Industrial internet scene-oriented dynamic resource allocation method and related equipment

Abstract

The invention provides an industrial internet scene-oriented dynamic resource allocation method and related equipment, which considers that the industrial internet scene has mobile position production equipment of a time-varying geographic position, so that the total time delay and the total energy consumption of the scene are analyzed, and processing is carried out through a resource consumption algorithm based on the total time delay and the total energy consumption, so that the dynamic resource allocation efficiency is improved. According to the error between the predicted total resource energy consumption and the actual total resource energy consumption, guiding whether the target edge server executes resource reallocation in the communication range or not; and then adaptively solving an optimal resource allocation scheme in the considered scene based on the near-end strategy optimization algorithm as a target resource allocation strategy, and carrying out resource allocation according to the target resource allocation strategy, so that the resource allocation strategy can be adaptively optimized while the production demand change of the industrial internet scene can be met, and the resource allocation efficiency is improved. And the overall efficiency and reliability of the system are improved.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a dynamic resource allocation method for industrial Internet scenarios. Background Art

[0002] The Industrial Internet of Things (IIoT) is crucial to the development of smart manufacturing. Due to the heterogeneity of industrial network systems, industrial production equipment with different workloads compete for limited communication resources, which requires optimizing resource allocation to achieve effective resource utilization.

[0003] However, the industrial Internet environment is highly dynamic and uncertain, and the geographical location of industrial production equipment will change over time, making it difficult for traditional resource allocation strategies to adapt to changing needs. Summary of the invention

[0004] In view of this, the purpose of this application is to propose a dynamic resource allocation method and related equipment for industrial Internet scenarios to solve the above-mentioned technical problems.

[0005] Based on the above purpose, the first aspect of the present application provides a dynamic resource allocation method for industrial Internet scenarios, which is applied to a dynamic resource allocation system, wherein the system includes multiple edge servers, and any edge server among the multiple edge servers is used as a target edge server, and the target edge server is respectively communicated with at least one fixed position production equipment and at least one mobile position production equipment; the method includes:

[0006] Determine the total delay corresponding to the target edge server in the industrial Internet scenario, and determine the total energy consumption corresponding to the target edge server in the industrial Internet scenario;

[0007] Based on the total delay and the total energy consumption, a resource consumption algorithm is used to process the total delay and the total energy consumption to obtain an actual total resource consumption;

[0008] Obtaining the historical delay and historical energy consumption corresponding to the target edge server, obtaining the predicted total delay and the predicted total energy consumption through a pre-trained prediction model according to the historical delay and the historical energy consumption, and processing the predicted total delay and the predicted total energy consumption through a resource consumption algorithm to obtain the predicted total resource consumption;

[0009] Determine an error between the actual total resource consumption and the predicted total resource consumption, and determine whether to reallocate resources on the target edge server based on the error to obtain a determination result;

[0010] Based on the determination result, the actual total resource consumption is optimized by a proximal strategy optimization algorithm to obtain a target resource allocation strategy, and resources are allocated to fixed-location production equipment and mobile-location production equipment that communicate with the target edge server according to the target resource allocation strategy.

[0011] Based on the same inventive concept, the second aspect of the present application provides a dynamic resource allocation device for industrial Internet scenarios, the device is arranged in a dynamic resource allocation system, the system includes multiple edge servers, any edge server among the multiple edge servers is used as a target edge server, and the target edge server is respectively communicated with at least one fixed position production equipment and at least one mobile position production equipment; the device includes:

[0012] A determination module is configured to determine a total delay corresponding to the target edge server in an industrial Internet scenario, and to determine a total energy consumption corresponding to the target edge server in an industrial Internet scenario;

[0013] A resource consumption processing module, configured to process the total delay and the total energy consumption through a resource consumption algorithm to obtain an actual total resource consumption;

[0014] A prediction module is configured to obtain a historical delay and a historical energy consumption corresponding to the target edge server, obtain a predicted total delay and a predicted total energy consumption according to the historical delay and the historical energy consumption through a pre-trained prediction model, and process the predicted total delay and the predicted total energy consumption through a resource consumption algorithm to obtain a predicted total resource consumption;

[0015] a reallocation determination module, configured to determine an error between the actual total resource consumption and the predicted total resource consumption, and determine whether to perform resource reallocation on the target edge server based on the error to obtain a determination result;

[0016] The optimization module is configured to optimize the actual total resource consumption through a proximal strategy optimization algorithm based on the determination result, obtain a target resource allocation strategy, and allocate resources to the fixed-location production equipment and the mobile-location production equipment that communicate with the target edge server according to the target resource allocation strategy.

[0017] Based on the same inventive concept, the third aspect of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method described in the first aspect above when executing the computer program.

[0018] Based on the same inventive concept, the fourth aspect of the present application provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the method described in the first aspect above.

[0019] From the above, it can be seen that the dynamic resource allocation method and related equipment for industrial Internet scenarios provided by the present application take into account the existence of mobile production equipment with time-varying geographical locations in industrial Internet scenarios. Therefore, the total delay and total energy consumption of the scenario are analyzed, and the total delay and total energy consumption are processed through a resource consumption algorithm to obtain the actual total resource consumption. Then, based on the error between the predicted total resource energy consumption and the actual total resource energy consumption, the target edge server is guided to perform resource reallocation within the communication range. Then, based on this, the proximal strategy optimization algorithm is used to adaptively solve the optimal resource allocation scheme in the considered scenario as the target resource allocation strategy, and resources are allocated according to the target resource allocation strategy. This can meet the changes in production demand in the industrial Internet scenario while adaptively optimizing the resource allocation strategy to improve the overall efficiency and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1A A schematic diagram of a collaborative optimization framework according to an embodiment of the present application;

[0022] Figure 1B A schematic diagram of a model architecture corresponding to a dynamic resource allocation system according to an embodiment of the present application;

[0023] Figure 1C A flowchart of the proximal strategy optimization algorithm processing of an embodiment of the present application;

[0024] Figure 1D A schematic diagram of releasing and allocating bandwidth due to movement of production equipment at a mobile location according to an embodiment of the present application;

[0025] Figure 2 A flowchart of a dynamic resource allocation method for industrial Internet scenarios according to an embodiment of the present application;

[0026] Figure 3 This is a structural block diagram of a dynamic resource allocation device for industrial Internet scenarios according to an embodiment of the present application;

[0027] Figure 4A schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0029] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0030] It is understandable that before using the technical solutions of each embodiment of the present application, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0031] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to the electronic device, application, server, storage medium or other software or hardware that performs the operation of the technical solution of the present application according to the prompt message.

[0032] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0033] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation method of this application. Other methods that meet relevant laws and regulations may also be applied to the implementation method of this application.

[0034] The Industrial Internet of Things (IIoT) is crucial to the development of smart manufacturing. However, the heterogeneity and complexity of industrial systems pose major challenges to dynamic and efficient resource allocation. First, existing resource allocation strategies often lack in-depth analysis of the impact of resource reallocation in dynamic scenarios: mobile industrial production equipment in smart factories moves regularly to connect various production processes in series, and the resource allocation strategy of mobile devices is affected by their location changes. In addition, the existing resource allocation cannot understand the unstructured data in the factory from a linguistic perspective, such as factory production plans and status information of various equipment in the factory. This makes it difficult for allocation strategies to adapt to changing needs. Therefore, this application considers the above two problems at the same time, introduces Large Language Models (LLM) into IIoT to propose a new framework, and analyzes the dynamic resource allocation problem in smart factories with time-varying geographic location characteristics. The dynamic resource allocation framework determined in this application provides a new perspective for flexible decision-making and resource allocation in smart factories. Solutions to the listed problems are as follows:

[0035] 1) Existing allocation schemes lack language understanding and cannot achieve flexible decision-making. In current research, many resource allocation strategies cannot fully understand the unstructured data within the factory, such as various status information in the production plan file, which requires technical personnel to interpret and convert. This lack of language understanding makes it impossible for existing models to flexibly adjust their strategies to cope with changes in the factory's production process or production priorities, thereby affecting overall production efficiency and resource utilization. Traditional deep reinforcement learning (DRL) models have difficulties in directly using unstructured data and need to rely on pre-defined fixed optimization objectives. When the factory's production process or production priority changes, these models cannot flexibly adjust their strategies to respond to new needs. Therefore, this application proposes a fusion framework based on LLM and deep reinforcement learning DRL. The framework uses the natural language processing capabilities of LLM to interpret unstructured production data, combined with the strategy exploration capabilities of DRL, to achieve intelligent decision-making on dynamic resource allocation problems. In this way, while responding to changes in factory production needs, resource allocation strategies can be optimized to improve the overall efficiency and reliability of the system.

[0036] 2) Lack of analysis on the impact of resource reallocation in dynamic scenarios. The equipment in smart manufacturing factories is not evenly distributed within the coverage of edge nodes. In most cases, the equipment in the factory is laid out according to the factory's production capacity and production process, so its distribution has the characteristics of hotspot distribution and concentrated distribution. In addition, the equipment in a smart factory is not all fixed. There will be mobile industrial production devices (Mobile Industrial Production Devices, M-IPD) (i.e., mobile location production devices) to assist industrial production. M-IPD also needs to communicate with edge nodes at all times, and its transmission delay requirements are more stringent than fixed devices (i.e., fixed location production devices). Due to the mobility of M-IPD, there will inevitably be two time-varying processes in its movement: moving away from edge nodes (target edge servers) and approaching edge nodes, which are not available for fixed devices. If the situation that the M-IPD is far away from the edge node is considered during resource allocation, in order to ensure the delay requirements, more bandwidth needs to be allocated to the M-IPD. However, when the M-IPD gradually approaches the edge node, the M-IPD does not need so much bandwidth to ensure the production delay requirements. The excess bandwidth is allocated, which will inevitably lead to a decrease in bandwidth utilization; the resource allocation scheme when the M-IPD is close to the edge node will inevitably be difficult to meet the link delay requirements when the M-IPD is far away from the edge node. In order to ensure the real-time position of the M-IPD, dynamic adjustments are made. However, if the bandwidth allocation scheme is adjusted in each time slot of the M-IPD movement, it is bound to cause a large computing energy consumption to the edge node. The ideal situation should be that the node makes an autonomous decision based on the actual situation whether the allocation scheme needs to be adjusted to achieve a balance between system delay and energy consumption. Therefore, based on the proposed fusion framework, this application provides a dynamic resource allocation method for industrial Internet scenarios, and designs a dynamic resource allocation strategy based on proximal strategy optimization of adaptive language information.

[0037] In addition, IIoT has gradually evolved into a key technology platform for intelligent manufacturing. Through network interconnection, data exchange, and system interoperability, IIoT can achieve precise control of the production process, reasonable scheduling of the manufacturing process, and flexible allocation of resources, creating an application-centric industrial ecosystem. Typical IIoT applications include network resource scheduling, fault diagnosis, and equipment status prediction. In these application scenarios, industrial production equipment IPDs will generate a large number of computing tasks, which are usually sensitive to delays or consume a lot of energy. IPDs usually have limited power, storage, and computing capabilities to process and transmit large amounts of production data. In addition, traditional cloud computing has significant waiting delays, which makes it difficult to meet the various quality of experience (QoE) or quality of service (QoS) requirements of IIoT applications. To solve this problem, edge computing (EC) is introduced in the Internet of Things, allowing industrial production equipment IPDs to directly transmit computing tasks to nearby edge servers (ES), thereby reducing task delays and equipment energy consumption compared to centralized cloud computing.

[0038] In order to achieve more efficient and intelligent resource management, the relevant technologies have effectively reduced task delays by optimizing power control and computing resource allocation of mobile edge computing. For example, a DRL-based offloading decision and time allocation algorithm solves mixed integer nonlinear programming problems and optimizes resource allocation. Jointly optimize subchannel allocation, offloading decision, and computing resource allocation to minimize delay; propose a joint optimization problem to minimize energy consumption while meeting delay requirements. An intelligent-driven 5G network IoT green resource allocation mechanism is proposed, which uses deep reinforcement learning for efficient resource management; a DRL-based resource allocation and IIoT device scheduling joint strategy is adopted to minimize delay, energy consumption, and model accuracy. The impact of mobile devices on resource allocation is analyzed, and a new mobile-aware scheduling method based on DRL is proposed to minimize the maximum task delay.

[0039] In addition, in order to better solve natural language processing tasks in different fields, the use of pre-trained LLM in related technologies can handle natural language processing tasks under a unified pre-training-fine-tuning paradigm. In the pre-training stage, the model usually learns general language representations through large-scale unlabeled text. In the fine-tuning stage, annotated and task-specific datasets are used to supervise the pre-trained model to perform specific downstream tasks. For example, a lightweight model based on the pre-trained model (BERT) architecture is trained for network threat detection in the Internet of Things; a framework of giving large language models optimal planning capabilities (LLM+P) is proposed, which combines the advantages of LLM and classical planners to solve planning problems; LLM is used for hierarchical goal decomposition and structured action planning, which significantly improves the success rate of completing complex tasks.

[0040] Among them, the problems existing in the above related technologies are as follows:

[0041] 1) Due to the heterogeneity of industrial network systems, industrial production devices (IPDs) with different workloads compete for limited communication resources, which requires optimized resource allocation to achieve effective resource utilization. However, effective resource allocation of IIoT faces many challenges. First, the access of massive devices has led to a highly distributed and complex IIoT environment, increasing the demand for industrial network processing power and data transmission capabilities. Second, the IIoT environment is highly dynamic and uncertain, and the geographical location of devices changes over time, resulting in frequent changes in communication paths and network topology. This further complicates the management and optimization of network resources, requiring factory networks to respond quickly and adjust resource allocation strategies. The resource allocation problem is a nonlinear integer programming problem that is non-deterministic polynomial (NP-hard), making it unrealistic to find a global optimal solution in polynomial time. The low complexity of traditional iterative optimization methods leads to a compromise in model performance, especially for systems with multi-dimensional inputs, making it difficult to solve the above problems.

[0042] 2) Although the related technologies have considered the characteristics of continuous production tasks in factories and dynamic wireless environments, they all explore resource allocation strategies from the perspective of equipment and tasks, without considering the impact of frequent resource allocation on the system in dynamic scenarios. This impact needs to be quantified to build a more reasonable allocation strategy.

[0043] 3) Existing DRL-based methods have two major limitations. The first is the lack of language understanding capabilities. Traditional DRL models have difficulty directly utilizing unstructured data, such as production planning documents and various status information in IIoT, which require manual interpretation and conversion. Second, existing models rely on predefined and fixed optimization objectives. When the factory's production process or production priorities change, these models cannot flexibly adjust strategies to cope with new demands, thus affecting overall productivity and resource utilization.

[0044] In response to the above-mentioned problems, this application introduces LLM into IIoT, endows the IIoT system with more powerful natural language interaction capabilities, and provides a new perspective for intelligent decision-making in complex manufacturing environments. Specifically, this application: 1) designs a fusion framework, namely the LLM-driven collaborative optimization (LCOP) framework, which aims to combine the natural language understanding and generation capabilities of LLM with the policy exploration capabilities of DRL. In addition, LCOP is applied to dynamic resource allocation to demonstrate its specific workflow. 2) The resource allocation problem in dynamic industrial scenarios characterized by time-varying geographical locations is analyzed. Considering the impact of frequent resource reallocation on system energy consumption in dynamic scenarios, reallocation decision variables are proposed to guide ES to reallocate resources within the communication range. A long short-term memory (LSTM) network is used to analyze data changes and affect the thresholds of decision variables. 3) Under the proposed framework, a dynamic resource allocation method for industrial Internet scenarios is proposed, and an adaptive language-adaptivelanguage PPO dynamic resource allocation (ALIP-DRA) algorithm is designed to solve the optimal allocation scheme in the considered scenario.

[0045] This application proposes an LLM-driven joint optimization framework based on large language models, edge computing, dynamic resource allocation, and deep reinforcement learning, and applies it to time-varying industrial Internet scenarios to achieve dynamic resource allocation solutions with automated decision-making. Specifically, this application: 1) combines the natural language understanding and generation capabilities of LLM with the policy exploration capabilities of DRL; 2) considering the impact of frequent resource reallocation caused by the movement of mobile devices, a reallocation decision variable is proposed to guide edge nodes to reallocate resources; 3) based on the above scenarios, deep reinforcement learning is introduced to solve the solution.

[0046] Among them, the collaborative optimization (LCOP) framework proposed in this application is as follows Figure 1A As shown:

[0047] Goal: Minimizing factory production cost with limited resources.

[0048] Step 1: Optimization suggestion: Collect relevant data, such as factory production plan and factory production status information, clean and normalize them, and fine-tune the general LLM to adapt it to the characteristics and needs of industrial scenarios. The standard input format is {instruction: plan, information}. The instruction represents the input prompt and represents the decision-making direction of the LLM, which can be cost minimization, equipment status prediction, safety risk warning, troubleshooting, etc. LLM provides corresponding output (Output) based on the input, such as optimization goals (Optimization goals). In the scenario considered in this application, the instruction is assumed to be the minimization of resource consumption (Costminization) in the production process, and the output is the joint optimization of delay (Delay) and energy consumption (Energy consumption).

[0049] Step 2: Data Prediction: Based on the LLM output, use LSTM to predict and integrate the historical data of delay and energy consumption to generate the predicted value (X Pre ), and compared with the actual value (X obs ) is analyzed (Evaluate), with the error representing the difference between the data and directly affecting the threshold of reallocating the decision variables, thereby affecting the action strategy of the DRL agent, where the error can be the root mean square error (RMSE).

[0050] Step 3: Agent action: The agent executes the adaptive language-adaptive language PPO dynamic resource allocation (ALIP-DRA) algorithm to explore the optimal allocation strategy.

[0051] Based on the reallocation decision (ReallocationDecision), the optimization goal (Optimizationgoal) under the influence of constraints (Constraints) is determined, where the constraints include delay constraints (DelayConstraints), energy constraints (EnergyConstraints) and bandwidth limitation constraints (BandwidthConstraint), and the optimization goal is to minimize system resource consumption (Minimizingsystemcost).

[0052] An embodiment of the present application provides a dynamic resource allocation method for industrial Internet scenarios. Taking into account the existence of mobile production equipment with time-varying geographical locations in industrial Internet scenarios, the total latency and total energy consumption of the scenario are analyzed, and the total latency and total energy consumption are processed through a resource consumption algorithm to obtain the actual total resource consumption. The error between the predicted total resource energy consumption and the actual total resource energy consumption is then used to guide the target edge server whether to perform resource reallocation within the communication range. Based on this, the proximal strategy optimization algorithm is used to adaptively solve the optimal resource allocation scheme in the considered scenario as the target resource allocation strategy, and resources are allocated according to the target resource allocation strategy. This can meet the changes in production demand in the industrial Internet scenario while adaptively optimizing the resource allocation strategy to improve the overall efficiency and reliability of the system.

[0053] The method of this embodiment is applied to a dynamic resource allocation system, the system comprising a plurality of edge servers, any edge server among the plurality of edge servers being used as a target edge server, the target edge server being respectively connected to at least one fixed-position production device and at least one mobile-position production device in communication;

[0054] Figure 1B As shown in the figure, a three-layer model of a smart factory for LCOP deployment corresponding to the system is shown, which includes a strategy & optimization (SO) layer, an intelligent processing (IP) layer, and a perception layer. The fine-tuned LLM is deployed in the SO layer to provide optimization suggestions for the lower layer. Multiple edge servers ES are located in the IP layer to execute the DRL algorithm, and the agent takes actions based on the suggestions provided by the upper layer according to the factory status information. The perception layer contains multiple production equipment IPDs.

[0055] This application defines the IPD of production equipment with fixed geographical location (i.e., fixed location production equipment) as F-IPD, the total number of which is M, and the set M = {fIPD1, fIPD2, ..., fIPD i , ..., fIPD M}. However, in actual factories, not all IPDs are located in fixed positions. There are mobile IPDs (i.e., mobile production equipment), i.e., M-IPDs, which need to move within the region to complete production tasks, represented by the variable mIPD. IPDs exchange data with ESs (edge ​​servers), the number of ESs is N, and the set N = {ES1, ES2, ..., Es i , ..., ES N Each edge server ES has a certain communication range and can communicate with the IPDs within its coverage. i , the set of F-IPDs in its coverage area is Easy to know The time slot model {1, 2, ..., t, ..., T} is used to describe a complete production process in the industrial Internet scenario. Fixed-location production equipment and the mobile location production device mIPD is uploaded to the target edge server ES at time slot t i The data volumes are and Since the amount of data transmitted in the downlink is usually small, only the uplink from the production device IPD to the edge server ES is considered.

[0056] Among them, the production equipment IPDs and edge servers ESs are modeled using a two-dimensional coordinate system, in which the fixed position production equipment Mobile location production device mIPD and target edge server ES i The coordinates of are expressed as and (x i ,y i ).

[0057] like Figure 2 As shown, the method includes:

[0058] Step 201, determine the total delay corresponding to the target edge server in the industrial Internet scenario, and determine the total energy consumption corresponding to the target edge server in the industrial Internet scenario.

[0059] In this step, the target edge server ES in the industrial Internet scenario i There are fixed production equipment within the coverage area And at time slot t, the mobile location production device mIPD enters the target edge server ES i coverage and communicate with it.

[0060] Taking into account the existence of mobile production equipment with time-varying geographical locations in industrial Internet scenarios, the total latency and total energy consumption of this scenario are analyzed as a basis for subsequently determining the actual total resource consumption.

[0061] Step 202: Process the total delay and the total energy consumption through a resource consumption algorithm to obtain an actual total resource consumption.

[0062] In this step, the total delay and total energy consumption are comprehensively considered, and the speed and accuracy of obtaining the actual total resource consumption can be guaranteed through the resource consumption algorithm.

[0063] Step 203, obtain the historical delay and historical energy consumption corresponding to the target edge server, obtain the predicted total delay and the predicted total energy consumption based on the historical delay and the historical energy consumption through a pre-trained prediction model, and process the predicted total delay and the predicted total energy consumption through a resource consumption algorithm to obtain the predicted total resource consumption.

[0064] In this step, the prediction model introduces the LSTM network. Different from the traditional neural network, the LSTM network uses memory blocks and gate mechanisms to maintain the internal state of the network and explore the internal abstract features and underlying structure of the data to achieve powerful prediction capabilities for time series.

[0065] It can map the historical sequence x to the predicted sequence y = (y1, y2, ..., y Tpre) :

[0066] τ t =σ(W τ ·[h t-1 , x t ]+b τ );

[0067]

[0068] f gt =σ(W f ·[h t-1 , x t ]+b f );

[0069]

[0070] e t =σ(W e ·[hx -1 , x t ]+b e );

[0071] h t =e t ⊙tanh(C t);

[0072] y t =φ(W y h t +b y ).

[0073] where τ, C, fg, and e represent the input gate, cell activation, forging gate, and output gate vectors, respectively. h t and t Represent the candidate state, hidden layer state and final output respectively. τ , W f , W c , W e and W y represents the weight matrix, b τ 、b f 、b c 、b e and b y is the corresponding bias vector. σ(·) is the Sigmoid function, ⊙ gives the element product of the vector, and φ is the network output activation function.

[0074] Use LSTM to delay the two subsequences by T all，t and energy consumption E all，t Establish a prediction model to obtain the predicted total delay and predict total energy consumption It can capture the changing patterns of data more accurately. Finally, the total delay is predicted by comprehensive consideration. and predict total energy consumption The resource consumption algorithm can ensure the predicted total resource consumption speed and accuracy.

[0075] Step 204: determine the error between the actual total resource consumption and the predicted total resource consumption, and determine whether to reallocate resources on the target edge server based on the error to obtain a determination result.

[0076] In this step, the gap between the actual total resource consumption and the predicted total resource consumption is evaluated by a root mean square error function to guide the target edge server whether to perform resource reallocation within the communication range.

[0077] Step 205, based on the determination result, the actual total resource consumption is optimized by a proximal strategy optimization algorithm to obtain a target resource allocation strategy, and resources are allocated to the fixed-location production equipment and the mobile-location production equipment that communicate with the target edge server according to the target resource allocation strategy.

[0078] In this step, different allocation schemes have different impacts on system costs. The optimal resource allocation scheme is obtained under the constraints of bandwidth resources, communication delay, etc., to achieve a balance between delay and energy consumption.

[0079] This application establishes an optimization problem that minimizes the actual total resource consumption. t ,Right now:

[0080]

[0081] The constraints corresponding to this optimization problem must be met as follows:

[0082]

[0083] in, represents the bandwidth allocation scheme (i.e., the target resource allocation strategy). C1 represents the maximum delay constraint. Constraint C2 indicates that the target edge server ES i With limited allocatable bandwidth B i In addition, only when the mobile location production device mIPD is connected to the target edge server ES i Bandwidth corresponding to mobile production equipment during communication Constraint C3 ensures that and mIPD to allocate bandwidth. Indicates the bandwidth corresponding to fixed-location production equipment. Used to indicate whether to perform resource reallocation.

[0084] Since the state of the system changes over time, the optimization problem of minimizing the actual total resource consumption is t It is expressed as a Markov decision process (MDP). The state transition probability matrix of MDP is also difficult to obtain. However, model-free reinforcement learning algorithms can obtain suboptimal solutions without any prior knowledge.

[0085] The Proximal Policy Optimization (PPO) algorithm is an emerging Policy Gradient (PG) algorithm. This algorithm designs a new objective function to achieve minimum batch updates, solving the problem that the PG algorithm is sensitive to step size and difficult to determine a reasonable step size. The PPO algorithm originated from the Trust Region Policy Optimization (TRPO) algorithm, but is easier to solve than the TRPO algorithm. Compared with the TRPO algorithm, the PPO algorithm uses a scissors proxy objective instead of a constraint function, which reduces the complexity of the algorithm. The key to reinforcement learning lies in the setting of the state space, action space, and rewards, which is very important for whether the algorithm can quickly converge to the correct result. The process of the PPO algorithm is as follows Figure 1C shown.

[0086] For the optimization problem proposed in this application, the state information of all production equipment IPDs, including geographic location, data transmission volume, etc., is used as the state space of reinforcement learning, and the bandwidth allocation scheme of the target edge server ESs is used as the action space. Therefore, the optimization goal of this application is to minimize the average delay, but reinforcement learning generally maximizes the reward, so the complex value of the average delay is used as the reward, that is:

[0087]

[0088] Through the above scheme, taking into account the existence of mobile production equipment with time-varying geographical locations in industrial Internet scenarios, the total delay and total energy consumption are analyzed for the scenario, and the resource consumption algorithm is used to process the total delay and total energy consumption to obtain the actual total resource consumption. The error between the predicted total resource energy consumption and the actual total resource energy consumption is then used to guide the target edge server whether to perform resource reallocation within the communication range. Based on this, the proximal strategy optimization algorithm is used to adaptively solve the optimal resource allocation scheme in the considered scenario as the target resource allocation strategy, and resources are allocated according to the target resource allocation strategy. This can meet the changes in production demand in the industrial Internet scenario while adaptively optimizing the resource allocation strategy to improve the overall efficiency and reliability of the system.

[0089] In some embodiments, the system further comprises a policy optimization layer.

[0090] In step 201, determining the total delay corresponding to the target edge server in the industrial Internet scenario includes:

[0091] Step A1, obtaining the transmission power of the mobile location production device communicating with the target edge server The Gaussian noise power N0 of the mobile location production device, the channel path loss from the mobile location production device to the target edge server Small-scale fading H caused by the mobility of the mobile location production equipment t , the distance from the mobile location production device to the target edge server Signal interference with fixed-location production equipment communicating with the target edge server

[0092] Step A2, based on the Said Said The H t , the N0 and the The first signal-to-noise ratio of the mobile location production equipment is obtained by the following formula

[0093]

[0094] Step A3, obtaining the amount of data uploaded by the mobile location production device to the target edge server in time slot t and the communication bandwidth between the mobile location production device and the target edge server

[0095] Step A4, based on the Said and stated The first delay of the communication between the mobile location production device and the target edge server is obtained by the following formula

[0096]

[0097] Step A5, obtaining the transmission power of the fixed location production equipment communicating with the target edge server The Gaussian noise power N0 of the fixed-location production equipment, the channel path loss PL (d ij，i ), the distance d from the fixed location production equipment to the target edge server ij，i Signal interference with mobile location production equipment communicating with the target edge server

[0098] Step A6, based on the The d ij，i , the PL (d ij，j ), said N0 and said The second signal-to-noise ratio of the fixed position production equipment is obtained by the following formula

[0099]

[0100] Step A7, obtaining the amount of data uploaded by the fixed location production equipment to the target edge server in time slot t and the communication bandwidth between the fixed location production equipment and the target edge server

[0101] Step A8, based on the Said and stated The second delay for the fixed-position production device to communicate with the target edge server is obtained by the following formula

[0102]

[0103] Step A9: Obtain the amount of data transmitted by the target edge server and the wired link transmission rate R between the target edge server and the policy optimization layer w .

[0104] Step A10, based on the and the R w The third delay for the target edge server to communicate with the policy optimization layer is obtained by the following formula:

[0105]

[0106] Step A11, obtaining the number of CPU cycles c required for processing the amount of data transmitted by all the target edge servers n，t , and the computing power f of the strategy optimization layer SO .

[0107] Step A12, based on the c n，t and the f SO The fourth time delay T calculated by the strategy optimization layer is obtained by the following formula: SO，t：

[0108]

[0109] Step A13, based on the Said and the T SO，t The total delay T is obtained by the following formula all，t：

[0110]

[0111] In the above scheme, the uplink transmission delay (i.e., the first delay) of the mobile location production device M-IPD is:

[0112] The signal to noise ratio (ie, the first signal to noise ratio) (Signal to Noise Ratio, SNR) at the mobile location production device mIPD can be given by the following formula:

[0113]

[0114] Among them, the distance from the mobile location production equipment to the target edge server It can be obtained by:

[0115]

[0116] Mobile location production device mIPD and target edge server ES i The coordinates of are expressed as and (x i ,y i ).

[0117] In addition, the channel path loss from the mobile location production device to the target edge server It can be obtained by:

[0118]

[0119] Among them, PL(d) is a function of d and can be calculated as follows:

[0120]

[0121] Among them, f c is the carrier center frequency, d0 represents the reference distance, and c is the speed of light, which is equal to 3×108m / s. loss is the distance correlation index, X σ It means that shadow fading follows a normal distribution with a standard deviation of σ.

[0122] Uplink transmission delay (i.e. second delay) of fixed-location production equipment F-IPDs:

[0123] Target edge server ES i The signal to noise ratio (SNR) at can be given by the following formula:

[0124]

[0125] Among them, the distance d from the fixed location production equipment to the target edge serverij，i It can be obtained by:

[0126]

[0127] Fixed position production equipment and the target edge server ES i The coordinates of ij，i ,y ij，i ) and (x i ,y i ).

[0128] In addition, the channel path loss PL (d ij，i ) can be obtained as follows:

[0129]

[0130] Among them, PL(d) is a function of d and can be calculated as follows:

[0131]

[0132] Among them, f c is the carrier center frequency, d0 represents the reference distance, and c is the speed of light, which is equal to 3×108m / s. loss is the distance correlation index, X σ It means that shadow fading follows a normal distribution with a standard deviation of σ.

[0133] The communication delay between the target edge server ES and the policy optimization (SO) layer (i.e., the third delay) is:

[0134] At this stage, the target edge server ES i Upload the collected key information of IPDs of all production equipment in the coverage area to the SO layer. The transmission delay can be calculated as:

[0135]

[0136] SO layer calculation delay (ie, the fourth delay):

[0137] The computational delay of the SO layer processing the data uploaded by the target edge server ES is given by:

[0138]

[0139] based on and T SO，t The total delay T can be quickly obtained by the following formula all，t :

[0140]

[0141] In some embodiments, the system further comprises a policy optimization layer.

[0142] In step 201, determining the total energy consumption corresponding to the target edge server in the industrial Internet scenario includes:

[0143] Step B1, obtaining the transmission power of the mobile location production device communicating with the target edge server and a first delay for the mobile location production device to communicate with the target edge server

[0144] Step B2, based on the and stated The first energy consumption of the fixed position production equipment data upload is determined by the following formula

[0145]

[0146] Step B3, obtaining the transmission power of the fixed location production equipment communicating with the target edge server and a second delay for the fixed location production device to communicate with the target edge server

[0147] Step B4, based on the and stated The second energy consumption of the fixed position production equipment data upload is determined by the following formula

[0148]

[0149] Step B5: Obtain the transmission power for the target edge server to communicate with the policy optimization layer and a third delay for the target edge server to communicate with the policy optimization layer

[0150] Step B6, based on the and stated The third energy consumption of data upload to the target edge server is determined by the following formula:

[0151]

[0152] Step B7, obtaining the energy consumed by the target edge server in each CPU cycle and the number of CPU cycles required for each resource reallocation of the target edge server

[0153] Step B8, based on the and stated The fourth energy consumption E of the target edge server for resource reallocation is determined by the following formula: re，t :

[0154]

[0155] Step B9, based on the Said Said and the E re，t The total energy consumption E is determined by the following formula all，t :

[0156]

[0157] in, Indicates whether the target edge server needs to reallocate resources in time slot t. Resource reallocation is performed when No resource reallocation is performed.

[0158] In the above scheme, the energy consumption during data exchange (including the first energy consumption, the second energy consumption and the third energy consumption) is:

[0159] Fixed position production equipment The energy consumption of data upload (i.e. the second energy consumption) is given by the following formula:

[0160]

[0161] Similarly, the mobile location production device mIPD and the target edge server ES can be obtained. i The upload energy consumption is (i.e. the first energy consumption) and (i.e. the third energy consumption).

[0162] Calculate consumption:

[0163] make (in J / Gcycle) represents the energy consumed per CPU cycle, calculated at the SO level The energy consumption is as follows:

[0164]

[0165] in, (J / Gcycle) indicates the target edge server ES i The energy consumed in each CPU cycle of the target edge server ES iThe number of CPU cycles required for each resource reallocation is

[0166] Energy consumption during resource reconfiguration (i.e., the fourth energy consumption):

[0167] Each time the edge server ES reallocates resources, computing energy consumption is generated, which can be calculated by the following formula:

[0168]

[0169] based on and E re，t The total energy consumption E can be quickly determined by the following formula: all，t :

[0170]

[0171] In some embodiments, step 202 includes:

[0172] Based on the total delay T all，t and the total energy consumption E all，t The actual total resource consumption is determined by the following formula: t :

[0173] O t =w1·A·T all，t+ w2 · B.E all，t

[0174] Among them, w1 and w2 are preset weighted parameters corresponding to the resource consumption of delay and energy consumption that satisfy w1+w2=1, w1∈(0,1), w2∈(0,1), A and B are preset values ​​that normalize the delay and energy consumption units to resource consumption units.

[0175] In the above scheme, by comprehensively considering the total delay T all，t and total energy consumption E all，t , and normalizing both to the value of resource consumption units can improve the actual total resource consumption O t The accuracy of the prediction can also facilitate the subsequent gap analysis with the predicted total resource consumption.

[0176] In some embodiments, in step 203, the processing based on the predicted total delay and the predicted total energy consumption through a resource consumption algorithm to obtain the predicted total resource consumption includes:

[0177] Based on the predicted total delay and the predicted total energy consumption The predicted total resource consumption is determined by the following formula

[0178]

[0179] Among them, w1 and w2 are preset weighted parameters corresponding to the resource consumption of delay and energy consumption that satisfy w1+w2=1, w1∈(0,1), w2∈(0,1), A and B are preset values ​​that normalize the delay and energy consumption units to resource consumption units.

[0180] In the above scheme, the total delay is predicted by comprehensive consideration and predict total energy consumption And normalizing both to the value of resource consumption unit can improve the predicted total resource consumption The accuracy of the data can also facilitate subsequent gap analysis with the actual total resource consumption.

[0181] In some embodiments, in step 204, determining the error between the actual total resource consumption and the predicted total resource consumption includes:

[0182] Based on the actual total resource consumption t and the predicted total resource consumption The error RMSE is determined by the following formula:

[0183]

[0184] Among them, T represents all time slots of the entire production process corresponding to the industrial Internet scenario, and t represents time slot t.

[0185] In the above scheme, the error of this application is preferably the root mean square error, which can effectively measure the total resource consumption of the prediction The actual total resource consumption O t This sensitivity makes RMSE more applicable in application scenarios where large errors need to be strictly controlled.

[0186] In some embodiments, in step 204, determining whether the target edge server performs resource reallocation based on the error to obtain a determination result includes:

[0187] Step C1, obtaining the location of the target edge server and the location of the mobile location production device communicating with the target edge server

[0188] Step C2, based on the and stated The distance d between the target edge server and the mobile location production equipment is determined by the following formula Δ :

[0189]

[0190] Step C3, obtaining the communication bandwidth between the mobile location production device and the target edge server and the time interval Δτ.

[0191] Step C4, based on the The change in the communication bandwidth occupancy time within the time interval Δτ is determined by the following formula: Δ :

[0192]

[0193] Step C5, based on the d Δ and the φ Δ The resource reallocation variable Γ(φ) is determined by the following formula Δ , d Δ ):

[0194] Γ(φ Δ , d Δ )=log2[(1+arctanφ Δ )(1+arctan d Δ )].

[0195] Step C6, based on the Γ(φ Δ , d Δ ) and the error RMSE determine whether the target edge server performs resource reallocation through the following formula to obtain a determination result:

[0196]

[0197] Among them, Γ0 represents the preset decision threshold, Indicates the result of determination. Resource reallocation is performed when No resource reallocation is performed.

[0198] In the above scheme, an example of releasing and allocating bandwidth due to the movement of the mobile location production device mIPD is as follows: Figure 1D As shown, it is necessary to reallocate bandwidth within the coverage of the target edge server ES1 and the target edge server ES2 to minimize the O t .

[0199] The reallocation of bandwidth resources reduces the system latency, but it increases the system energy consumption. Therefore, a resource reallocation variable Γ(φ Δ , d Δ ) to guide the target edge server ESi Whether the allocation plan needs to be adjusted. Δ , d Δ ) can be expressed as:

[0200] Γ(φ Δ , d Δ )=log2[(1+arctanφ Δ )(1+arctand Δ )];

[0201] Among them, due to d Δ and φ Δ The minimum, maximum and distribution function of are unknown and unstable, so the inverse tangent function is selected as the normalization function.

[0202] merge and Γ(φ Δ , d Δ )=log2[(1+arctanφ Δ )(1+arctan d Δ )], we can get the following redistribution decision criterion:

[0203]

[0204] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0205] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0206] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a dynamic resource allocation device for industrial Internet scenarios.

[0207] refer to Figure 3, the dynamic resource allocation device for industrial Internet scenarios, the device is arranged in a dynamic resource allocation system, the system includes multiple edge servers, any edge server among the multiple edge servers is used as a target edge server, and the target edge server is respectively connected to at least one fixed position production equipment and at least one mobile position production equipment in communication; the device includes:

[0208] The determination module 301 is configured to determine the total delay corresponding to the target edge server in the industrial Internet scenario, and determine the total energy consumption corresponding to the target edge server in the industrial Internet scenario;

[0209] The resource consumption processing module 302 is configured to process the total delay and the total energy consumption through a resource consumption algorithm to obtain an actual total resource consumption;

[0210] The prediction module 303 is configured to obtain the historical delay and the historical energy consumption corresponding to the target edge server, obtain the predicted total delay and the predicted total energy consumption according to the historical delay and the historical energy consumption through a pre-trained prediction model, and process the predicted total delay and the predicted total energy consumption through a resource consumption algorithm to obtain the predicted total resource consumption;

[0211] A reallocation determination module 304 is configured to determine an error between the actual total resource consumption and the predicted total resource consumption, and determine whether to perform resource reallocation on the target edge server based on the error to obtain a determination result;

[0212] The optimization module 305 is configured to optimize the actual total resource consumption through a proximal strategy optimization algorithm based on the determination result, obtain a target resource allocation strategy, and allocate resources to the fixed-location production equipment and the mobile-location production equipment that communicate with the target edge server according to the target resource allocation strategy.

[0213] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0214] The device of the above-mentioned embodiment is used to implement the corresponding dynamic resource allocation method for industrial Internet scenarios in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0215] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the dynamic resource allocation method for the industrial Internet scenario described in any of the above embodiments is implemented.

[0216] Figure 4 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 401, a memory 402, an input / output interface 403, a communication interface 404, and a bus 405. The processor 401, the memory 402, the input / output interface 403, and the communication interface 404 are connected to each other in communication within the device through the bus 405.

[0217] The processor 401 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0218] The memory 402 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 402 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 402 and called and executed by the processor 401.

[0219] The input / output interface 403 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0220] The communication interface 404 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0221] The bus 405 comprises a pathway for transmitting information between the various components of the device (eg, the processor 401 , the memory 402 , the input / output interface 403 , and the communication interface 404 ).

[0222] It should be noted that, although the above device only shows the processor 401, the memory 402, the input / output interface 403, the communication interface 404 and the bus 405, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0223] The electronic device of the above-mentioned embodiment is used to implement the corresponding dynamic resource allocation method for industrial Internet scenarios in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0224] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the dynamic resource allocation method for industrial Internet scenarios as described in any of the above embodiments.

[0225] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0226] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the dynamic resource allocation method for industrial Internet scenarios as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0227] A person skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0228] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0229] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0230] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the protection scope of the present application.

Claims

1. A dynamic resource allocation method for industrial Internet scenarios, characterized in that: Applied to a dynamic resource allocation system, the system includes a plurality of edge servers, any edge server among the plurality of edge servers is used as a target edge server, and the target edge server is respectively connected to at least one fixed-position production device and at least one mobile-position production device in communication; the method includes: Determine the total delay corresponding to the target edge server in the industrial Internet scenario, and determine the total energy consumption corresponding to the target edge server in the industrial Internet scenario; Based on the total delay and the total energy consumption, a resource consumption algorithm is used to process the total delay and the total energy consumption to obtain an actual total resource consumption; Obtaining the historical delay and historical energy consumption corresponding to the target edge server, obtaining the predicted total delay and the predicted total energy consumption through a pre-trained prediction model according to the historical delay and the historical energy consumption, and processing the predicted total delay and the predicted total energy consumption through a resource consumption algorithm to obtain the predicted total resource consumption; Determine an error between the actual total resource consumption and the predicted total resource consumption, and determine whether to reallocate resources on the target edge server based on the error to obtain a determination result; Based on the determination result, the actual total resource consumption is optimized by a proximal strategy optimization algorithm to obtain a target resource allocation strategy, and resources are allocated to fixed-location production equipment and mobile-location production equipment that communicate with the target edge server according to the target resource allocation strategy.

2. The method according to claim 1, characterized in that The system also includes a strategy optimization layer; The determining of the total delay corresponding to the target edge server in the industrial Internet scenario includes: Obtaining the transmission power of the mobile location production device communicating with the target edge server The Gaussian noise power N0 of the mobile location production device, the channel path loss from the mobile location production device to the target edge server Small-scale fading H caused by the mobility of the mobile location production equipment t , the distance from the mobile location production device to the target edge server Signal interference with fixed-location production equipment communicating with the target edge server Based on the Said Said The H t , the N0 and the The first signal-to-noise ratio of the mobile location production equipment is obtained by the following formula Obtain the amount of data uploaded by the mobile location production device to the target edge server in time slot t and the communication bandwidth between the mobile location production device and the target edge server Based on the Said and stated The first time delay T for the mobile location production device to communicate with the target edge server is obtained by the following formula t m，i : Obtain the transmission power of the fixed-location production equipment that communicates with the target edge server The Gaussian noise power N0 of the fixed-location production equipment, the channel path loss PL (d ij，i ), the distance d from the fixed location production equipment to the target edge server ij，i Signal interference with the mobile location production device communicating with the target edge server Based on the The d ij，i , the PL (d ij，i ), said N0 and said The second signal-to-noise ratio of the fixed position production equipment is obtained by the following formula Obtain the amount of data uploaded by the fixed location production device to the target edge server in time slot t and the communication bandwidth between the fixed location production equipment and the target edge server Based on the Said and stated The second delay T for the communication between the fixed location production equipment and the target edge server is obtained by the following formula t ij，i : Get the amount of data transmitted by the target edge server and the wired link transmission rate R between the target edge server and the policy optimization layer w ; Based on the and the R w The third delay for the target edge server to communicate with the policy optimization layer is obtained by the following formula: Get the number of CPU cycles c required to process the amount of data transmitted by all the target edge servers n，t , and the computing power f of the strategy optimization layer SO ; Based on the c n，t and the f SO The fourth time delay T calculated by the strategy optimization layer is obtained by the following formula: SO，t : Based on the T t m，i , the T t ij，i , and the T SO，t The total delay T is obtained by the following formula all，t :

3. The method according to claim 1, characterized in that The system also includes a strategy optimization layer; The determining of the total energy consumption corresponding to the target edge server in the industrial Internet scenario includes: Obtaining the transmission power of the mobile location production device communicating with the target edge server and a first delay T for the mobile location production device to communicate with the target edge server min i ; Based on the and the T t m，i The first energy consumption of the fixed position production equipment data upload is determined by the following formula Obtain the transmission power of the fixed-location production equipment that communicates with the target edge server and a second delay T for the fixed location production device to communicate with the target edge server t ij，i ; Based on the and the T t ij，t The second energy consumption of the fixed position production equipment data upload is determined by the following formula Obtain the transmission power of the target edge server to communicate with the policy optimization layer and a third delay for the target edge server to communicate with the policy optimization layer Based on the and stated The third energy consumption of data upload to the target edge server is determined by the following formula: Get the energy consumed by the target edge server in each CPU cycle and the number of CPU cycles required for each resource reallocation of the target edge server Based on the and stated The fourth energy consumption E of the target edge server for resource reallocation is determined by the following formula: re，t : Based on the Said Said and the E re，t The total energy consumption E is determined by the following formula all，t : in, Indicates whether the target edge server needs to reallocate resources in time slot t. Resource reallocation is performed when No resource reallocation is performed.

4. The method according to claim 1, characterized in that The processing based on the total delay and the total energy consumption by a resource consumption algorithm to obtain the actual total resource consumption includes: Based on the total delay T all，t and the total energy consumption E all，t The actual total resource consumption is determined by the following formula: t : O t =w1·A·T all，t +w2·B·E all,t Among them, w1 and w2 are preset weighted parameters corresponding to the resource consumption of delay and energy consumption that satisfy w1+w2=1, w1∈(0,1), w2∈(0,1), A and B are preset values ​​that normalize the delay and energy consumption units to resource consumption units.

5. The method according to claim 1, characterized in that The processing based on the predicted total delay and the predicted total energy consumption by a resource consumption algorithm to obtain the predicted total resource consumption includes: Based on the predicted total delay and the predicted total energy consumption The predicted total resource consumption is determined by the following formula Among them, w1 and w2 are preset weighted parameters corresponding to the resource consumption of delay and energy consumption that satisfy w1+w2=1, w1∈(0,1), w2∈(0,1), A and B are preset values ​​that normalize the delay and energy consumption units to resource consumption units.

6. The method according to claim 1, characterized in that The determining an error between the actual total resource consumption and the predicted total resource consumption includes: Based on the actual total resource consumption t and the predicted total resource consumption The error RMSE is determined by the following formula: Among them, T represents all time slots of the entire production process corresponding to the industrial Internet scenario, and t represents time slot t.

7. The method according to claim 1, characterized in that The determining whether to reallocate resources on the target edge server based on the error to obtain a determination result includes: Get the location of the target edge server and the location of the mobile location production device communicating with the target edge server Based on the and stated The distance d between the target edge server and the mobile location production equipment is determined by the following formula Δ : Obtaining the communication bandwidth between the mobile location production device and the target edge server and the time interval Δτ; Based on the The change in the communication bandwidth occupancy time within the time interval Δτ is determined by the following formula: Δ : Based on the d Δ and the φ Δ The resource reallocation variable Γ(φ) is determined by the following formula Δ , d Δ ): Γ(φ Δ ,d Δ )=log2[(1+arctanφ Δ )(1+arctand Δ )]; Based on the Γ(φ Δ , d Δ ) and the error RMSE determine whether the target edge server performs resource reallocation through the following formula to obtain a determination result: Among them, Γ0 represents the preset decision threshold, Indicates the result of determination. Resource reallocation is performed when No resource reallocation is performed.

8. A dynamic resource allocation device for industrial Internet scenarios, characterized in that: The device is arranged in a dynamic resource allocation system, the system comprising a plurality of edge servers, any edge server among the plurality of edge servers is used as a target edge server, the target edge server is respectively connected to at least one fixed position production equipment and at least one mobile position production equipment in communication; the device comprises: A determination module is configured to determine a total delay corresponding to the target edge server in an industrial Internet scenario, and to determine a total energy consumption corresponding to the target edge server in an industrial Internet scenario; A resource consumption processing module, configured to process the total delay and the total energy consumption through a resource consumption algorithm to obtain an actual total resource consumption; A prediction module is configured to obtain a historical delay and a historical energy consumption corresponding to the target edge server, obtain a predicted total delay and a predicted total energy consumption according to the historical delay and the historical energy consumption through a pre-trained prediction model, and process the predicted total delay and the predicted total energy consumption through a resource consumption algorithm to obtain a predicted total resource consumption; a reallocation determination module, configured to determine an error between the actual total resource consumption and the predicted total resource consumption, and determine whether to perform resource reallocation on the target edge server based on the error to obtain a determination result; The optimization module is configured to optimize the actual total resource consumption through a proximal strategy optimization algorithm based on the determination result, obtain a target resource allocation strategy, and allocate resources to the fixed-location production equipment and the mobile-location production equipment that communicate with the target edge server according to the target resource allocation strategy.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images