Multi-core heterogeneous new energy core configuration optimization method and device

Abstract

The invention discloses a multi-core heterogeneous new energy core configuration optimization method and device. The method comprises the following steps: acquiring multi-core heterogeneous new energy core information; according to the multi-core heterogeneous new energy core information, performing power service adaptation processing to obtain an adaptation result; calculating multi-core heterogeneous chip parameters according to the adaptation result; according to the multi-core heterogeneous chip parameters, constructing a to-be-selected new energy core inner core combination; according to a characteristic index and the to-be-selected new energy core kernel combination, constructing a target new energy core kernel combination; and performing new energy core configuration optimization according to the target new energy core inner core combination. According to the method, the new energy core configuration optimization is realized by calculating the adaptation degree of the new energy core kernel and the power business, the adaptability is improved, and the configuration redundancy is reduced. The method can be widely applied to the technical field of new energy cores.

Description

Technical Field

[0001] The present invention relates to the field of new energy core technology, and in particular to a method and device for optimizing the configuration of a multi-core heterogeneous new energy core. Background Art

[0002] As an embedded customized algorithm core, the new energy core has the characteristics of strong scene adjustment capability and high business processing timeliness, which can effectively reduce the problem of power business execution blocking in the scenario of large-scale access of distributed new energy. However, the new energy core cannot fully demonstrate its advantages based on its own capacity supply characteristics and power business demand characteristics, which increases the risk of safe and stable operation of the new power system. The existing new energy core configuration optimization method mainly relies on the passive adjustment of power business demand within the system, which leads to the configuration of multi-core heterogeneous new energy cores being too redundant and having high configuration redundancy. At the same time, the passive level adjustment still relies too much on the feedback of the scene, and cannot be adapted favorably from the active level, and has low adaptability.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the invention

[0004] The embodiments of the present invention provide a method and device for optimizing the configuration of a multi-core heterogeneous new energy cell, which effectively improves adaptability and reduces configuration redundancy.

[0005] On the one hand, an embodiment of the present invention provides a multi-core heterogeneous new energy core configuration optimization method, comprising the following steps:

[0006] Obtain information about multi-core heterogeneous new energy chips;

[0007] Performing power service adaptation processing according to the multi-core heterogeneous new energy core information to obtain an adaptation result;

[0008] Calculating the multi-core heterogeneous chip parameters according to the adaptation result, wherein the multi-core heterogeneous chip parameters include the total power consumption of the multi-core heterogeneous chip service flow execution, the multi-core heterogeneous chip composition volume, and the multi-core heterogeneous chip price;

[0009] According to the multi-core heterogeneous chip parameters, construct a combination of new energy cores to be selected;

[0010] According to the characteristic indicators and the candidate new energy core combination, a target new energy core combination is constructed, wherein the characteristic indicators include a real-time indicator, a reliability indicator, a flexibility indicator, an expansibility indicator, and an economic indicator;

[0011] The new energy cell configuration is optimized according to the target new energy cell core combination.

[0012] In some embodiments, performing power service adaptation processing according to the multi-core heterogeneous new energy core information to obtain an adaptation result includes:

[0013] Determine the core structure of the new energy core according to the multi-core heterogeneous new energy core information, wherein the core structure of the new energy core includes a central processing unit core, a digital signal processing core, a power-specific algorithm IP core, a field programmable gate array core, and a bus;

[0014] According to the full life cycle stages of power data, the power business is divided to obtain the power business division results. The full life cycle stages of power data include generation and extraction stage, analysis and use stage, evaluation and optimization stage, and storage and standby stage. The power business includes acquisition business, communication business, distributed source and storage topology identification business, operation control business, energy management business, intelligent inspection business, protection business, user demand side response business, power quality business, information security business, low-carbon monitoring business, and data management business;

[0015] According to the new energy core structure and the power service division result, the new energy core is matched with the power service to obtain the adaptation result.

[0016] In some embodiments, calculating the multi-core heterogeneous chip parameters according to the adaptation result includes:

[0017] Calculate the running dynamic power consumption based on the processing instruction length, dynamic execution loss and processor core effective capacitance;

[0018] Calculate the total power consumption of the multi-core heterogeneous chip service flow execution according to the dynamic power consumption of operation, static power consumption of data uploading, static power consumption of data downloading, the number of processors and the number of power services to be executed;

[0019] Calculating the volume of the multi-core heterogeneous chip according to the number of processors, the number of processor cores, the volume of the processor cores and the volume space coefficient;

[0020] The price of the multi-core heterogeneous chip is calculated based on the price cost coefficient, the number of processors, the processor core price cost and the number of processor cores.

[0021] In some embodiments, constructing a new energy core combination to be selected according to the multi-core heterogeneous chip parameters includes:

[0022] Construct power consumption limit constraints based on the power consumption generated by executing power services and the rated power consumption limit of the processor core;

[0023] According to the total power consumption of the multi-core heterogeneous chip business flow and the rated power consumption limit of the new energy core, a total power consumption constraint of the new energy core is constructed;

[0024] According to the time required for waiting state instruction capture, the time required for ready state instruction analysis, the time required for running state instruction analysis, the time required for data upload to the bus and the time required for data download from the bus, the time delay constraint for power business completion time is established;

[0025] According to the data space occupied by the data upload unit instruction and the data space occupied by the data download unit instruction, the bus can be constructed to carry data space constraints;

[0026] Constructing a multi-objective optimization function according to the power consumption limit constraint, the total power consumption constraint of the new energy core, the power service completion time delay constraint, the bus-carryable data space constraint and the multi-core heterogeneous chip parameters;

[0027] According to the multi-objective optimization function, the new energy core combination to be selected is constructed.

[0028] In some embodiments, constructing a target new energy core combination according to the characteristic index and the candidate new energy core combination includes:

[0029] According to the characteristic indicators, a characteristic indicator set is constructed;

[0030] Constructing an important value sequence according to the characteristic indicator set and the combination of the new energy cores to be selected;

[0031] According to the importance value sequence and importance normalization strategy, construct an importance value matrix;

[0032] Calculating the sum of importance values ​​according to the importance value matrix;

[0033] Normalizing the sum of the important values ​​to obtain a normalized value;

[0034] According to the evaluation value distance coefficient, the normalized value is interval mapped to obtain an importance evaluation value;

[0035] The target new energy core combination is constructed according to the importance evaluation value.

[0036] In some embodiments, the calculating the total power consumption of the multi-core heterogeneous chip service flow execution according to the running dynamic power consumption, the data uploading static power consumption, the data downloading static power consumption, the number of processors and the number of power services to be executed includes:

[0037] According to the dynamic power consumption of operation, static power consumption of data upload, static power consumption of data download, the number of processors and the number of power services to be executed, the total power consumption of the multi-core heterogeneous chip service flow execution is calculated by the total power consumption calculation formula of the multi-core heterogeneous chip service flow execution. The total power consumption calculation formula of the multi-core heterogeneous chip service flow execution is:

[0038]

[0039] Where P c is the total power consumption of the multi-core heterogeneous chip service flow execution, p i,j (f) is the dynamic power consumption of the operation, p i,j,up is the static power consumption of data upload, p i,j,do is the static power consumption of data downloading, N is the number of processors, and M is the number of power services.

[0040] In some embodiments, the calculating the volume of the multi-core heterogeneous chip according to the number of processors, the number of processor cores, the volume of the processor cores and the volume space coefficient includes:

[0041] According to the number of processors, the number of processor cores, the volume of the processor cores and the volume space coefficient, the volume of the multi-core heterogeneous chip is calculated by the multi-core heterogeneous chip volume calculation formula, and the multi-core heterogeneous chip volume calculation formula is:

[0042]

[0043] Where V c is the volume of the multi-core heterogeneous chip, N is the number of processors, m is i is the number of processor cores, V i is the volume of the processor core, and σ is the volume space coefficient.

[0044] In some embodiments, the calculating the price of the multi-core heterogeneous chip according to the price cost coefficient, the number of processors, the price cost of the processor cores and the number of processor cores includes:

[0045] The price of the multi-core heterogeneous chip is calculated according to the price cost coefficient, the number of processors, the price cost of the processor core and the number of processor cores by using the multi-core heterogeneous chip price calculation formula. The multi-core heterogeneous chip price calculation formula is:

[0046]

[0047] In the formula, C c is the price of the multi-core heterogeneous chip, λ is the price cost coefficient, N is the number of processors, ω i is the price cost of the processor core, m i is the number of processor cores.

[0048] On the other hand, an embodiment of the present invention provides a multi-core heterogeneous new energy core configuration optimization device, comprising:

[0049] The first module is used to obtain multi-core heterogeneous new energy chip information;

[0050] The second module is used to perform power business adaptation processing according to the multi-core heterogeneous new energy core information to obtain an adaptation result;

[0051] The third module is used to calculate the multi-core heterogeneous chip parameters according to the adaptation result, wherein the multi-core heterogeneous chip parameters include the total power consumption of the multi-core heterogeneous chip business flow execution, the multi-core heterogeneous chip composition volume and the multi-core heterogeneous chip price;

[0052] The fourth module is used to construct a combination of new energy cores to be selected according to the multi-core heterogeneous chip parameters;

[0053] A fifth module is used to construct a target new energy core core combination according to characteristic indicators and the candidate new energy core core combination, wherein the characteristic indicators include a real-time indicator, a reliability indicator, a flexibility indicator, an expansibility indicator, and an economic indicator;

[0054] The sixth module is used to optimize the configuration of the new energy cell according to the target new energy cell core combination.

[0055] In another aspect, an embodiment of the present invention provides a computer device, comprising:

[0056] at least one processor;

[0057] at least one memory for storing at least one program;

[0058] When the at least one program is executed by the at least one processor, the at least one processor implements the described method.

[0059] The beneficial effects of the present invention are as follows:

[0060] The embodiment of the present invention first obtains multi-core heterogeneous new energy core information, and performs power business adaptation processing according to the multi-core heterogeneous new energy core information to obtain adaptation results, and then calculates multi-core heterogeneous chip parameters according to the adaptation results, and constructs a candidate new energy core kernel combination according to the multi-core heterogeneous chip parameters, and then constructs a target new energy core kernel combination according to the characteristic indicators and the candidate new energy core kernel combination, and finally optimizes the new energy core configuration according to the target new energy core kernel combination, so that the new energy core configuration optimization can be achieved by calculating the degree of adaptation between the new energy core kernel and the power business, thereby improving adaptability and reducing configuration redundancy.

[0061] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0063] Figure 1 This is a flow chart of a multi-core heterogeneous new energy core configuration optimization method according to an embodiment of the present invention;

[0064] Figure 2 A schematic diagram of a new energy core structure according to an embodiment of the present invention;

[0065] Figure 3 A schematic diagram of a power service division result according to an embodiment of the present invention;

[0066] Figure 4 A schematic diagram of a power service sequence connection mode division according to an embodiment of the present invention;

[0067] Figure 5 A schematic diagram of the response of different kernel combination solutions to different characteristic indicators according to an embodiment of the present invention;

[0068] Figure 6 A schematic diagram of an overall process of constructing a kernel service matching solution according to an embodiment of the present invention;

[0069] Figure 7 This is a schematic diagram of the structure of a multi-core heterogeneous new energy core configuration optimization device according to an embodiment of the present invention;

[0070] Figure 8 The figure is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0071] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0072] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0073] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0074] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0075] Before describing the embodiments of the present application in detail, some nouns and terms involved in the embodiments of the present application are first described. The nouns and terms involved in the embodiments of the present application are subject to the following explanations.

[0076] New energy core: refers to various chips and batteries used in new energy vehicles, mainly including control chips, computing chips, power chips, communication chips, storage chips, security chips, etc. These chips play a vital role in new energy vehicles, covering all aspects from power systems to vehicle systems and safety systems. The embodiments of the present invention mainly focus on computing chips, such as CPU, DSP, FPGA, etc., which are used to handle complex computing tasks and multimedia interfaces.

[0077] In the related technologies, when traditional industrial-grade general-purpose chips are applied to scenarios where distributed new energy is accessed in large quantities, there are problems such as high power consumption loss, poor scene flexibility and adaptation, and insufficient real-time processing of business. As an embedded customized algorithm core, the new energy chip has the characteristics of strong scene adjustment capability and high business processing timeliness, which can effectively reduce the problem of power business execution blocking in scenarios where distributed new energy is accessed in large quantities. However, the new energy chip is in an emerging stage and cannot fully demonstrate its advantages based on its own capability supply characteristics and power business demand characteristics, which increases the risk of safe and stable operation of the new power system. The configuration of new energy chips under multiple constraints based on its own capability characteristics and power business demand characteristics can effectively deal with such risks. The essence of the stable operation of the power system under the large-scale access of distributed new energy lies in whether the new energy chip can effectively deal with the extensive and complex power business. When there is a large amount of differentiated feature data in the power system, the corresponding power business to be processed also has different feature requirements. If the pertinence and adaptability of the new energy chip cannot form a powerful grip, the power business under the massive differentiated feature data will face execution difficulties or even blocking. With the participation of more distributed new energy grid-connected, new power business expansion, and data mining in the power system in the future, the adaptive optimization configuration of new energy cores faces new challenges. The existing adaptive optimization configuration scheme for new energy cores mainly relies on the passive adjustment of power business needs within the system, that is, iteratively adding or transforming the core of new energy cores according to the characteristic needs of power business to adapt to the needs of different new energy scenarios. Although this process can effectively cope with the complex characteristics of new energy scenarios, this unconstrained solution makes the configuration of multi-core heterogeneous new energy cores too redundant, with high configuration redundancy and lack of future optimization possibilities. In addition, the passive-level adjustments still rely too much on the feedback of the scenarios, and cannot be adapted favorably from the active level, resulting in low adaptability.

[0078] In view of this, the embodiment of the present invention focuses on the advantages of commonly used cores of multi-core heterogeneous new energy cores, summarizes and organizes power services for new energy scenarios, and comprehensively considers the two to perform initial modeling of the core and power service adaptation. The embodiment of the present invention considers the three decision variables of power consumption, volume and core price to optimize the matching of power services and the core composition of multi-core heterogeneous new energy cores. By constructing a multi-objective optimization problem, the core combination of new energy cores is screened. The embodiment of the present invention comprehensively evaluates the characteristic indicators of five dimensions: real-time, reliability, flexibility, scalability and economy, and selects the best core business matching solution for multi-core heterogeneous new energy cores to optimize the configuration of new energy cores.

[0079] A multi-core heterogeneous new energy core configuration optimization method provided in an embodiment of the present application relates to the field of new energy core technology. A multi-core heterogeneous new energy core configuration optimization method provided in an embodiment of the present application can be applied to a terminal, can also be applied to a server, and can also be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or it can be configured as a server cluster or distributed system composed of multiple physical servers, and can also be configured to provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms and other basic cloud computing services. The cloud server, the server can also be a node server in a blockchain network; the software can be an application that implements a multi-core heterogeneous new energy core configuration optimization method, etc., but is not limited to the above forms.

[0080] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0081] The following is a detailed explanation of the embodiments of the present application in conjunction with the accompanying drawings:

[0082] Figure 1 is an optional flow chart of a multi-core heterogeneous new energy core configuration optimization method provided in an embodiment of the present application, Figure 1 The method may include but is not limited to steps S101 to S106.

[0083] Step S101, obtaining multi-core heterogeneous new energy chip information;

[0084] Step S102: Perform power service adaptation processing according to the multi-core heterogeneous new energy core information to obtain an adaptation result;

[0085] Step S103: Calculate the multi-core heterogeneous chip parameters according to the adaptation result, where the multi-core heterogeneous chip parameters include the total power consumption of the multi-core heterogeneous chip service flow execution, the multi-core heterogeneous chip composition volume, and the multi-core heterogeneous chip price;

[0086] Step S104, constructing a combination of new energy cores to be selected according to the multi-core heterogeneous chip parameters;

[0087] Step S105, constructing a target new energy core combination according to characteristic indicators and the new energy core combination to be selected, wherein the characteristic indicators include real-time indicators, reliability indicators, flexibility indicators, scalability indicators and economic indicators;

[0088] Step S106: Optimize the configuration of the new energy core according to the target new energy core core combination.

[0089] Steps S101 to S106 shown in the embodiment of the present application achieve new energy cell configuration optimization, improve adaptability, and reduce configuration redundancy.

[0090] In step S101 of some embodiments, the multi-core heterogeneous new energy core information may be obtained through a new energy core database, or may be obtained through other methods, not limited thereto.

[0091] In some embodiments, in step S102, power service adaptation processing is performed according to the multi-core heterogeneous new energy core information to obtain an adaptation result, which may include but is not limited to the following steps:

[0092] According to the information of multi-core heterogeneous new energy core, determine the core structure of the new energy core, which includes the central processing unit core, digital signal processing core, power-specific algorithm IP core, field programmable gate array core and bus;

[0093] According to the full life cycle stages of power data, the power business is divided to obtain the power business division results. The full life cycle stages of power data include generation and extraction stage, analysis and use stage, evaluation and optimization stage, and storage and standby stage. The power business includes acquisition business, communication business, distributed source and storage topology identification business, operation and control business, energy management business, intelligent inspection business, protection business, user demand side response business, power quality business, information security business, low-carbon monitoring business, and data management business.

[0094] According to the new energy core structure and the power business division results, the new energy core is matched with the power business to obtain the adaptation result.

[0095] In some embodiments, the core structure of the new energy core can be determined based on the multi-core heterogeneous new energy core information, wherein the core structure of the new energy core is as follows: Figure 2As shown, it includes a central processing unit core (CPU core), a digital signal processing core (DSP core), a power-specific algorithm IP core, a field programmable gate array core (FPGA core) and a bus. It can be understood that various types of processor cores communicate using the bus. The CPU core and the DSP core have internal caches, and in the task state, they can use their own caches to form task readiness and waiting. The power-specific algorithm IP core and the FPGA core do not have internal caches, and the task readiness and waiting are completed on the bus. The subsystems in the multi-core heterogeneous new energy core must not only ensure operational independence, but also have large-capacity and high-frequency data interactions with each other. For example, multiple processor cores need to transmit configuration information, status information, recorded data, and commands. The data interaction mechanism between each processor core must not only ensure efficient and convenient data interaction, but also meet the security and reliability of data transmission. Then, according to the full life cycle stage of power data, the power business is divided, and the power business division results are obtained as shown in the figure. Figure 3 As shown, the full life cycle of power data includes the generation and extraction stage, the analysis and use stage, the evaluation and optimization stage, and the storage standby stage. Power services include acquisition services, communication services, distributed source storage topology identification services, operation control services, energy management services, intelligent inspection services, protection services, user demand side response services, power quality services, information security services, low-carbon monitoring services, and data management services. Finally, according to the core structure of the new energy core and the power service division results, the new energy core core is matched with the power service to obtain the adaptation result. The advantages of different cores of multi-core heterogeneous new energy cores can be used to adapt the power services they carry. Exemplarily, for power-specific algorithm IP cores, the power-specific algorithm IP core has a high degree of parallel computing capability and excellent power consumption efficiency, and is suitable for computing tasks in fields such as deep learning and neural networks. It is often used for acquisition services, operation control services, demand side response services, communication services, information security services, or distributed source storage topology identification services. For the central processing unit core, the advantage of the CPU core is that it is highly versatile and suitable for various application scenarios. It is often used in acquisition services, operation control services, protection services, energy management services, power quality services, demand-side response services, data management services, communication services, information security services, low-carbon monitoring services, distributed source storage topology identification services or intelligent inspection services. For the field programmable gate array core, the advantage of the FPGA core is that it is highly flexible and reconfigurable, and has a wide range of adaptability. It is often used in energy management services, demand-side response services, data management services, communication services, information security services, low-carbon monitoring services or intelligent inspection services. For the digital signal processing core, the advantage of the DSP core is that it has relatively excellent computing power and real-time performance in the scenarios of processing high-speed data streams and complex algorithms. It is often used in acquisition services, power quality services, data management services or low-carbon monitoring services.

[0096] In some embodiments, in step S103, the multi-core heterogeneous chip parameters are calculated according to the adaptation result, which may include but is not limited to the following steps:

[0097] Calculate the running dynamic power consumption based on the processing instruction length, dynamic execution loss and processor core effective capacitance;

[0098] Calculate the total power consumption of multi-core heterogeneous chip service flow execution based on dynamic power consumption, data upload static power consumption, data download static power consumption, number of processors and number of power services to be executed;

[0099] Calculate the volume of a multi-core heterogeneous chip based on the number of processors, the number of processor cores, the volume of the processor cores, and the volume space coefficient;

[0100] The price of a multi-core heterogeneous chip is calculated based on the price cost coefficient, the number of processors, the processor core price cost, and the number of processor cores.

[0101] In some embodiments, the multi-core heterogeneous chip parameters can be calculated based on the adaptation results, where the multi-core heterogeneous chip parameters can include the total power consumption of the multi-core heterogeneous chip service flow execution, the multi-core heterogeneous chip composition volume, and the multi-core heterogeneous chip price. To calculate the multi-core heterogeneous chip parameters when the power business is processed on different cores, the running dynamic power consumption can be calculated based on the processing instruction length, dynamic execution loss, and processor core effective capacitance, where the calculation formula for running dynamic power consumption is: In the formula, p i,j (f) is the dynamic power consumption of the jth power service running on the i-th processor core, f i,j is the processing instruction length of the jth power business on the i-th processor core, P ind is the dynamic execution cost that is independent of instruction length, C ef is the effective capacitance of the processor core, d is the dynamic power index, and generally d is not less than 2. Then, according to the dynamic power consumption of operation, static power consumption of data upload, static power consumption of data download, number of processors and number of power services to be executed, the total power consumption of the multi-core heterogeneous chip service flow execution is calculated by the total power consumption calculation formula of the multi-core heterogeneous chip service flow execution. The total power consumption calculation formula of the multi-core heterogeneous chip service flow execution is: Where P c is the total power consumption of multi-core heterogeneous chip service flow execution, p i,j (f) is the dynamic power consumption of operation, p i,j,up is the static power consumption of data upload of the jth power service after execution on the i-th processor core, p i,j,dois the static power consumption of data download when the jth power service starts to be processed by the i-th processor core, N is the number of processors in the multi-core heterogeneous chip, and M is the number of power services to be executed. Then, according to the number of processors, the number of processor cores, the volume of the processor cores and the volume space coefficient, the volume calculation formula of the multi-core heterogeneous chip is used to calculate the volume of the multi-core heterogeneous chip. The volume calculation formula of the multi-core heterogeneous chip is: Where V c is the volume of a multi-core heterogeneous chip, N is the number of processors, and m is i is the number of the i-th processor core, v i is the volume of the ith processor core, and σ is the volume space coefficient of multi-core heterogeneous chips under different arrangements. Finally, the price of multi-core heterogeneous chips is calculated using the multi-core heterogeneous chip price calculation formula based on the price cost coefficient, the number of processors, the price cost of the processor core, and the number of processor cores. The multi-core heterogeneous chip price calculation formula is: In the formula, C c is the price of multi-core heterogeneous chips, λ is the price cost coefficient of multi-core heterogeneous chips with multiple processor cores, N is the number of processors, ω i is the price cost of the i-th processor core, m i is the number of processor cores.

[0102] In some embodiments, in step S104, constructing a candidate new energy core combination according to the multi-core heterogeneous chip parameters may include but is not limited to the following steps:

[0103] Construct power consumption limit constraints based on the power consumption generated by executing power services and the rated power consumption limit of the processor core;

[0104] According to the total power consumption of multi-core heterogeneous chip business flows and the rated power consumption limit of new energy chips, the total power consumption constraint of new energy chips is established;

[0105] According to the time required for waiting state instruction capture, the time required for ready state instruction analysis, the time required for running state instruction analysis, the time required for data upload to the bus and the time required for data download from the bus, the time delay constraint for power business completion time is established;

[0106] According to the data space occupied by the data upload unit instruction and the data space occupied by the data download unit instruction, the bus can be constructed to carry data space constraints;

[0107] Construct a multi-objective optimization function based on power consumption limit constraints, total power consumption constraints of new energy chips, power service completion time delay constraints, bus-carryable data space constraints, and multi-core heterogeneous chip parameters;

[0108] Based on the multi-objective optimization function, a combination of new energy cores to be selected is constructed.

[0109] In some embodiments, a power consumption limit constraint may be constructed based on the power consumption generated by executing the power service and the rated power consumption limit of the processor core, wherein the power consumption limit constraint is expressed as: In the formula, p i (f) is the power consumption generated by executing power business on the i-th processor core, p i,j (f) is the dynamic power consumption of the jth power service running on the i-th processor core, p i,j,up is the static power consumption of data upload of the jth power service after execution on the i-th processor core, p i,j,do is the static power consumption of data downloading of the jth power service when the i-th processor core starts processing, p i,limit is the rated power consumption limit of the i-th processor core.

[0110] According to the total power consumption of the multi-core heterogeneous chip business flow and the rated power consumption limit of the new energy core, the total power consumption constraint of the new energy core is constructed. The expression of the total power consumption constraint of the new energy core is: Where P c is the total power consumption of executing the service flow of the multi-core heterogeneous chip, that is, the total power consumption of executing the power service on the multi-core heterogeneous new energy core, N is the number of processors in the multi-core heterogeneous chip, M is the number of power services to be executed, P c,limit It is the rated power consumption limit of multi-core heterogeneous new energy chips.

[0111] According to the time required for waiting state instruction capture, the time required for ready state instruction analysis, the time required for running state instruction analysis, the time required for data upload to the bus, and the time required for data download from the bus, the power business completion time delay constraint is constructed. The expression of the power business completion time delay constraint is: In the formula, X is the number of blocks x divided by the power business sequence, K is the total number of branches in block x, t i,j,fe is the time required for the jth power business to fetch the waiting state instruction on the ith processor core, t i,j,an is the time required for the jth power business to analyze the ready state instructions on the i-th processor core, t i,j,op is the time required for the jth power business to run state instruction analysis on the i-th processor core, t i,j,up is the time required for the jth power business to complete data processing on the i-th processor core and upload it to the bus, t i,j,do is the time required for the jth power business to start processing data from the bus on the ith processor core, t limit Latency constraints for power business flows executed on multi-core heterogeneous chips.

[0112] According to the data space occupied by the data upload unit instruction and the data space occupied by the data download unit instruction, the bus can carry data space constraints, where the expression of the bus can carry data space constraints is: In the formula, f i,j is the processing instruction length of the jth power business on the i-th processor core, Q i,j,up Q is the data space occupied by the data upload unit instruction when uploading data from the processor core to the bus. i,j,do Q is the data space occupied by the data download unit instruction downloaded from the bus to each processor core, line_limit The data space constraint that can be carried on the bus. In addition, the serial connection mode of the power business in this embodiment can be defined as three types: hybrid, parallel and series. More complex forms such as other parallel branches in the hybrid can be simplified to these three forms. The serial connection mode of the power business is divided into the following: Figure 4 shown.

[0113] Then, according to the power consumption limit constraint, the total power consumption constraint of the new energy core, the power service completion time delay constraint, the bus loadable data space constraint and the multi-core heterogeneous chip parameters, a multi-objective optimization function is constructed to optimize the weighted values ​​of the three decision variables of power consumption, cost and volume. The expression of the multi-objective optimization function is: minP1=w1P c +w2V c +w3C c , where P1 is the objective function value, P c is the total power consumption of multi-core heterogeneous chip business flow execution, V c The volume of multi-core heterogeneous chips, C c is the price of multi-core heterogeneous chips, w1, w2 and w3 are all weight coefficients, w1+w2+w3=1. Finally, according to the multi-objective optimization function, a combination of new energy cores to be selected is constructed. The multi-objective optimization function can be solved by the optimization solution method. When the objective function value is as small as possible, a variety of combinations of new energy cores to be selected can be obtained for further screening.

[0114] In some embodiments, in step S105, constructing a target new energy core combination according to the characteristic index and the candidate new energy core combination may include but is not limited to the following steps:

[0115] According to the characteristic indicators, a characteristic indicator set is constructed;

[0116] According to the characteristic indicator set and the combination of the new energy cores to be selected, an important value sequence is constructed;

[0117] According to the importance value sequence and importance normalization strategy, an importance value matrix is ​​constructed;

[0118] According to the importance value matrix, calculate the sum of important values;

[0119] Normalize the sum of the important values ​​to obtain a normalized value;

[0120] According to the evaluation value distance coefficient, the normalized value is interval mapped to obtain the importance evaluation value;

[0121] According to the importance evaluation value, construct the target new energy core combination.

[0122] In some embodiments, a target new energy core core combination can be constructed based on characteristic indicators and candidate new energy core core combinations, wherein the characteristic indicators may include real-time indicators, reliability indicators, flexibility indicators, scalability indicators, and economic indicators. The characteristic indicators are used to evaluate and analyze multiple candidate new energy core core combinations to obtain the optimal target new energy core core combination. The characteristic indicator set K = {k q},q=1,2,…,Q, where k q is the characteristic index, Q is the total number of evaluation indicators. According to the characteristic index set and the combination of new energy cores to be selected, B = {b l}, l = 1, 2, ..., L, construct an important value sequence Among them, s l (k q ) represents the kernel combination scheme b l The important value under the characteristic index is q The most demanding business For the characteristic index k q Minimum business requirements l (k q )=1, The solution set is based on the characteristic index k q The value of the difference between solution set B and indicator set k is determined by q have There are different requirements, such as high, relatively high, and general evaluation requirements. For example, according to the definition of the characteristic index, the response of different kernel combination schemes to different characteristic indexes can be as follows: Figure 5 shown.

[0123] Then, according to the importance value sequence and importance normalization strategy, the importance value matrix is ​​constructed. For example, taking the real-time requirement as an example, the expression can be obtained as follows: in, Indicates the importance of the kernel combination scheme, that is, the kernel combination scheme b l In the characteristic index k q Compared with other combination schemes b yIs it important? 1 is important, 0 is unimportant, and 0.5 is equally important. When l = y, that is, the data on the diagonal has no practical meaning, take So when l≠y, In order to avoid the difference between the business importance evaluation results being too large or too small, the sum of the importance values ​​can be calculated according to the importance value matrix, where the calculation formula for the sum of the importance values ​​is: In the formula, is the sum of important values, Q is the total number of evaluation indicators, and Y is the total number of kernel combination solutions. Then the sum of important values ​​is normalized to obtain the normalized value. Then, the maximum value can be found from the sum of important values. With minimum And perform normalization processing, where the calculation formula of the normalized value is: In the formula, is the normalized value, is the maximum value found in the sum of important values, is the minimum value found in the sum of important values. After normalization, it will appear In the case of , the relative importance is 0 in the physical sense, and the problem cannot be solved. Therefore, this embodiment performs interval mapping after normalization to avoid this situation. The normalized value can be interval mapped according to the evaluation value distance coefficient to obtain the importance evaluation value, wherein the calculation formula of the importance evaluation value is: In the formula, H l is the importance evaluation value of the final kernel combination scheme after interval mapping, u is the evaluation value distance coefficient, the value range is 0-1, generally 0.1, so that the evaluation value distance between the most important scheme and the least important scheme is set to 10 times. Finally, according to the importance evaluation value, the target new energy core kernel combination is constructed. Exemplarily, the combination with a high importance evaluation value can be used as the target new energy core kernel combination.

[0124] In some embodiments, in step S106, the new energy core configuration can be optimized according to the target new energy core core combination, and the new energy core configuration can be adjusted according to the new energy core core parameters in the target new energy core core combination, so that the new energy core is more suitable for the target power business, thereby improving adaptability and reducing configuration redundancy.

[0125] In some embodiments, the overall process of building a kernel business matching solution is as follows: Figure 6As shown, this embodiment proposes a strategy for adapting power services according to the core advantages of multi-core heterogeneous new energy cores. Analyze the advantages of commonly used cores of multi-core heterogeneous new energy cores, summarize and organize power services for new energy scenarios, and comprehensively consider the two to perform initial modeling of core and power service adaptation. Then a dynamic combination optimization strategy based on the matching of new energy core cores and power services is proposed. Consider setting three decision variables of power consumption, volume and core price on the basis of the new energy core core business adaptation model to optimize the matching of power services and the core composition of multi-core heterogeneous new energy cores. By constructing a multi-objective optimization problem, the combination of new energy core cores is screened. Finally, a strategy for evaluating and selecting the best combination of new energy core cores is proposed. According to the optimal solutions obtained in the dynamic combination model of new energy core cores, the characteristic indicators of five dimensions of real-time, reliability, flexibility, scalability and economy are evaluated, and finally the best core business matching solution for multi-core heterogeneous new energy cores is selected.

[0126] The beneficial effects of implementing the embodiments of the present invention include: the embodiments of the present invention first obtain multi-core heterogeneous new energy core information, and perform power business adaptation processing based on the multi-core heterogeneous new energy core information to obtain adaptation results, and then calculate the multi-core heterogeneous chip parameters based on the adaptation results, and construct a candidate new energy core kernel combination based on the multi-core heterogeneous chip parameters, and then construct a target new energy core kernel combination based on the characteristic indicators and the candidate new energy core kernel combination, and finally optimize the new energy core configuration based on the target new energy core kernel combination, so that the new energy core configuration optimization can be achieved by calculating the degree of adaptation between the new energy core kernel and the power business, thereby improving adaptability and reducing configuration redundancy.

[0127] like Figure 7 As shown, the embodiment of the present invention also provides a multi-core heterogeneous new energy core configuration optimization device, including:

[0128] The first module 801 is used to obtain multi-core heterogeneous new energy chip information;

[0129] The second module 802 is used to perform power service adaptation processing according to the multi-core heterogeneous new energy core information to obtain an adaptation result;

[0130] The third module 803 is used to calculate the multi-core heterogeneous chip parameters according to the adaptation result, and the multi-core heterogeneous chip parameters include the total power consumption of the multi-core heterogeneous chip service flow execution, the multi-core heterogeneous chip composition volume and the multi-core heterogeneous chip price;

[0131] The fourth module 804 is used to construct a combination of new energy cores to be selected according to the multi-core heterogeneous chip parameters;

[0132] The fifth module 805 is used to construct a target new energy core combination according to the characteristic indicators and the candidate new energy core combination, wherein the characteristic indicators include a real-time indicator, a reliability indicator, a flexibility indicator, an expansibility indicator and an economic indicator;

[0133] The sixth module 806 is used to optimize the configuration of the new energy cell according to the target new energy cell core combination.

[0134] The contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0135] like Figure 8 As shown, an embodiment of the present invention further provides a computer device, including:

[0136] at least one processor 901;

[0137] At least one memory 902, used to store at least one program;

[0138] When at least one program is executed by at least one processor, the at least one processor implements Figure 1 The method shown.

[0139] The contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0140] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A multi-core heterogeneous new energy core configuration optimization method, characterized in that: The following steps are involved: Obtain information about multi-core heterogeneous new energy chips; Performing power service adaptation processing according to the multi-core heterogeneous new energy core information to obtain an adaptation result; Calculating the multi-core heterogeneous chip parameters according to the adaptation result, wherein the multi-core heterogeneous chip parameters include the total power consumption of the multi-core heterogeneous chip service flow execution, the multi-core heterogeneous chip composition volume, and the multi-core heterogeneous chip price; According to the multi-core heterogeneous chip parameters, construct a combination of new energy cores to be selected; According to the characteristic indicators and the candidate new energy core combination, a target new energy core combination is constructed, wherein the characteristic indicators include a real-time indicator, a reliability indicator, a flexibility indicator, an expansibility indicator, and an economic indicator; The new energy cell configuration is optimized according to the target new energy cell core combination.

2. The method according to claim 1, characterized in that The performing power service adaptation processing according to the multi-core heterogeneous new energy core information to obtain the adaptation result includes: Determine the core structure of the new energy core according to the multi-core heterogeneous new energy core information, wherein the core structure of the new energy core includes a central processing unit core, a digital signal processing core, a power-specific algorithm IP core, a field programmable gate array core, and a bus; According to the full life cycle stages of power data, the power business is divided to obtain the power business division results. The full life cycle stages of power data include generation and extraction stage, analysis and use stage, evaluation and optimization stage, and storage and standby stage. The power business includes acquisition business, communication business, distributed source and storage topology identification business, operation control business, energy management business, intelligent inspection business, protection business, user demand side response business, power quality business, information security business, low-carbon monitoring business, and data management business; According to the new energy core structure and the power service division result, the new energy core is matched with the power service to obtain the adaptation result.

3. The method according to claim 1, characterized in that: The calculating the multi-core heterogeneous chip parameters according to the adaptation result includes: Calculate the running dynamic power consumption based on the processing instruction length, dynamic execution loss and processor core effective capacitance; Calculate the total power consumption of the multi-core heterogeneous chip service flow execution according to the dynamic power consumption of operation, static power consumption of data uploading, static power consumption of data downloading, the number of processors and the number of power services to be executed; Calculating the volume of the multi-core heterogeneous chip according to the number of processors, the number of processor cores, the volume of the processor cores and the volume space coefficient; The price of the multi-core heterogeneous chip is calculated based on the price cost coefficient, the number of processors, the processor core price cost and the number of processor cores.

4. The method according to claim 1, characterized in that: The step of constructing a combination of new energy cores to be selected according to the multi-core heterogeneous chip parameters includes: Construct power consumption limit constraints based on the power consumption generated by executing power services and the rated power consumption limit of the processor core; According to the total power consumption of the multi-core heterogeneous chip business flow and the rated power consumption limit of the new energy core, a total power consumption constraint of the new energy core is constructed; According to the time required for waiting state instruction capture, the time required for ready state instruction analysis, the time required for running state instruction analysis, the time required for data upload to the bus and the time required for data download from the bus, the time delay constraint for power business completion time is established; According to the data space occupied by the data upload unit instruction and the data space occupied by the data download unit instruction, the bus can be constructed to carry data space constraints; Constructing a multi-objective optimization function according to the power consumption limit constraint, the total power consumption constraint of the new energy core, the power service completion time delay constraint, the bus-carryable data space constraint and the multi-core heterogeneous chip parameters; According to the multi-objective optimization function, the new energy core combination to be selected is constructed.

5. The method according to claim 1, characterized in that The step of constructing a target new energy core combination according to the characteristic index and the candidate new energy core combination includes: According to the characteristic indicators, a characteristic indicator set is constructed; Constructing an important value sequence according to the characteristic indicator set and the combination of the new energy cores to be selected; According to the importance value sequence and importance normalization strategy, construct an importance value matrix; Calculating the sum of importance values ​​according to the importance value matrix; Normalizing the sum of the important values ​​to obtain a normalized value; According to the evaluation value distance coefficient, the normalized value is interval mapped to obtain an importance evaluation value; The target new energy core combination is constructed according to the importance evaluation value.

6. The method according to claim 3, characterized in that The calculating the total power consumption of the multi-core heterogeneous chip service flow execution according to the dynamic power consumption of operation, the static power consumption of data uploading, the static power consumption of data downloading, the number of processors and the number of power services to be executed includes: According to the dynamic power consumption of operation, static power consumption of data upload, static power consumption of data download, the number of processors and the number of power services to be executed, the total power consumption of the multi-core heterogeneous chip service flow execution is calculated by the total power consumption calculation formula of the multi-core heterogeneous chip service flow execution. The total power consumption calculation formula of the multi-core heterogeneous chip service flow execution is: Where P c is the total power consumption of the multi-core heterogeneous chip service flow execution, p i,j (f) is the dynamic power consumption of the operation, p i,j,up is the static power consumption of data upload, p i,j,do is the static power consumption of data downloading, N is the number of processors, and M is the number of power services.

7. The method according to claim 3, characterized in that The calculating the volume of the multi-core heterogeneous chip according to the number of processors, the number of processor cores, the volume of the processor cores and the volume space coefficient includes: According to the number of processors, the number of processor cores, the volume of the processor cores and the volume space coefficient, the volume of the multi-core heterogeneous chip is calculated by the multi-core heterogeneous chip volume calculation formula, and the multi-core heterogeneous chip volume calculation formula is: Where V c is the volume of the multi-core heterogeneous chip, N is the number of processors, m is i is the number of processor cores, V i is the volume of the processor core, and σ is the volume space coefficient.

8. The method according to claim 3, characterized in that The calculating the price of the multi-core heterogeneous chip according to the price cost coefficient, the number of processors, the price cost of processor cores and the number of processor cores includes: The price of the multi-core heterogeneous chip is calculated according to the price cost coefficient, the number of processors, the price cost of the processor core and the number of processor cores by using the multi-core heterogeneous chip price calculation formula. The multi-core heterogeneous chip price calculation formula is: In the formula, C c is the price of the multi-core heterogeneous chip, λ is the price cost coefficient, N is the number of processors, ω i is the price cost of the processor core, m i is the number of processor cores.

9. A multi-core heterogeneous new energy core configuration optimization device, characterized in that: include: The first module is used to obtain multi-core heterogeneous new energy chip information; The second module is used to perform power business adaptation processing according to the multi-core heterogeneous new energy core information to obtain an adaptation result; The third module is used to calculate the multi-core heterogeneous chip parameters according to the adaptation result, wherein the multi-core heterogeneous chip parameters include the total power consumption of the multi-core heterogeneous chip business flow execution, the multi-core heterogeneous chip composition volume and the multi-core heterogeneous chip price; The fourth module is used to construct a combination of new energy cores to be selected according to the multi-core heterogeneous chip parameters; A fifth module is used to construct a target new energy core core combination according to characteristic indicators and the candidate new energy core core combination, wherein the characteristic indicators include a real-time indicator, a reliability indicator, a flexibility indicator, an expansibility indicator, and an economic indicator; The sixth module is used to optimize the configuration of the new energy cell according to the target new energy cell core combination.

10. A computer device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 8.

Images