Charging pile OCPP protocol conversion adaptation method based on intelligent algorithm

Abstract

The invention relates to the technical field of charging pile communication protocols, and discloses a charging pile OCPP protocol conversion adaptation method based on an intelligent algorithm. According to the method, original communication data streams of multi-brand charging piles are collected, and a basic protocol data set containing real-time operation parameters and historical interaction records is obtained through analysis; a heterogeneous protocol instruction set which is issued by the background management system for each charging pile identifier and conforms to different communication specifications is obtained; various protocol fields in the heterogeneous protocol instruction set are input into a pre-trained protocol feature extraction model, a protocol feature vector set is generated, fusion protocol features are obtained through integration of a dynamic weighted fusion mechanism, a corresponding standardized OCPP instruction set and operation type identification thereof are generated in combination with a protocol conversion model library, and the operation type identification of the standardized OCPP instruction set is identified. And a two-way communication adaptive channel between the charging pile and the background system is constructed. According to the method, communication adaptation between multiple brands of charging piles and a background system can be achieved, different protocol differences are coped, and the development requirement for increasing the number and types of the charging piles is met.

Description

Technical Field

[0001] This invention relates to the field of charging pile communication protocol technology, specifically to a charging pile OCPP protocol conversion and adaptation method based on intelligent algorithms. Background Technology

[0002] With the rapid development of the new energy vehicle industry, charging piles, as an important infrastructure, are constantly increasing in number and variety. Currently, there are many charging pile brands on the market, and different brands of charging piles often use their own independent communication protocols, which differ significantly in data format, instruction set, and interaction logic.

[0003] The back-end management system needs to uniformly monitor, schedule, and manage charging piles of different brands. However, due to the inconsistent communication protocols followed by each charging pile, there are many obstacles in communication between the back-end management system and the charging piles. For example, when the back-end management system issues instructions to charging piles of different brands, it is necessary to write an adaptation program separately for each brand's protocol. This not only increases the complexity of system development but also significantly increases the difficulty of system maintenance.

[0004] With the continuous upgrading of charging pile technology, new communication standards and protocols are constantly emerging. Existing adaptation programs struggle to quickly respond to the requirements of new protocols, limiting the system's scalability. Furthermore, the conversion between different protocols often relies on manually written conversion rules, which are prone to omissions or errors, affecting the accuracy and stability of communication. These problems result in inefficient information exchange between charging piles and the backend management system, hindering the large-scale development of charging pile networks and the improvement of intelligent management levels. Summary of the Invention

[0005] The purpose of this invention is to provide a charging pile OCPP protocol conversion and adaptation method based on intelligent algorithms to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, this invention provides a charging pile OCPP protocol conversion and adaptation method based on intelligent algorithms, the method comprising:

[0007] The raw communication data streams of charging piles from multiple brands are collected, and the protocol features of the raw communication data streams are parsed to obtain a basic protocol dataset. The raw communication data streams include real-time operating parameters and historical interaction records of the charging piles.

[0008] For each charging pile identifier in the basic protocol dataset, obtain the heterogeneous protocol instruction set that conforms to different communication specifications issued by the backend management system for that charging pile identifier;

[0009] For each heterogeneous protocol instruction set in the obtained heterogeneous protocol instruction group, the various protocol fields in the heterogeneous protocol instruction set are respectively input into the pre-trained protocol feature extraction model to generate a protocol feature vector set;

[0010] For each protocol feature vector set in the obtained protocol feature vector group, a dynamic weighted fusion mechanism is used to integrate the feature vectors within the protocol feature vector set to generate fused protocol features;

[0011] For each fusion protocol feature in the obtained fusion protocol feature set, the corresponding standardized OCPP instruction set and its operation type identifier are generated by combining the protocol conversion model library and the fusion protocol feature.

[0012] Based on the basic protocol dataset, the protocol conversion model library, the generated standardized OCPP instruction set and its operation type identifier, a bidirectional communication adaptation channel between the charging pile and the backend system is constructed.

[0013] Preferably, the step of parsing the protocol features of the original communication data stream to obtain the basic protocol dataset includes:

[0014] Identify protocol syntax structure features from the original communication data stream;

[0015] Based on the aforementioned protocol syntax and structural features, abnormal data frames are cleaned to generate purified protocol data.

[0016] By using preset protocol integrity verification rules, a subset of the purified protocol data that meets the communication reliability conditions is selected as the basic protocol dataset.

[0017] Preferably, the step of integrating the feature vectors within the protocol feature vector set using a dynamic weighted fusion mechanism to generate fused protocol features includes:

[0018] Construct a main fusion channel based on protocol syntax tree topology analysis and extract logical dependencies between protocol fields;

[0019] Establish an auxiliary fusion channel based on communication timing characteristics and analyze the timestamp distribution pattern of command interaction;

[0020] By calculating the semantic relevance metric of the primary and secondary fusion channels, the fusion weight coefficient of the feature vector is dynamically adjusted.

[0021] Preferably, for each fusion protocol feature in the obtained fusion protocol feature set, generating the corresponding standardized OCPP instruction set and its operation type identifier by combining the protocol conversion model library and the fusion protocol feature includes:

[0022] Obtain the conversion requirement coefficient for each model in the protocol conversion model library;

[0023] The protocol conversion model whose conversion demand coefficient reaches the activation threshold is selected as the core conversion engine;

[0024] The fusion protocol features are input into the core conversion engine, which outputs a primary OCPP instruction set and its operation type identifier.

[0025] The fusion protocol features are input into the auxiliary conversion model group in the protocol conversion model library to generate a secondary OCPP instruction set and its operation type identifier.

[0026] For each instruction in the primary OCPP instruction set, the following verification steps are performed: detect whether there is an instruction in the secondary OCPP instruction set that matches the operation type identifier;

[0027] When a matching instruction is detected, the frequency of this operation type in the secondary OCPP instruction set is counted.

[0028] If the frequency exceeds a preset consensus threshold, the corresponding instruction in the primary OCPP instruction set will be confirmed as a standardized OCPP instruction.

[0029] Preferably, the bidirectional communication adaptation channel between the charging pile and the backend system includes:

[0030] Based on the basic protocol dataset and the protocol conversion model library, generate an intermediate protocol conversion instruction set and its operation type identifier;

[0031] Associate and map the operation type identifiers of the intermediate protocol conversion instruction set with the operation type identifiers of the standardized OCPP instruction group;

[0032] Based on the mapping results, an instruction conversion routing table is established, and configuration parameters for the bidirectional communication adaptation channel are generated.

[0033] Preferably, the generation of the intermediate protocol conversion instruction set includes:

[0034] Calculate the historical call priority of each model in the protocol conversion model library;

[0035] Select protocol conversion models that meet the execution criteria based on historical call priorities as target conversion models;

[0036] The basic protocol dataset is input into the target conversion model to generate an initial intermediate instruction set;

[0037] The basic protocol dataset is input into the candidate conversion model group in the protocol conversion model library to generate a reference intermediate instruction set;

[0038] For each instruction in the initial intermediate instruction set, the following verification steps are performed: verify whether there are instructions with the same operation type in the reference intermediate instruction set;

[0039] When verification exists, all reference intermediate instructions of the same operation type are aggregated to form a verification instruction group;

[0040] If the size of the verification instruction group reaches the reliability threshold, the corresponding instruction in the initial intermediate instruction set is confirmed to be valid.

[0041] Preferably, the method further includes:

[0042] Monitor the real-time data throughput of the bidirectional communication adapter channel;

[0043] When the data throughput exceeds the load threshold, the protocol conversion resource scheduler is activated;

[0044] Based on the output instructions of the protocol conversion resource scheduler, the concurrent processing capability of the bidirectional communication adaptation channel is optimized.

[0045] Preferably, the startup protocol conversion resource scheduler includes:

[0046] Parse the operation type identifier of each instruction in the currently running standardized OCPP instruction set;

[0047] The conversion tasks are clustered and grouped based on the matching degree of the operation type identifier;

[0048] Based on the resource utilization rate of the cluster groups, prioritize the conversion tasks of groups with high resource utilization rates;

[0049] Place conversion tasks for groups with low resource utilization into a delayed processing queue.

[0050] Preferably, optimizing the concurrent processing capability of the bidirectional communication adaptation channel includes:

[0051] Establish a state value assessment function for the protocol transition model;

[0052] When the state value evaluation function is lower than the activity threshold, the computing resources occupied by the corresponding protocol conversion model are released;

[0053] Predict peak resource demand based on historical conversion task load patterns;

[0054] Reserve a computational resource buffer for high-priority protocol conversion models.

[0055] Preferably, releasing the computing resources occupied by the corresponding protocol conversion model includes:

[0056] Identify shared weight modules among protocol conversion models;

[0057] The duplicate weight module is eliminated through a communication feature fingerprint comparison algorithm;

[0058] Only unload the memory space corresponding to the non-shared weight module;

[0059] When the idle time of the shared weight module exceeds the recycling threshold, the distributed memory reclamation mechanism is triggered.

[0060] Compared with the prior art, the beneficial effects of the present invention are:

[0061] By collecting raw communication data streams from charging piles of multiple brands and analyzing their protocol characteristics, a comprehensive understanding of the protocol features of different charging piles can be achieved, providing sufficient foundational information for subsequent protocol conversion. Obtaining heterogeneous protocol instruction sets issued by the backend management system for different charging pile identifiers ensures that the conversion process is closely integrated with actual management needs, guaranteeing that the converted instructions match the actual application scenario.

[0062] A pre-trained protocol feature extraction model is used to process various protocol fields in heterogeneous protocol instruction sets, generating a protocol feature vector set. This model can accurately capture key information in protocol fields, reduce information loss, and improve the accuracy of feature representation. A dynamic weighted fusion mechanism is then used to integrate the feature vectors, generating fused protocol features. This allows for reasonable weighting based on the importance of different features, making the fused features more reflective of the overall characteristics of the protocol and enhancing their representativeness.

[0063] By combining a protocol conversion model library and fusion protocol features to generate corresponding standardized OCPP instruction sets and their operation type identifiers, effective conversion from heterogeneous protocols to standardized protocols is achieved. This eliminates the differences between different protocols, enabling charging piles of different brands to communicate with the backend system using a unified protocol. The constructed bidirectional communication adaptation channel breaks down communication barriers between charging piles and the backend system, enabling efficient and smooth information exchange between the two. This facilitates unified management and scheduling of charging piles from multiple brands by the backend system, improving the collaborative working capability of the entire charging pile network.

[0064] This method eliminates the need for manually writing numerous conversion rules, reducing reliance on human experience and minimizing human error. It also improves the efficiency and flexibility of protocol conversion, enabling rapid adaptation to new communication protocols and standards, and enhancing the system's adaptability and scalability. Attached Figure Description

[0065] Figure 1 This is a schematic diagram illustrating the working principle of the charging pile OCPP protocol conversion and adaptation method based on intelligent algorithms described in this invention.

[0066] Figure 2A flowchart for generating fusion protocol features for a dynamic weighted fusion mechanism;

[0067] Figure 3 A flowchart for the generation and verification of the standardized OCPP instruction set;

[0068] Figure 4 A flowchart for generating and verifying intermediate protocol conversion instruction sets;

[0069] Figure 5 A flowchart for strategies to optimize concurrent processing capabilities. Detailed Implementation

[0070] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0071] Please see Figure 1 This invention provides a charging pile OCPP protocol conversion and adaptation method based on intelligent algorithms, the method comprising:

[0072] The system collects raw communication data streams from charging piles of multiple brands, performs protocol feature parsing on these raw data streams to obtain a basic protocol dataset. The raw communication data streams include real-time operating parameters and historical interaction records of the charging piles. For each charging pile identifier in the basic protocol dataset, it obtains heterogeneous protocol instruction sets conforming to different communication standards issued by the backend management system for that charging pile identifier. For each heterogeneous protocol instruction set in the obtained heterogeneous protocol instruction set, it inputs various protocol fields within the heterogeneous protocol instruction set into a pre-trained protocol feature extraction model to generate a protocol feature vector set. For each protocol feature vector set in the obtained protocol feature vector set, it uses a dynamic weighted fusion mechanism to integrate the feature vectors within the protocol feature vector set to generate a fused protocol feature. For each fused protocol feature in the obtained fused protocol feature set, it combines a protocol conversion model library and the fused protocol feature to generate a corresponding standardized OCPP instruction set and its operation type identifier. Based on the basic protocol dataset, the protocol conversion model library, the generated standardized OCPP instruction set and its operation type identifier, a bidirectional communication adaptation channel between the charging pile and the backend system is constructed.

[0073] Example 1: See Figure 2When parsing the protocol features of the original communication data stream to obtain the basic protocol dataset, the process involves identifying protocol syntax structure features from the original communication data stream. This process includes locating the start and end characters of data frames, field separators, and extracting the data type (e.g., numeric, character, boolean), length constraints, and value ranges of each field. By scanning the original communication data stream frame by frame and comparing it with a preset syntax rule template, the differences between different brands of charging pile protocols in terms of field arrangement order, checksum calculation methods, etc., are determined. Based on the identified protocol syntax structure features, abnormal data frames are cleaned. Specific operations include removing data frames that do not conform to the syntax rules, such as data frames with field lengths exceeding the specified range or data types that do not match the definition; for data frames with missing fields that can be inferred from adjacent valid data frames or historical data, interpolation or pattern matching methods are used for repair, generating cleaned protocol data. By using preset protocol integrity verification rules, a subset of the purified protocol data that meets the communication reliability conditions is selected as the basic protocol dataset. The protocol integrity verification rules include data frame sequence continuity checks, which verify whether the sequence numbers of data frames are continuous and without skipping or duplication during the instruction interaction process; key field integrity checks, which ensure that fields involving key information such as charging pile operating status and instruction execution results are not missing; and check bit verification, which confirms that the data has not been tampered with or damaged during transmission by recalculating the check bits of the data frames and comparing them with the original check bits. Only data that passes all verification rules is included in the basic protocol dataset.

[0074] When using a dynamic weighted fusion mechanism to integrate feature vectors within the protocol feature vector set to generate fused protocol features, a main fusion channel based on protocol syntax tree topology analysis is constructed. First, protocol instructions are parsed into a syntax tree structure, where the root node represents the entire instruction and child nodes represent protocol fields at different levels. By traversing the node relationships of the syntax tree, the logical dependencies between each protocol field are extracted. For example, the "charging start instruction" field requires the existence of the "charging pile number" and "user authentication" fields to be effective, and the "charging power adjustment" field has a numerical correlation with the "current charging current" field. An auxiliary fusion channel based on communication timing characteristics is established to collect information such as the sending timestamp, receiving timestamp, and response timestamp of each instruction. The timestamp distribution pattern of instruction interactions is analyzed, including the sending interval pattern of the same type of instruction, the response delay distribution between different instructions, and the timing characteristics such as the difference in instruction frequency between peak and off-peak periods. The semantic relevance metric of the primary and secondary fusion channels is calculated. This metric is obtained by quantifying the degree of correlation between logical dependencies and temporal patterns. For example, when two protocol fields have a strong logical dependency and frequently appear together temporally, their semantic relevance metric is high; conversely, it is low. The fusion weight coefficients of the feature vectors are dynamically adjusted based on the semantic relevance metric. Feature vectors with high semantic relevance metric values ​​are assigned higher weights and have a greater impact during the integration process. Finally, all feature vectors are weighted and summed according to the adjusted weights to generate a fused protocol feature. This fused protocol feature contains both the logical relationship information between protocol fields and integrates the temporal features of command interactions, thus more comprehensively reflecting the essential characteristics of the protocol.

[0075] Example 2: See Figure 3When parsing the protocol features of the original communication data stream to obtain the basic protocol dataset, the process involves identifying protocol syntax structure features from the original communication data stream. This process requires frame-by-frame parsing of communication data from multiple brands of charging piles, extracting key syntax elements such as start markers, end markers, and field separators from the data frames, and determining the data type of each field. For example, numeric fields may represent parameters such as charging voltage and current, while character fields may identify information such as charging pile numbers and fault codes. The length limits and positional order of each field in the data frame also need to be clearly defined. Based on these identified protocol syntax structure features, abnormal data frames are cleaned. Specifically, data frames with field lengths exceeding the specified range, data types that do not conform to the definition, or missing key separators are judged as abnormal and removed. For data frames with missing fields but whose reasonable values ​​can be inferred from the patterns of preceding and following valid data frames, a filling method based on historical data distribution is used for repair. This process generates cleaned protocol data. By using preset protocol integrity verification rules, a subset of the purified protocol data that meets the communication reliability conditions is selected as the basic protocol dataset. The protocol integrity verification rules include checking the continuity of the data frame sequence, that is, verifying whether the sequence number of the data frame increases sequentially in the order of transmission and without repetition, ensuring the continuity of the command interaction process; checking the integrity of key information fields, such as commands involving core operations such as charging start, stop, and fault alarm must contain complete parameter information; and verifying the integrity of the data, by recalculating the check value of the data frame and comparing it with the original check value to confirm that the data has not been erroneous or tampered with during transmission. Only data that passes all these verifications will be included in the basic protocol dataset.

[0076] When using a dynamic weighted fusion mechanism to integrate feature vectors within the protocol feature vector set to generate fused protocol features, a main fusion channel based on protocol syntax tree topology analysis is constructed. First, each protocol instruction is converted into a syntax tree structure, where the root node represents the entire instruction, and each child node represents a different level of protocol field. By analyzing the parent-child and sibling relationships between nodes in the syntax tree, the logical dependencies between protocol fields are extracted. For example, the value of the "charging mode selection" field directly affects the effective range of the "charging current limit" field, and the status of the "identity authentication result" field determines the validity of the "charging start permission" field. An auxiliary fusion channel based on communication timing characteristics is established, collecting timestamp information such as the sending time, receiving time, and response time of each instruction during the interaction process. The distribution patterns of these timestamps are analyzed, including the frequency of occurrence of the same type of instruction within a unit of time, the distribution of time intervals between different instructions, and the fluctuation range of response time. For example, during peak electricity consumption periods, the sending frequency of charging request instructions increases significantly, while fault instructions are usually accompanied by shorter response times. The semantic relevance metric of the primary and secondary fusion channels is calculated. This metric is derived by comparing the co-occurrence of fields in logical dependencies with the temporal correlation of fields in temporal features. For example, when two fields have a strong logical dependency and frequently appear simultaneously in temporal sequence, their semantic relevance metric is higher. The fusion weight coefficients of the feature vectors are dynamically adjusted based on the semantic relevance metric, assigning greater weight to feature vectors with high semantic relevance metric values, allowing them to play a greater role in the integration process. Finally, all feature vectors are combined according to the adjusted weights to generate a fusion protocol feature. This fusion protocol feature integrates the logical correlation and temporal features of the protocol fields, providing a more comprehensive reflection of the overall characteristics of the protocol.

[0077] Example 3: See Figure 4 When generating the intermediate protocol conversion instruction set, the historical call priority of each model in the protocol conversion model library is calculated. This priority is determined by combining multiple historical performance indicators of the model. Specifically, the number of past calls for each model is collected, the number of successfully completed conversion tasks is counted, the time consumed for each conversion is recorded, and the system resources used during runtime, including memory usage and processor utilization, are monitored. Using this data, a specific algorithm is employed to calculate the historical call priority of each model, thus reflecting the model's overall performance in practical applications. Protocol conversion models whose historical call priority meets the execution criteria are selected as target conversion models. The execution criteria are set based on the system's overall requirements for conversion efficiency and stability; only models that demonstrate high success rates, fast processing speeds, and reasonable resource usage in historical calls are selected as target conversion models.

[0078] The basic protocol dataset is input into the target conversion model. This model incorporates parsing rules and conversion logic for various common protocol formats, enabling preliminary conversion of various instructions within the basic protocol dataset. During conversion, the model identifies protocol type identifiers in the data and calls the corresponding conversion module based on these identifiers. This module performs operations such as format adjustment, unit conversion, and semantic mapping on the parameters in the instructions, converting the original protocol instructions into an intermediate format and generating an initial intermediate instruction set. Simultaneously, the basic protocol dataset is input into a candidate conversion model group within the protocol conversion model library. This group contains models optimized for specific brand charging pile protocols or special application scenarios, which may offer unique advantages in handling certain edge cases or complex protocol structures. Each model in the candidate conversion model group independently converts the basic protocol data, outputting its corresponding intermediate instructions. These instructions collectively form a reference intermediate instruction set.

[0079] For each instruction in the initial intermediate instruction set, it is necessary to verify whether there is an instruction with the same operation type in the reference intermediate instruction set. The operation type is determined by the function code or key fields in the instruction; for example, charging start, parameter query, and fault reporting are all different operation types. When instructions with the same operation type are verified, all these reference intermediate instructions with the same operation type are aggregated together to form a verification instruction group. The instructions in the verification instruction group may differ in parameter details or format, but their core operation functions are consistent. If the size of the verification instruction group reaches the reliability threshold, which is set according to the system's requirements for instruction conversion accuracy and is usually related to the size of the candidate conversion model group, when a sufficient number of candidate models convert instructions with the same operation type, it indicates that the corresponding instructions in the initial intermediate instruction set have consistency and universality in conversion logic, confirming the validity of the instruction. Through this process, each instruction in the initial intermediate instruction set is verified one by one, ultimately forming an intermediate protocol conversion instruction set that has passed validity verification.

[0080] The following formula can be used to calculate the priority of historical calls:

[0081]

[0082] in, Indicates the priority of historical calls. This represents the number of successful transformations in the model's history. This represents the total number of historical calls to the model. This represents the model's average conversion speed (in instructions per second). This represents the model's average memory usage (in MB). This represents the model's average processor utilization (in %). , , These are the weighting coefficients for each indicator, and .

[0083] Example 4: Monitoring the real-time data throughput of the bidirectional communication adaptation channel. Real-time data throughput is achieved by continuously collecting the number of instructions transmitted per unit time and the total number of bytes in data frames within the channel. The collection process covers both the input and output ports of the channel, recording the original protocol instruction traffic entering the channel and the standardized OCPP instruction traffic outputting, while marking the transmission time of each instruction to form a continuous throughput monitoring sequence. When the data throughput exceeds the load threshold, which is set based on the channel's hardware processing capabilities, the computational upper limit of the protocol conversion model, and historical peak traffic, the protocol conversion resource scheduler is activated to dynamically manage the conversion tasks within the channel.

[0084] The system analyzes the operation type identifiers of each instruction in the currently running standardized OCPP instruction group. These identifiers are determined by the function code field in the instruction header; for example, function code "0x01" represents charging parameter query, "0x02" represents charging start control, and "0x03" represents fault status reporting. Each operation type identifier corresponds to an instruction structure and processing logic. For instance, parameter query instructions contain a list of parameter numbers to be queried, while control instructions contain specific operation parameter values. The system clusters conversion tasks based on the matching degree of the operation type identifiers. The matching degree is calculated by comparing the consistency of the function code field and the correlation between the instruction parameters. Conversion tasks with the same function code and high parameter correlation are grouped together. For example, all parameter query instructions targeting the same charging pile are grouped together, while start control instructions for different charging piles are grouped together.

[0085] The tasks are sorted by resource utilization based on clustering grouping. Resource utilization is determined by statistically analyzing the CPU processing time, memory usage, and number of protocol conversion model calls required for each group of tasks. For example, fault status reporting tasks typically have a higher resource utilization than ordinary parameter query tasks because they require processing a large number of status code mappings. Conversion tasks in high resource utilization groups are prioritized for execution, allocating more computing cores and memory space to them and shortening their waiting time in the processing queue. Conversion tasks in low resource utilization groups are placed in a delayed processing queue, which uses a first-in-first-out scheduling strategy, executing them sequentially after the high resource utilization group tasks are processed.

[0086] Based on the output instructions of the protocol conversion resource scheduler, optimize the concurrent processing capability of the bidirectional communication adaptation channel. Specifically, this includes dynamically adjusting the size of the thread pool within the channel, adding dedicated processing threads for high-priority task groups, adjusting the calling order of the protocol conversion model so that high-resource-occupancy groups can use the better-performing model instance first, and setting a threshold for the task buffer queue so that when the length of the low-priority task queue exceeds the threshold, temporary use of backup computing resources for processing is initiated.

[0087]

[0088] Through the above process, the protocol conversion resource scheduler can intelligently schedule tasks based on task type and resource requirements when the channel load is too high, ensuring efficient processing of critical conversion tasks while balancing the overall utilization of system resources and achieving dynamic optimization of the concurrent processing capability of the bidirectional communication adaptation channel.

[0089] Example 5: See Figure 5 When optimizing the concurrent processing capability of the bidirectional communication adaptation channel, a state value evaluation function for the protocol conversion model is established. This function comprehensively considers the model's current conversion efficiency, i.e., the number of protocol conversion tasks completed per unit time; the model's utilization of system resources, including memory usage and processor utilization; and the length of the task queue associated with the model, i.e., the number of tasks waiting for the model to process. Through the comprehensive calculation of these indicators, a quantitative evaluation of the model's current operating state is formed. When the state value evaluation function is lower than the activity threshold, it indicates that the protocol conversion model has low operating efficiency in the current system environment and limited contribution to the overall conversion process. At this time, the computing resources occupied by the model are released, which involves reclaiming the processor computing time allocated to the model, clearing the memory space occupied by the model during runtime, and releasing the occupation of specific protocol conversion interfaces.

[0090] Peak resource demand is predicted based on historical conversion task load patterns. These patterns are derived by analyzing the changes in the number of conversion tasks and resource consumption curves for different time periods and protocol types over a past period. For example, the number of charging-related instruction conversion tasks during weekday morning and evening peak hours is typically significantly higher than at other times, resulting in a corresponding increase in resource demand. Based on these patterns, time series analysis is used to infer the maximum resource demand that may occur within a certain future period, i.e., the peak resource demand.

[0091] A computational resource buffer is reserved for high-priority protocol conversion models. These high-priority models are determined based on the importance of the instruction types they process; for example, models responsible for charging safety parameter conversion and emergency fault instruction handling are designated as high-priority. The computational resource buffer includes dedicated processor cores, independent memory blocks, and prioritized network bandwidth to ensure that these high-priority models receive continuous and sufficient computational support during peak resource demand periods, unaffected by other tasks.

[0092] When releasing computing resources occupied by the corresponding protocol conversion model, the shared weight modules among the protocol conversion models are first identified. These modules are basic algorithm components that multiple models rely on when performing conversion tasks, such as common field parsing modules and data format conversion functions. A communication feature fingerprint comparison algorithm is used to extract features from the weight modules of each model, generating unique feature fingerprints. Duplicate weight modules are identified by comparing fingerprints, and one instance is retained while other duplicate modules are eliminated. Only the memory space corresponding to non-shared weight modules is unloaded. These modules are unique to specific models, and unloading them will not affect the normal operation of other models. When the idle time of a shared weight module exceeds the reclamation threshold (calculated by the difference between the module's last call time and the current time; the reclamation threshold is dynamically adjusted based on the system's memory resource scarcity), a distributed memory reclamation mechanism is triggered, releasing the shared weight module from the memory of all nodes. The reclaimed memory resources are uniformly incorporated into the system resource pool for other modules to apply for.

[0093] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0094] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A charging pile OCPP protocol conversion and adaptation method based on intelligent algorithms, characterized in that, Includes the following steps: The raw communication data streams of charging piles from multiple brands are collected, and the protocol features of the raw communication data streams are parsed to obtain a basic protocol dataset. The raw communication data streams include real-time operating parameters and historical interaction records of the charging piles. For each charging pile identifier in the basic protocol dataset, obtain the heterogeneous protocol instruction set that conforms to different communication specifications issued by the backend management system for that charging pile identifier; For each heterogeneous protocol instruction set in the obtained heterogeneous protocol instruction group, the various protocol fields in the heterogeneous protocol instruction set are respectively input into the pre-trained protocol feature extraction model to generate a protocol feature vector set; For each protocol feature vector set in the obtained protocol feature vector group, a dynamic weighted fusion mechanism is used to integrate the feature vectors within the protocol feature vector set to generate fused protocol features; For each fusion protocol feature in the obtained fusion protocol feature set, the corresponding standardized OCPP instruction set and its operation type identifier are generated by combining the protocol conversion model library and the fusion protocol feature. Based on the basic protocol dataset, the protocol conversion model library, the generated standardized OCPP instruction set and its operation type identifier, a bidirectional communication adaptation channel between the charging pile and the backend system is constructed.

2. The charging pile OCPP protocol conversion and adaptation method based on intelligent algorithm according to claim 1, characterized in that, The process of parsing the protocol features of the original communication data stream to obtain the basic protocol dataset includes: Identify protocol syntax structure features from the original communication data stream; Based on the aforementioned protocol syntax and structural features, abnormal data frames are cleaned to generate purified protocol data. By using preset protocol integrity verification rules, a subset of the purified protocol data that meets the communication reliability conditions is selected as the basic protocol dataset.

3. The charging pile OCPP protocol conversion and adaptation method based on intelligent algorithm according to claim 1, characterized in that, The step of integrating feature vectors within the protocol feature vector set using a dynamic weighted fusion mechanism to generate fused protocol features includes: Construct a main fusion channel based on protocol syntax tree topology analysis and extract logical dependencies between protocol fields; Establish an auxiliary fusion channel based on communication timing characteristics and analyze the timestamp distribution pattern of command interaction; By calculating the semantic relevance metric of the primary and secondary fusion channels, the fusion weight coefficient of the feature vector is dynamically adjusted.

4. The charging pile OCPP protocol conversion and adaptation method based on intelligent algorithm according to claim 3, characterized in that, For each fusion protocol feature in the obtained fusion protocol feature set, the generation of the corresponding standardized OCPP instruction set and its operation type identifier, in conjunction with the protocol conversion model library and the fusion protocol feature, includes: Obtain the conversion requirement coefficient for each model in the protocol conversion model library; The protocol conversion model whose conversion demand coefficient reaches the activation threshold is selected as the core conversion engine; The fusion protocol features are input into the core conversion engine, which outputs a primary OCPP instruction set and its operation type identifier. The fusion protocol features are input into the auxiliary conversion model group in the protocol conversion model library to generate a secondary OCPP instruction set and its operation type identifier. For each instruction in the primary OCPP instruction set, the following verification steps are performed: detect whether there is an instruction in the secondary OCPP instruction set that matches the operation type identifier; When a matching instruction is detected, the frequency of this operation type in the secondary OCPP instruction set is counted. If the frequency exceeds a preset consensus threshold, the corresponding instruction in the primary OCPP instruction set will be confirmed as a standardized OCPP instruction.

5. The charging pile OCPP protocol conversion and adaptation method based on intelligent algorithm according to claim 4, characterized in that, The bidirectional communication adaptation channel between the charging pile and the backend system includes: Based on the basic protocol dataset and the protocol conversion model library, generate an intermediate protocol conversion instruction set and its operation type identifier; Associate and map the operation type identifiers of the intermediate protocol conversion instruction set with the operation type identifiers of the standardized OCPP instruction group; Based on the mapping results, an instruction conversion routing table is established, and configuration parameters for the bidirectional communication adaptation channel are generated.

6. The charging pile OCPP protocol conversion and adaptation method based on intelligent algorithm according to claim 5, characterized in that, The generation of intermediate protocol conversion instruction set includes: Calculate the historical call priority of each model in the protocol conversion model library; Select protocol conversion models that meet the execution criteria based on historical call priorities as target conversion models; The basic protocol dataset is input into the target conversion model to generate an initial intermediate instruction set; The basic protocol dataset is input into the candidate conversion model group in the protocol conversion model library to generate a reference intermediate instruction set; For each instruction in the initial intermediate instruction set, the following verification steps are performed: verify whether there are instructions with the same operation type in the reference intermediate instruction set; When verification exists, all reference intermediate instructions of the same operation type are aggregated to form a verification instruction group; If the size of the verification instruction group reaches the reliability threshold, the corresponding instruction in the initial intermediate instruction set is confirmed to be valid.

7. The charging pile OCPP protocol conversion and adaptation method based on intelligent algorithm according to claim 1, characterized in that, Also includes: Monitor the real-time data throughput of the bidirectional communication adapter channel; When the data throughput exceeds the load threshold, the protocol conversion resource scheduler is activated; Based on the output instructions of the protocol conversion resource scheduler, the concurrent processing capability of the bidirectional communication adaptation channel is optimized.

8. The charging pile OCPP protocol conversion and adaptation method based on intelligent algorithm according to claim 7, characterized in that, The startup protocol conversion resource scheduler includes: Parse the operation type identifier of each instruction in the currently running standardized OCPP instruction set; The conversion tasks are clustered and grouped based on the matching degree of the operation type identifier; Based on the resource utilization rate of the cluster groups, prioritize the conversion tasks of groups with high resource utilization rates; Place conversion tasks for groups with low resource utilization into a delayed processing queue.

9. The charging pile OCPP protocol conversion and adaptation method based on intelligent algorithms according to claim 8, characterized in that, The optimization of the concurrent processing capability of the bidirectional communication adaptation channel includes: Establish a state value assessment function for the protocol transition model; When the state value evaluation function is lower than the activity threshold, the computing resources occupied by the corresponding protocol conversion model are released; Predict peak resource demand based on historical conversion task load patterns; Reserve a computational resource buffer for high-priority protocol conversion models.

10. The charging pile OCPP protocol conversion and adaptation method based on intelligent algorithms according to claim 9, characterized in that, The release of the computing resources occupied by the corresponding protocol conversion model includes: Identify shared weight modules among protocol conversion models; The duplicate weight module is eliminated through a communication feature fingerprint comparison algorithm; Only unload the memory space corresponding to the non-shared weight module; When the idle time of the shared weight module exceeds the recycling threshold, the distributed memory reclamation mechanism is triggered.

Images