CN116451483A - Distributed energy SaaS application safety modeling method - Google Patents
Distributed energy SaaS application safety modeling method Download PDFInfo
- Publication number
- CN116451483A CN116451483A CN202310424057.3A CN202310424057A CN116451483A CN 116451483 A CN116451483 A CN 116451483A CN 202310424057 A CN202310424057 A CN 202310424057A CN 116451483 A CN116451483 A CN 116451483A
- Authority
- CN
- China
- Prior art keywords
- data
- modeling
- distributed energy
- task
- safety joint
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000009826 distribution Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 16
- 230000035945 sensitivity Effects 0.000 claims description 10
- 238000005520 cutting process Methods 0.000 claims description 9
- 238000010248 power generation Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 238000004146 energy storage Methods 0.000 claims description 6
- 238000013136 deep learning model Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 3
- 239000003999 initiator Substances 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 10
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 229910052799 carbon Inorganic materials 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Bioethics (AREA)
- Computer Hardware Design (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of distributed energy, in particular to a distributed energy SaaS application safety modeling method, which comprises the following steps: creating a safety joint modeling task; issuing a safety joint modeling task; executing a safety joint modeling task; optimizing a safety joint modeling model; the beneficial effects are as follows: the distributed energy SaaS application security modeling method provided by the invention utilizes a distributed cloud and cloud side cooperation technology, combines a privacy computing technology, is based on the data requirements of different service scenes of distributed energy service at the cloud side, effectively utilizes the data from various digital energy systems at the cloud side, and relies on the energy cloud data center resources according to the data ownership and the actual distribution conditions, so as to form an optimal security joint modeling scheme.
Description
Technical Field
The invention relates to the technical field of distributed energy, in particular to a distributed energy SaaS application safety modeling method.
Background
Federal learning is a common safe joint modeling method, and is firstly proposed by google in 2016 to solve the problem of updating local models of android mobile phone terminal users, and as an emerging artificial intelligence basic technology, the design target is to participate by multiple parties together on the premise of guaranteeing information safety, data privacy and legal compliance during data exchange, and complete efficient joint modeling based on multi-party data, reduce data islands and improve data value; the trusted execution environment TEE is an execution environment that is parallel to the device operating system and isolated from each other. The data and algorithm are encrypted and input into a feasible execution environment, the final calculation result is only output to the outside, and the original data and the process data are destroyed in situ, so that the 'available invisible' of the data is realized.
In the prior art, the traditional fossil energy is developed and utilized on a large scale in the global scope, so that the problems of environmental pollution, climate change and the like are increasingly outstanding, and the new energy plays a role in improving the energy structure, saving energy and reducing emission under the large environment of carbon peak and carbon neutralization. With the rapid development of new energy industry, the energy system is gradually distributed from a centralized mode, distributed photovoltaic, distributed wind power, biological power generation, natural gas distributed energy, energy Internet, micro-grid and multi-energy complementary projects are emerging in batches, the distributed energy is slowly an important carrier and a propelling means of energy revolution, and is also an important component of the future energy system, more reasonable use of the distributed energy is realized by utilizing new generation information technologies such as cloud computing, big data, deep learning and the like to become a focus of concern, and the digital energy system formed by the distributed energy is based on distributed cloud to realize cloud edge coordination of energy digitization, so that new transformation is brought to the energy industry. Particularly, the development of a distributed energy SaaS (Software-as-a-Service) Service gradually appears digital energy operators of cross-region, multi-manufacturer and multi-cloud infrastructures, so that various distributed energy resources such as source network loads and the like are more effectively managed and utilized.
However, prediction, optimization and deployment in the distributed energy core business are all independent of intelligence, and the competitiveness of the core SaaS application is a business model formed by the data support owned by the core SaaS application, which aggravates the attention of back vendors to data and data modeling. Different cloud infrastructure manufacturers, different SaaS application manufacturers and different digital energy operators exist in the distributed energy SaaS service, and each manufacturer expects cooperation on energy data and needs to protect private data of a user at the same time, so that the energy data safety problem is solved. Under the circumstance, how to effectively utilize the privacy computing technology, realize efficient energy data fusion modeling aiming at different distributed energy business demands of the cloud side end, and finish the optimization promotion of personalized SaaS by combining with the digital energy core business becomes a problem to be solved.
Disclosure of Invention
The invention aims to provide a distributed energy SaaS application safety modeling method for solving the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions: a distributed energy SaaS application security modeling method, the security modeling method comprising the steps of:
creating a safety joint modeling task;
issuing a safety joint modeling task;
executing a safety joint modeling task;
and (5) optimizing a safety joint modeling model.
Preferably, the security joint modeling task creation includes the following steps:
step 101, a distributed energy SaaS application service provider puts forward a safety joint modeling requirement, wherein the safety joint modeling requirement comprises a data item requirement, a safety joint modeling algorithm, an operation environment resource requirement and a participant charging mode;
step 102, a distributed energy SaaS application service provider publishes or directionally publishes a security joint modeling task;
step 103, a digital energy comprehensive service provider, a distributed photovoltaic service provider, a distributed wind power generation service provider, an energy storage system service provider, a power load system service provider, an electric automobile system service provider, an energy data service provider and a distributed energy SaaS application user with data ownership, selecting participation tasks according to the data distribution and the data sensitivity degree, and providing data specification requirements, distribution conditions, a deep learning model algorithm and calculation resource feedback;
step 104, selecting a plurality of groups of schemes from the safety joint modeling scheme template according to requirements and feedback, negotiating to form two groups of preliminary schemes of the A/distributed energy by each participant participating in the safety joint modeling of the distributed energy SaaS application, and uploading small samples of the data set;
step 105, the distributed energy SaaS application service provider runs a distributed energy safety modeling prototype system in a cloud data center according to a preliminary scheme and a small data set sample, simulates a multi-party safety joint modeling process of an A/distributed energy two-group scheme, and records a modeling process log;
step 106, according to the simulated prototype system log, the parties involved integrate multiple factors of safety, privacy, efficiency and accuracy, and one scheme is selected from two groups of preliminary schemes of the A/distributed energy;
and 107, adjusting the selected safety joint machine modeling scheme to determine a final safety joint modeling scheme.
Preferably, the safety joint modeling task issuing comprises the following steps:
step 201, generating a container mirror image which needs to be operated for each participant according to a safety joint machine modeling scheme of a safety joint modeling task;
step 202, an operating task node in the cloud provides a computing modeling operation environment for public data, sensitive data need to be operated in a TEE trusted execution environment, and client secret data need to be operated in a designated TEE trusted execution environment, and a mirror image is issued to each participant according to the resource deployment condition of the participant;
step 203, performing mirror image cutting on task nodes running on the edge sides of the energy stations and the intelligent electric vehicles according to the calculation storage resources of the nodes and the local data conditions, and issuing mirror images to all the participants according to the resource deployment conditions of the participants;
204, distributing a data collection mirror image for task nodes running on the end sides of an energy router, an electric automobile and the like if the task nodes are used as data nodes, realizing safe data transmission with an edge computing node, distributing a cutting mirror image for the end sides if the task nodes are used as computing nodes, realizing light weight computing, and carrying out joint computing on the end side nodes and the edge computing node;
step 205, digitally signing the mirror image of the safety joint machine modeling scheme of the safety joint modeling task, ensuring operation in a designated TEE trusted execution environment, distributing to appointed nodes, testing network connectivity, and confirming completion of task issuing.
Preferably, the safety joint modeling task is executed, comprising the following steps:
step 301, according to task mirroring issued by the security joint modeling, each participant performs mirror image loading according to local resources and local data calculation, a cloud end adopts a net structure, a cloud edge end adopts a tree structure, and distributed energy SaaS application model training is executed;
step 302, as a terminal participant of the data node participating in the security joint modeling, creating a container, loading a distributed mirror image, and transmitting required data to the edge end participant through a secure channel;
step 303, creating a container and loading a distributed mirror image as a terminal participant of a computing node participating in the security joint modeling, computing the gradient of a local model as a lightweight node, and uploading intermediate data to an edge end participant;
step 304, the edge end participants participating in the security joint modeling receive the terminal data, combine the edge side local data, create an operation environment according to the data sensitivity, particularly, create a TEE trusted execution environment for the sensitive data, load the task calculation mirror image and the sensitive data to the TEE trusted execution environment after verifying the mirror image and the participant identity, execute the transverse and longitudinal federation model training, form an intermediate result, and perform joint modeling ciphertext calculation with the cloud end participants;
step 305, a cloud participant participating in security joint modeling creates an operation environment according to the data sensitivity, creates a TEE trusted execution environment for sensitive data, loads task computing images and sensitive data into the TEE trusted execution environment after verifying the images and participant identities, and performs transverse and longitudinal federation model training in the TEE trusted execution environment;
step 306, completing model training by the participants of the safety joint modeling, storing the generated model to a designated position of a distributed energy SaaS application service provider initiator, and evaluating the model efficiency;
step 307, save the current safety joint modeling training task scheme, and release all levels of resources at the cloud edge end.
Preferably, the safety joint modeling model optimization comprises the following steps:
step 401, performing model cutting of a network model formed by distributed energy safety joint modeling according to the running resource condition of the distributed energy intelligent SaaS application;
step 402, distributing the distributed energy intelligent SaaS application to a designated running environment node;
step 403, monitoring the running condition of the distributed energy intelligent SaaS application, and recording a log;
and 404, continuously collecting feedback data, continuously optimizing a safety joint modeling strategy, continuously iterating to perform safety joint modeling, and continuously improving the prediction and recommendation accuracy of the intelligent model.
Compared with the prior art, the invention has the beneficial effects that:
the distributed energy SaaS application security modeling method provided by the invention utilizes a distributed cloud and cloud side cooperation technology, combines a privacy computing technology, is based on the data requirements of different service scenes of distributed energy service at the cloud side, effectively utilizes the data from various digital energy systems at the cloud side, and relies on the energy cloud data center resources according to the data ownership and the actual distribution condition to form an optimal security joint modeling scheme; fully considering diversity and security appeal of participants such as distributed energy SaaS service cloud infrastructure manufacturers, saaS application manufacturers, digital energy operators and the like, adopting different security calculation strategies at cloud edge ends, and improving overall modeling efficiency; the cloud end adopts the mode of combining federal learning with TEE trusted execution environment, so that the cloud end resource is effectively utilized, meanwhile, dual safety is realized, and the problem of multi-cloud trust in distributed energy safety modeling is solved; at the side of the side, the method adopts mirror image cutting and other modes, more reasonably utilizes resources, simultaneously utilizes edge nodes biased to the client service side to realize the isolation of the cloud center and the IOT equipment, and performs necessary safe data exchange at the side of the side, thereby ensuring that the domain cannot be calculated to a certain extent and increasing the privacy protection of the data. In addition, various factors influencing the overall efficiency of the distributed energy are comprehensively considered, and the external public data are combined to realize safe and efficient joint modeling; through the intelligent model formed by the joint modeling, deep connection of each element influencing the overall efficiency of the distributed energy is discovered, saaS application is distributed according to the service requirements of different nodes, the personalized requirements of the distributed energy service are met, and further, the distributed energy is managed and utilized more reasonably and efficiently.
Drawings
FIG. 1 is a schematic diagram of a distributed energy SaaS application system;
fig. 2 is a schematic diagram of security modeling of a distributed energy SaaS application of the present invention.
Detailed Description
In order to make the objects, technical solutions, and advantages of the present invention more apparent, the embodiments of the present invention will be further described in detail with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are some, but not all, embodiments of the present invention, are intended to be illustrative only and not limiting of the embodiments of the present invention, and that all other embodiments obtained by persons of ordinary skill in the art without making any inventive effort are within the scope of the present invention.
Example 1
Referring to fig. 1 to 2, the present invention provides a technical solution: the distributed energy SaaS application safety modeling method is based on an intelligent model which takes a neural network as a core and is designed based on the distributed energy SaaS service, effectively utilizes data from various digital energy systems at the cloud side, and relies on energy cloud data center resources according to the ownership of the data and the actual conditions of the distribution of the data to form an optimal safety joint modeling scheme; each party participating in the joint modeling carries out necessary safe data exchange according to the IT resource condition and the business data condition of the node, comprehensively considers various factors influencing the overall efficiency of the distributed energy sources, and combines external public data to realize safe and efficient joint modeling; through an intelligent model formed by joint modeling, deep connection of each element influencing the overall efficiency of the distributed energy is discovered, and personalized SaaS application is distributed according to the service requirements of different nodes, so that the distributed energy is managed and utilized more reasonably and efficiently. Wherein, the liquid crystal display device comprises a liquid crystal display device,
the distributed energy SaaS application is used for providing energy digital service services for distributed energy sources such as distributed photovoltaics, distributed wind power, distributed energy storage, distributed loads, electric vehicles and the like, and comprises service services such as distributed energy equipment management, sensing data acquisition, power resource query statistics, joint modeling, model management and the like, and intelligent service services such as photovoltaic power generation capacity prediction, power scheme recommendation, wind power generation capacity prediction, power scheme recommendation, power load prediction, power storage electric quantity prediction, power scheme recommendation and the like; the distributed energy SaaS application adopts a multi-tenant and multi-user mode, and comprises a digital energy comprehensive service provider, a distributed photovoltaic service provider, a distributed wind power generation service provider, an energy storage system service provider, a power load system service provider, an electric automobile system service provider, an energy data service provider and other service providers with data; the core of the intelligent business service of the distributed energy SaaS is a deep learning model, multiparty safety joint modeling is carried out through the distributed energy safety modeling service, and a prediction and recommendation model is obtained through training and learning; the energy cloud data center provides infrastructure services such as computation, storage, network, security and the like to meet the resource requirements required by the running of the distributed energy SaaS application, and simultaneously provides data services, internet of things services, AI services, TEE trusted execution environments, federal learning training services and the like; the distributed energy SaaS application adopts a multi-cloud deployment mode, is deployed at nodes such as an energy cloud data center, an edge computing energy site, an energy router and the like according to user requirements and scene requirements, and is uniformly managed by a SaaS application management center; the edge computing energy site is a distributed energy edge computing node, has stronger computing storage network capability, is close to local energy equipment, is in bidirectional safe connection with an energy router, is connected with an energy cloud data center, is uniformly managed by a SaaS application management center, runs cloud distributed energy SaaS application on the local node, and is used as a computing storage node for edge side joint modeling; the energy router nodes are connected with the distributed energy equipment, and are uniformly managed by the SaaS application management center, and the distributed energy SaaS application of the cloud or edge computing node is operated on the local node to realize data acquisition, equipment control, equipment management and the like of the distributed energy Internet of things equipment such as distributed photovoltaic, distributed wind power, distributed energy storage, distributed load, electric vehicles and the like, and provide intelligent services under the condition of node resources; the SaaS application management center operates in the energy cloud data center, and the SaaS application is deployed at the cloud side end according to the requirements of the user side, so that the management of the distributed energy SaaS application is realized; the distributed energy safety modeling service operates in an energy cloud data center, realizes cross-cloud and cloud-edge cooperative safety modeling based on cloud infrastructure provided by the energy cloud data center, TEE trusted running environment, data service, federal learning service, model training and other services, and provides functions of creating, distributing, executing, monitoring, managing and the like of distributed energy business safety modeling tasks; the model formed by the distributed energy safety modeling can be optimized according to actual requirements and is used in the distributed energy SaaS application; the data used by the distributed energy SaaS application security modeling is classified into three authorization levels of general data, sensitive data and confidential data according to the sensitivity degree of the business data, the SaaS application service provider can directly use the general data for modeling, for the sensitive data, the SaaS application service provider can only be used in a TEE trusted execution environment, and for the confidential data, the SaaS application service provider can only be used in a resource environment formulated by a user, and cannot directly view the data.
The invention provides a distributed energy SaaS application safety modeling method, which is used for safety joint modeling task creation and comprises the following steps:
step 101, a distributed energy SaaS application service provider puts forward a safety joint modeling requirement, wherein the safety joint modeling requirement comprises a data item requirement, a safety joint modeling algorithm, an operation environment resource requirement, a party charging mode and the like;
step 102, a distributed energy SaaS application service provider publishes or directionally publishes a security joint modeling task;
step 103, digital energy comprehensive service providers, distributed photovoltaic service providers, distributed wind power generation service providers, energy storage system service providers, power load system service providers, electric automobile system service providers, energy data service providers and other service providers with data and users with data ownership of distributed energy SaaS application select participation tasks according to data distribution and data sensitivity, and provide feedback of data specification requirements, distribution conditions, deep learning model algorithms, computing resources and the like;
step 104, selecting a plurality of groups of schemes from the safety joint modeling scheme template according to requirements and feedback, negotiating to form two groups of A/B preliminary schemes by all the participants participating in the safety joint modeling of the distributed energy SaaS application, and uploading small samples of the data set;
step 105, the distributed energy SaaS application service provider runs a distributed energy safety modeling prototype system in a cloud data center according to a preliminary scheme and a small data set sample, simulates a multi-party safety joint modeling process of an A/B two-group scheme, and records a modeling process log;
step 106, selecting one scheme from the two groups of A/B preliminary schemes according to the simulated prototype system log and various factors such as comprehensive safety, privacy, efficiency, accuracy and the like of all parties;
and 107, adjusting the selected safety joint machine modeling scheme to determine a final safety joint modeling scheme.
The invention provides a distributed energy SaaS application safety modeling method, which is used for issuing a safety joint modeling task and comprises the following steps:
step 201, generating a container mirror image which needs to be operated for each participant according to a safety joint machine modeling scheme of a safety joint modeling task;
step 202, an operating task node in the cloud provides a computing modeling operation environment for public data, sensitive data need to be operated in a TEE trusted execution environment, and client secret data need to be operated in a designated TEE trusted execution environment, and a mirror image is issued to each participant according to the resource deployment condition of the participant;
step 203, performing mirror image clipping on task nodes running on the edge sides of an energy station, an intelligent electric vehicle and the like according to the calculation storage resources of the nodes and the local data conditions, and issuing mirror images to all participants according to the resource deployment conditions of the participants;
204, distributing a data collection mirror image for task nodes running on the end sides of an energy router, an electric automobile and the like if the task nodes are used as data nodes, realizing safe data transmission with an edge computing node, distributing a cutting mirror image for the end sides if the task nodes are used as computing nodes, realizing light weight computing, and carrying out joint computing on the end side nodes and the edge computing node;
step 205, digitally signing the mirror image of the security joint machine modeling scheme of the security joint modeling task, ensuring that the mirror image can run in a designated TEE trusted execution environment, distributing the mirror image to the appointed nodes, testing network connectivity, and confirming that the task issuing is completed.
The invention provides a distributed energy SaaS application safety modeling method, which is used for executing a safety joint modeling task and comprises the following steps:
step 301, according to task mirroring issued by the security joint modeling, each participant performs mirror image loading according to local resources and local data calculation, a cloud end adopts a net structure, a cloud edge end adopts a tree structure, and distributed energy SaaS application model training is executed;
step 302, as a terminal participant of the data node participating in the security joint modeling, creating a container, loading a distributed mirror image, and transmitting required data to an edge end participant through a secure channel;
step 303, creating a container and loading a distributed mirror image as a terminal participant of a computing node participating in the security joint modeling, computing the gradient of a local model as a lightweight node, and uploading intermediate data to an edge end participant;
step 304, the edge end participants participating in the security joint modeling receive the data from the terminal, combine the local data of the edge side, create an operation environment according to the data sensitivity, particularly, create a TEE trusted execution environment for the sensitive data, load the task calculation mirror image and the sensitive data to the TEE trusted execution environment after verifying the mirror image and the participant identity, execute the transverse and longitudinal federation model training to form an intermediate result, and perform joint modeling ciphertext calculation with the cloud end participants;
step 305, a cloud participant participating in the security joint modeling creates an operation environment according to the data sensitivity, particularly, creates a TEE trusted execution environment for sensitive data, loads task computing mirror images and sensitive data into the TEE trusted execution environment after verifying the mirror images and participant identities, and executes transverse and longitudinal federation model training in the TEE trusted execution environment;
step 306, completing model training by the participants of the safety joint modeling, storing the generated model to a designated position of a distributed energy SaaS application service provider initiator, and evaluating the model efficiency;
step 307, save the current safety joint modeling training task scheme, and release all levels of resources at the cloud edge end.
The invention provides a distributed energy SaaS application safety modeling method, which is used for optimizing a safety joint modeling model and comprises the following steps:
step 401, performing model cutting of a network model formed by distributed energy safety joint modeling according to the running resource condition of the distributed energy intelligent SaaS application;
step 402, distributing the distributed energy intelligent SaaS application to a designated running environment node;
step 403, monitoring the running condition of the distributed energy intelligent SaaS application, and recording a log;
and 404, continuously collecting feedback data, continuously optimizing a safety joint modeling strategy, continuously iterating to perform safety joint modeling, and continuously improving the prediction and recommendation accuracy of the intelligent model.
According to the invention, a distributed cloud and cloud side cooperation technology is utilized, a privacy computing technology is combined, a data joint modeling scheme is designed based on data requirements of different service scenes of distributed energy services at the cloud side, various factors influencing the overall efficiency of the distributed energy are comprehensively considered, and various technical means such as horizontal and vertical federal learning and trusted execution environments are adopted to combine, so that safe joint modeling of the distributed energy SaaS application service is realized, and according to the characteristics of the distributed energy, the optimal personalized SaaS application is formed, and the distributed energy is managed and utilized more reasonably and efficiently.
Although embodiments of the present 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 therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (5)
1. A distributed energy SaaS application safety modeling method is characterized in that: the safety modeling method comprises the following steps:
creating a safety joint modeling task;
issuing a safety joint modeling task;
executing a safety joint modeling task;
and (5) optimizing a safety joint modeling model.
2. The distributed energy SaaS application security modeling method according to claim 1, wherein: the safety joint modeling task creation comprises the following steps:
step 101, a distributed energy SaaS application service provider puts forward a safety joint modeling requirement, wherein the safety joint modeling requirement comprises a data item requirement, a safety joint modeling algorithm, an operation environment resource requirement and a participant charging mode;
step 102, a distributed energy SaaS application service provider publishes or directionally publishes a security joint modeling task;
step 103, a digital energy comprehensive service provider, a distributed photovoltaic service provider, a distributed wind power generation service provider, an energy storage system service provider, a power load system service provider, an electric automobile system service provider, an energy data service provider and a distributed energy SaaS application user with data ownership, selecting participation tasks according to the data distribution and the data sensitivity degree, and providing data specification requirements, distribution conditions, a deep learning model algorithm and calculation resource feedback;
step 104, selecting a plurality of groups of schemes from the safety joint modeling scheme template according to requirements and feedback, negotiating to form two groups of preliminary schemes of the A/distributed energy by each participant participating in the safety joint modeling of the distributed energy SaaS application, and uploading small samples of the data set;
step 105, the distributed energy SaaS application service provider runs a distributed energy safety modeling prototype system in a cloud data center according to a preliminary scheme and a small data set sample, simulates a multi-party safety joint modeling process of an A/distributed energy two-group scheme, and records a modeling process log;
step 106, according to the simulated prototype system log, the parties involved integrate multiple factors of safety, privacy, efficiency and accuracy, and one scheme is selected from two groups of preliminary schemes of the A/distributed energy;
and 107, adjusting the selected safety joint machine modeling scheme to determine a final safety joint modeling scheme.
3. The distributed energy SaaS application security modeling method according to claim 1, wherein: the safety joint modeling task issuing method comprises the following steps of:
step 201, generating a container mirror image which needs to be operated for each participant according to a safety joint machine modeling scheme of a safety joint modeling task;
step 202, an operating task node in the cloud provides a computing modeling operation environment for public data, sensitive data need to be operated in a TEE trusted execution environment, and client secret data need to be operated in a designated TEE trusted execution environment, and a mirror image is issued to each participant according to the resource deployment condition of the participant;
step 203, performing mirror image cutting on task nodes running on the edge sides of the energy stations and the intelligent electric vehicles according to the calculation storage resources of the nodes and the local data conditions, and issuing mirror images to all the participants according to the resource deployment conditions of the participants;
204, distributing a data collection mirror image for task nodes running on the end sides of an energy router, an electric automobile and the like if the task nodes are used as data nodes, realizing safe data transmission with an edge computing node, distributing a cutting mirror image for the end sides if the task nodes are used as computing nodes, realizing light weight computing, and carrying out joint computing on the end side nodes and the edge computing node;
step 205, digitally signing the mirror image of the safety joint machine modeling scheme of the safety joint modeling task, ensuring operation in a designated TEE trusted execution environment, distributing to appointed nodes, testing network connectivity, and confirming completion of task issuing.
4. The distributed energy SaaS application security modeling method according to claim 1, wherein: the safety joint modeling task execution comprises the following steps:
step 301, according to task mirroring issued by the security joint modeling, each participant performs mirror image loading according to local resources and local data calculation, a cloud end adopts a net structure, a cloud edge end adopts a tree structure, and distributed energy SaaS application model training is executed;
step 302, as a terminal participant of the data node participating in the security joint modeling, creating a container, loading a distributed mirror image, and transmitting required data to an edge end participant through a secure channel;
step 303, creating a container and loading a distributed mirror image as a terminal participant of a computing node participating in the security joint modeling, computing the gradient of a local model as a lightweight node, and uploading intermediate data to an edge end participant;
step 304, the edge end participants participating in the security joint modeling receive the terminal data, combine the edge side local data, create an operation environment according to the data sensitivity, particularly, create a TEE trusted execution environment for the sensitive data, load the task calculation mirror image and the sensitive data to the TEE trusted execution environment after verifying the mirror image and the participant identity, execute the transverse and longitudinal federation model training, form an intermediate result, and perform joint modeling ciphertext calculation with the cloud end participants;
step 305, a cloud participant participating in security joint modeling creates an operation environment according to the data sensitivity, creates a TEE trusted execution environment for sensitive data, loads task computing images and sensitive data into the TEE trusted execution environment after verifying the images and participant identities, and performs transverse and longitudinal federation model training in the TEE trusted execution environment;
step 306, completing model training by the participants of the safety joint modeling, storing the generated model to a designated position of a distributed energy SaaS application service provider initiator, and evaluating the model efficiency;
step 307, save the current safety joint modeling training task scheme, and release all levels of resources at the cloud edge end.
5. The distributed energy SaaS application security modeling method according to claim 1, wherein: the optimization of the safety joint modeling model comprises the following steps:
step 401, performing model cutting of a network model formed by distributed energy safety joint modeling according to the running resource condition of the distributed energy intelligent SaaS application;
step 402, distributing the distributed energy intelligent SaaS application to a designated running environment node;
step 403, monitoring the running condition of the distributed energy intelligent SaaS application, and recording a log;
and 404, continuously collecting feedback data, continuously optimizing a safety joint modeling strategy, continuously iterating to perform safety joint modeling, and continuously improving the prediction and recommendation accuracy of the intelligent model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310424057.3A CN116451483A (en) | 2023-04-20 | 2023-04-20 | Distributed energy SaaS application safety modeling method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310424057.3A CN116451483A (en) | 2023-04-20 | 2023-04-20 | Distributed energy SaaS application safety modeling method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116451483A true CN116451483A (en) | 2023-07-18 |
Family
ID=87125216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310424057.3A Pending CN116451483A (en) | 2023-04-20 | 2023-04-20 | Distributed energy SaaS application safety modeling method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116451483A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116800550A (en) * | 2023-08-29 | 2023-09-22 | 北京仁科互动网络技术有限公司 | Region management method, device and equipment in software as a service (SaaS) mode |
| CN118075293A (en) * | 2024-03-18 | 2024-05-24 | 北京谷器数据科技有限公司 | Cloud platform data storage method based on SaaS |
-
2023
- 2023-04-20 CN CN202310424057.3A patent/CN116451483A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116800550A (en) * | 2023-08-29 | 2023-09-22 | 北京仁科互动网络技术有限公司 | Region management method, device and equipment in software as a service (SaaS) mode |
| CN118075293A (en) * | 2024-03-18 | 2024-05-24 | 北京谷器数据科技有限公司 | Cloud platform data storage method based on SaaS |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116451483A (en) | Distributed energy SaaS application safety modeling method | |
| Wang et al. | AEBIS: AI-enabled blockchain-based electric vehicle integration system for power management in smart grid platform | |
| Liu et al. | Federated learning for 6G communications: Challenges, methods, and future directions | |
| Moeini-Aghtaie et al. | A decomposed solution to multiple-energy carriers optimal power flow | |
| Wu et al. | Distributed optimal coordination for distributed energy resources in power systems | |
| Zhang et al. | Energy management framework for electric vehicles in the smart grid: A three-party game | |
| CN113435472A (en) | Vehicle-mounted computing power network user demand prediction method, system, device and medium | |
| Zhang et al. | Digital twin for accelerating sustainability in positive energy district: a review of simulation tools and applications | |
| CN110417456B (en) | Information transmission method based on unmanned aerial vehicle | |
| Said et al. | Multi‐priority queuing for electric vehicles charging at public supply stations with price variation | |
| CN107579518A (en) | Power system environment economic load dispatching method and apparatus based on MHBA | |
| Almutairi et al. | Delay-optimal task offloading for UAV-enabled edge-cloud computing systems | |
| CN111461890A (en) | Distributed power generation transaction system and method based on multiple prediction and block chain technologies | |
| CN113098711A (en) | Power distribution Internet of things CPS (control system) management and control method and system based on cloud edge cooperation | |
| Guo et al. | Collaborative computation offloading for mobile-edge computing over fiber-wireless networks | |
| Cai et al. | Scalable on-chain and off-chain blockchain for sharing economy in large-scale wireless networks | |
| Miozzo et al. | Distributed and multi-task learning at the edge for energy efficient radio access networks | |
| Zhao et al. | Socialized learning for smart cities: cognitive paradigm, methodology, and solution | |
| Liu et al. | Joint optimization offloading and resource allocation in vehicular edge cloud computing networks with delay constraints | |
| Liu et al. | Distributed computation offloading with low latency for artificial intelligence in vehicular networking | |
| Aloqaily et al. | Guest editorial: Empowering sustainable energy infrastructures via AI-assisted wireless Communications | |
| Dridi et al. | Reinforcement Learning Vs ILP Optimization in IoT support of Drone assisted Cellular Networks | |
| CN114119278A (en) | Multi-station fusion power resource management system based on block chain technology | |
| Eldegwi et al. | Utilization of Mobile Agents for Building a Secure Decentralized Energy System with Remote Monitoring | |
| CN115002217B (en) | Scheduling method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |