does not meet the condition, and the reward is 0; the condition "res(l) ≥ d emi , l ∈ PH" corresponds to high-priority low-load and high-priority high-load links, and the specific reward is determined by the load r; the condition corresponds to the reward for low-priority low-load links; the condition corresponds to the reward for low-priority high-load links.

[0065] Preferably, in S24, the heuristic factor is defined as:

[0066]

[0067] In the formula, η l,cur is a variable with a value of 0 or 1. It is equal to 1 indicating that the currently selected link l is in the currently known optimal solution, and 0 indicating that the currently selected link l is not in the currently known optimal solution. n is the current iteration number, and N represents the maximum iteration number. is used to represent the total energy consumption of the current global optimal solution, PT gb represents the link set of the current global optimal solution, θ e is the link congestion factor;

[0068] η l,curNormalize the weights representing the current global optimal solution, so that the links in the current global optimal solution obtain more rewards through the reward function, guiding the model to select the links in the current optimal solution;

[0069] At the beginning of the iteration, the value of n / N is small, the value of h is also small, and the influence on the reward function is small, enabling a wider search range and being more conducive to exploration. As n / N gradually increases, the value of h also gradually increases, and the multi-objective reinforcement learning algorithm selection will be more focused near the global optimal solution set, which helps to improve the convergence speed of the algorithm;

[0070] In the initial stage of the algorithm, the global optimal solution is defined as an empty set. In the initial iteration, the algorithm generates solutions and calculates the multi-objective performance values of these solutions, and then filters out the non-dominated solutions (solutions that are not surpassed by other solutions in all optimization objectives) and adds them to the global optimal solution. After each round of iteration, the global optimal solution is updated by adding new non-dominated solutions and removing the dominated solutions (surpassed in some optimization objectives). This process ensures that the global optimal solution is always the current optimal non-dominated solution set and gradually approaches the final Pareto optimal solution as the number of iterations increases.

[0071] Preferably, the specific steps of S25 are as follows:

[0072] 1) Generate multiple candidate links for the links selected in S24 according to the requirements, score each link based on the energy consumption and load balancing of the link, and calculate the Q values for each of them for decision-making for the energy consumption optimization reward function and the load balancing reward function in S23;

[0073] 2) Optimize the comprehensive score of each link using the Chebyshev scalarization function, and select the link with the highest total score. The scalarization formula is:

[0074]

[0075] In the formula, is the scalarized Q value, ω i is the weight of the i-th objective, represents the Q value of the state-action pair (s t ,a t ) on the i-th objective, z i is the ideal value of the i-th objective, represents taking the maximum value of the deviations for all objectives;

[0076] The Chebyshev scalarization method is used to calculate the weighted deviation of each objective. If the deviation of a certain objective is particularly large, it will dominate the final scalarized value, driving the optimization algorithm to make improvements on this objective first to narrow the deviation. This mechanism ensures the balance between all objectives and avoids the deviation of some objectives being too large and being ignored;

[0077] 3) According to the scalarized value, select the action a with the smallest value t as the action with the minimum energy consumption and the best load balancing, and perform the next transmission.

[0078] Preferably, the specific implementation process of S4 is as follows:

[0079] 1) Routing adjustment: The SDN controller transmits the data packet through the optimized link according to the instruction of the central control server. If a certain link is congested, the system will immediately recalculate and allocate a new link to avoid transmission bottlenecks;

[0080] 2) Bandwidth allocation: The SDN controller adjusts the bandwidth allocation according to the real-time state of the link to ensure that the high-load link will not be overly congested. The system adjusts the transmission bandwidth of each link in real time to maintain the overall stability of the network.

[0081] Preferably, the specific implementation process of S5 is as follows:

[0082] 1) Real-time monitoring: The central control server continuously monitors the bandwidth, delay, and load conditions of the nodes and links;

[0083] 2) Dynamic adjustment: When it is detected that the link utilization rate exceeds the threshold, the system will automatically re-plan the link to ensure the correct scheduling of data.

[0084] Therefore, the edge data transmission optimization method based on energy consumption minimization and load balancing of the present invention has the following beneficial effects:

[0085] (1) The present invention takes energy consumption and load balancing as optimization objectives, and through designing a reasonable reward function, ensures that these two objectives can be optimized simultaneously during the data transmission process. The present invention gradually approaches the optimal solution through a multi-step state update method, and reduces the number of occupied devices by constructing the minimum topological subset, thereby realizing energy consumption minimization. In addition, during the load distribution optimization process, the load on the selected link is balanced by minimizing the maximum congestion factor to avoid overloading of some links or nodes.

[0086] (2) By adopting a multi-objective optimization algorithm based on reinforcement learning, the present invention comprehensively considers two objectives of energy consumption and load balancing when selecting a transmission link. By dynamically updating the Pareto approximation set, the transmission link that occupies the fewest devices and links is selected, minimizing the number of active devices and their power consumption. In practical applications, this means that the computing resources and transmission resources in the network are more reasonably allocated, thus significantly reducing the power consumption during transmission. Especially in large-scale data transmission scenarios, this optimization effect is particularly obvious, enabling the system to maintain low energy consumption while meeting the requirements of efficient data transmission.

[0087] (3) The present invention also proposes a link classification mechanism that divides candidate links into four different levels to select the optimal link during the link construction process, which helps to optimize link selection, reduce transmission delay and energy consumption on the premise of ensuring load balancing. The present invention also effectively solves the problem of uneven distribution of data traffic among links in traditional networks through a load balancing optimization mechanism; by introducing the multi-objective optimization idea, not only the transmission link is optimized, but also the traffic is more evenly distributed in the network. By classifying and real-time monitoring the links, the load balancing of each link is ensured, the usage frequency of overloaded links is reduced, and thus the transmission delay and data congestion are significantly reduced. This optimization strategy greatly improves the overall throughput of the network, enabling the system to complete more data transmission tasks in a shorter time and improving the transmission efficiency and service quality.

[0088] (4) To accelerate the convergence speed of the algorithm, the present invention introduces a heuristic factor to control the search of the solution space, and improves the optimization effect of the algorithm in complex network environments by strengthening the guiding effect of the existing optimal solution; it can find a transmission link close to the global optimum in a short time, avoiding the problem of local optimum solutions and significantly shortening the calculation and decision-making time. This feature enables the method to quickly adapt to changes in the network environment, especially in data transmission scenarios that require real-time optimization, ensuring the efficient operation of the system.

[0089] (5) To effectively select weights in multi-objective optimization, the present invention adopts a Chebyshev scalarization function based on roulette selection to optimize the weight selection process. This strategy can make a reasonable trade-off between multiple objectives, ensuring that both energy consumption and load balancing can be considered during the optimization process, thus obtaining a higher-quality solution.

[0090] (6) By adopting the Q-learning algorithm in reinforcement learning, the present invention can dynamically adjust the transmission link and load distribution according to the actual operating state and transmission requirements of the network. When some links or devices fail, the system can quickly respond and reallocate the transmission link to ensure the continuity and stability of data transmission. In addition, the load balancing optimization mechanism of the present invention enables the system to effectively cope with the impact of sudden traffic and avoid network collapse caused by overloading of individual links. This self-adaptability enables the system to maintain an efficient and stable operating state in the face of a complex network environment.

[0091] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Description of the Drawings

[0092] Figure 1 It is the overall process framework diagram of the embodiment of the present invention. Detailed Embodiments

[0093] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0094] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention.

[0095] The method protected by the present invention is based on an optimized system. The system includes a central control server, edge nodes, transmission links and an SDN controller. The central control server is the core control unit of the entire system. As the core control unit of the system, the central control server is responsible for real-time monitoring of all edge nodes and links in the entire network. The central server collects the key parameters of each node in real time by regularly sending probe data packets. The central control server not only needs to regularly collect data from each edge node, but also needs to dynamically adjust the path and network topology according to these data to ensure the minimization of energy consumption and the balanced distribution of load during data transmission.

[0096] The edge nodes are located near the data sources and are responsible for preprocessing the data and communicating with the central server and other nodes. The transmission links connect the edge nodes and the data center or other edge nodes, forming the physical basis of the entire network. During each data transmission, the system needs to select the optimal transmission path to minimize the energy consumption of the nodes and links as much as possible, while ensuring that the load is evenly distributed throughout the network.

[0097] The SDN controller is used to execute the path adjustment instructions issued by the central control server. The SDN controller controls the status of each network device through the OpenFlow protocol, and flexibly adjusts the traffic scheduling, bandwidth allocation, and topology configuration of the network devices. The centralized control mechanism of SDN makes network adjustment more flexible and efficient.

[0098] The following uses the above system and an edge data transmission optimization method based on energy consumption minimization and load balancing proposed by the present invention to illustrate its important role in different usage scenarios.

[0099] Embodiment 1

[0100] Apply the above system and optimization method in an intelligent factory:

[0101] In an intelligent factory, multiple edge nodes are deployed on different production devices. These nodes collect device status information in real time through sensors, such as temperature, vibration, operating status, etc. The central control server is responsible for monitoring the processing capacity, bandwidth utilization rate, and energy consumption of each node. The transmission link connects each node to the central server, and the SDN controller is used to control the traffic scheduling and link selection of each node.

[0102] After the system is completely deployed, the method protected by the present invention is used for testing. The results show that: the data transmission is efficient, the energy consumption is low, the network stability is good, and the system latency is low.

[0103] This shows that when it is applied to an intelligent factory, during the data transmission process, the system adjusts the transmission link according to the real-time status, reduces congestion, and ensures the efficient transmission of production data. While reducing the energy consumption of the devices in the intelligent factory, it improves the network stability and effectively reduces the overall latency of the system.

[0104] Embodiment 2

[0105] Apply the above system and optimization method in a remote monitoring system for efficient data transmission:

[0106] In a remote monitoring system, multiple cameras serve as edge nodes for real-time collection of environmental video data. The central control server is deployed in the data center and is responsible for receiving and processing the data of all edge nodes. The transmission link in the system connects the monitoring cameras to the central control server, and the SDN controller controls the data flow direction and priority.

[0107] Using the method protected by the present invention for testing, the results show that: the data transmission is stable, the video monitoring is clear and real-time, and the energy consumption is low.

[0108] This shows that when it is applied to a remote monitoring system, the system preferentially selects low-power links and avoids high-load links during data transmission, reducing energy consumption. The load balancing mechanism in the optimization method improves the stability of data transmission, ensuring the real-time, efficient, and clear video traffic. Through the system's calculation, the transmission links are reasonably allocated, saving power resources and being suitable for remote monitoring scenarios with limited power supply.

[0109] Embodiment 3

[0110] Apply the above system and optimization method to intelligent transportation management for link optimization:

[0111] In an intelligent transportation system, each traffic signal and monitoring device constitutes an edge node, and real-time traffic flow data is collected through sensors. The central control server is responsible for analyzing and processing this data to provide support for traffic dispatching. The transmission link connects each traffic node to the central server, and the SDN controller is used to control traffic scheduling.

[0112] Test with the method protected by the present invention, and the results show that: during peak hours, data transmission is smooth and highly time-sensitive.

[0113] This shows that when it is applied to intelligent transportation management, through this optimization method, the data traffic distribution in the network can be monitored in real time, ensuring that the selection of the transmission link not only meets the low-energy consumption requirements but also maintains load balance, guaranteeing that the data stream can be transmitted smoothly during peak hours and there will be no signal delay caused by network congestion.

[0114] Therefore, the present invention adopts the above-mentioned edge data transmission optimization method based on minimum energy consumption and load balance, uses a multi-objective reinforcement learning algorithm to achieve the joint optimization of minimum energy consumption and load balance in edge data transmission; reduces the overall energy consumption of the system by dynamically adjusting the transmission link and shutting down redundant nodes and links; improves data transmission efficiency and network stability through link classification and load balance optimization; introduces a heuristic factor and a Chebyshev scalarization function to accelerate the algorithm convergence speed.

[0115] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention and are not intended to limit it. 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: they can still modify or equivalently replace the technical solution of the present invention, and these modifications or equivalent replacements cannot make the modified technical solution deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. An edge data transmission optimization method based on energy consumption minimization and load balancing is implemented by a system consisting of a central control server, edge nodes, transmission links and an SDN controller, characterized in that: The following steps are involved: S1. Network topology modeling and data collection: The system performs comprehensive topology modeling and data collection on the network status; S2. Link selection optimization: Design the state space and action space, obtain the Pareto approximate set through Pareto optimization, and use it as the global optimal solution. Construct a multi-objective reward function to classify each link selection strategy in the action space, introduce a heuristic factor to weight the result of the reward function, use the Chebyshev scalar function to comprehensively score and optimize multiple links, and select the optimal link. The multi-objective reward function is: ； In the formula, Indicates a link, Yes Link The remaining bandwidth, It is the transmission requirement The bandwidth demand, is the set of candidate links, , and is the proportional coefficient for adjusting the weights of different targets, is the bandwidth surplus rate of the link, and the calculation formula is , is the total bandwidth of the link, is the bandwidth utilization of the link, calculated as , is the average bandwidth utilization of all selected links; The heuristic factor is defined as: ； In the formula, is a variable, n is the current number of iterations, N is the maximum number of iterations, It is used to represent the total energy consumption of the current global optimal solution. represents the link set of the current global optimal solution, is the link congestion factor; S3, topology optimization and dynamic adjustment: Based on the results of S2, the system dynamically shuts down redundant nodes and links to further optimize the network topology. At the same time, the central control server monitors and adjusts the link status in real time through the SDN controller; S4, data transmission execution and control: After completing S3, the data transmission task is transmitted through the optimized link, and the SDN controller performs specific link configuration and bandwidth allocation to ensure the efficiency and stability of data transmission; S5, Adaptive dynamic adjustment: The system automatically updates the Q value and Pareto approximation set according to the changes in the real-time network status and adjusts the transmission link; S6, executing S1 to S5 repeatedly.

2. The edge data transmission optimization method based on energy consumption minimization and load balancing according to claim 1, characterized in that: The specific steps of S1 are: S11. Constructing the minimum topology subset: The system analyzes the current network topology and determines the key links in the network that support the minimum data transmission; S12, sending and receiving detection data packets: the central control server periodically sends detection data packets to each edge node, and after the edge node returns a response data packet, the link delay is calculated; S13, link bandwidth monitoring: using the central control server to calculate the bandwidth utilization of each link; S14. Node processing capacity and energy consumption: The central control server regularly monitors the resource usage of each edge node, collects the node's energy consumption data, and evaluates the load of each node to ensure that data transmission does not cause node overload.

3. The edge data transmission optimization method based on energy consumption minimization and load balancing according to claim 1, characterized in that: The specific steps of S2 are: S21, using the current network topology and resource usage obtained in S1 as state information to construct a state space, where each state includes: 1) the processing capacity and current load of each node; 2) the bandwidth utilization, transmission delay and energy consumption of each link; 3) the topological structure of the network; S22, the action of each state in the state space is to select a different transmission link, and each link selection strategy is used as an action to construct the action space; S23. Combining multi-objective optimization and Q-learning methods, respectively construct energy consumption optimization reward function and load balancing reward function, then construct a multi-objective reward function with energy consumption optimization and load balancing as reward factors, and classify candidate links into four levels of high priority and low load, high priority and high load, low priority and low load, and give priority to high priority and low load links according to the multi-objective reward function; S24, introducing a heuristic factor as a weighted proportional coefficient of the multi-objective reward function obtained in S23, and using the weighted result as the value of the final multi-objective reward function to further guide the system to select a link in the global optimal solution; S25, action selection: For the link selected in S24, a link selection mechanism based on Chebyshev scalar function is used to select the link with the minimum energy consumption and the best load balancing after multiple iterations.

4. The edge data transmission optimization method based on energy consumption minimization and load balancing according to claim 3, characterized in that: In S23, the energy consumption optimization reward function is: ； The load balancing reward function is: 。 5. The edge data transmission optimization method based on energy consumption minimization and load balancing according to claim 4, characterized in that: The specific steps of S25 are as follows: 1) Generate multiple candidate links for the link selected in S24 according to the demand, score each link according to the energy consumption and load balancing of the link, and use the Q-learning method to calculate the Q value for decision-making based on the energy consumption optimization reward function and load balancing reward function in S23; 2) Use the Chebyshev scalar function to optimize the comprehensive score of each link and select the link with the highest total score. The scalar formula is: ； In the formula, is the scalarized Q value, is the weight of the ith target, Representing state-action pairs The Q value on the i-th target, is the ideal value of the ith target, Indicates that the maximum value of the deviation of all targets is sought; 3) According to the scalarized Value, selected in the current state The action with the smallest value As the action with the minimum energy consumption and the best load balance, the next transmission is performed.

6. The edge data transmission optimization method based on energy consumption minimization and load balancing according to claim 5, characterized in that: In step 1) of S25, the Q value calculation formula is: ； In the formula, and Respectively represent the current state and action, is the learning rate, is the current instant reward, is the discount factor, and They are the next state and action after taking the action.

7. The edge data transmission optimization method based on energy consumption minimization and load balancing according to claim 1, characterized in that: The specific steps of S4 are: 1) Route adjustment: The SDN controller transmits the data packet through the link selected by S25 according to the instructions of the central control server. If a link is congested, the system will immediately recalculate and allocate a new link to avoid transmission bottlenecks; 2) Bandwidth allocation: The SDN controller adjusts bandwidth allocation according to the real-time status of the link to ensure that high-load links are not overly congested. The system adjusts the transmission bandwidth of each link in real time to maintain the overall stability of the network.

8. The edge data transmission optimization method based on energy consumption minimization and load balancing according to claim 1, characterized in that: The specific steps of S5 are: 1) Real-time monitoring: The central control server continuously monitors the bandwidth, latency, and load of nodes and links; 2) Dynamic adjustment: When it is detected that the link utilization exceeds the threshold, the system automatically replans the link to ensure that data is correctly scheduled.

Images