A smart street lamp automatic control system and method
By deploying edge computing technology and asymmetric encryption algorithms in smart street light systems, the data processing capabilities, transmission security and network reliability of smart street light systems are solved, efficient data processing and real-time control strategy adjustments are achieved, and the system is improved overall performance and security.
Patent Information
- Application Number
- CN202411244147.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-09-06
AI Technical Summary
The existing smart street light control system has poor data processing capabilities, low transmission security, poor network reliability and poor control strategy flexibility, resulting in slow data processing speed, poor real-time performance, vulnerability to hackers, insufficient network signal stability and energy. waste.
Adopt edge computing technology to deploy data analysis models, automatic control models and network detection models, combine asymmetric encryption algorithms and digital signature technology to realize data localization processing and real-time network detection, dynamically adjust control strategies, and ensure data transmission security and network stability sex.
It improves data processing capabilities and response speed, enhances data transmission security and network reliability, and realizes dynamic adjustment of control strategies based on real-time environments to avoid energy waste, improves lighting effects and control flexibility.
Smart Images

Figure CN118765020B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of smart street lamps, and in particular relates to a smart street lamp automatic control system and method. Background Art
[0002] As a key component of smart cities, the functions of smart street lights have expanded from single lighting to multiple fields such as environmental monitoring, information release, and urban security. With the development of technologies such as the Internet of Things, big data, and cloud computing, smart street light control systems are also constantly improving. However, the existing smart street light control systems still have shortcomings in the following aspects:
[0003] 1) Poor data processing capabilities: Existing smart street lighting systems rely heavily on centralized servers for data processing, which can easily cause the server to be overloaded when the amount of data is huge, resulting in slow data processing and poor real-time performance.
[0004] 2) Low transmission security: The data involved in the smart street lighting system usually includes sensitive information or confidential data. The existing system lacks effective encryption and authentication mechanisms during data transmission and storage, making it vulnerable to hacker attacks and data leaks.
[0005] 3) Poor network reliability: Smart street lights usually rely on stable network connections, but in actual applications, the network environment is complex and changeable, and is easily affected by factors such as weather and geographical location, resulting in insufficient network signal stability and poor transmission reliability.
[0006] 4) Poor flexibility of control strategies: Existing smart street light control strategies are often based on preset rules and lack the ability to dynamically adjust according to real-time environment and demand, resulting in energy waste and poor lighting effects. Summary of the invention
[0007] In order to solve the problems of poor data processing capability, low transmission security, poor network reliability and poor control strategy flexibility in the prior art, the present invention aims to provide a smart street lamp automatic control system and method.
[0008] The technical solution adopted by the present invention is:
[0009] A smart street light automatic control system includes a control center, a trusted organization and a plurality of smart street light units. The control center and the trusted organization are respectively connected to the plurality of smart street light units in communication, and the control center is also connected to the trusted organization in communication. Each smart street light unit is connected to an external third-party data platform in communication.
[0010] Furthermore, the smart street light unit includes an edge computing base station, a switch cabinet and several smart street lights. The edge computing base station is electrically connected to the switch cabinet and the several smart street lights, respectively, and the edge computing base station is communicatively connected to the controller, control center, trusted organization and external third-party data platform of the smart street light, respectively.
[0011] Furthermore, the edge computing base station includes an edge computing gateway, several electrical signal edge computing gateways, several environmental edge computing gateways and several switch driving devices. The edge computing gateway is electrically connected to all electrical signal edge computing gateways, all environmental edge computing gateways and all switch driving devices respectively, and the edge computing gateway is respectively communicated with the controllers, control center, trusted institutions and external third-party data platforms of all smart street lamps. Each electrical signal edge computing gateway is electrically connected to the power supply line of a smart street lamp in the switch cabinet one by one, each environmental edge computing gateway is arranged at a smart street lamp one by one, and each switch driving device is electrically connected to the control switch of a smart street lamp in the switch cabinet one by one.
[0012] Furthermore, the edge computing gateway is provided with a data transmission module, a network detection module, a data processing module, an encryption and decryption module, a digital signature module, a data analysis module, an automatic control module and an instruction generation module which are connected in sequence. The data transmission module is respectively communicated with the controller, the control center, the trusted organization and the external third-party data platform of the smart street lamp. The data processing module is respectively electrically connected with several electrical signal edge computing gateways and several environmental edge computing gateways. The instruction generation module is electrically connected with several switch driving devices. The data analysis module is provided with a data analysis model. The automatic control module is provided with an automatic control model. The network detection module is provided with a network detection model.
[0013] Furthermore, the control center is provided with a preprocessing unit, a model training unit, a model deployment unit and a database unit which are connected in sequence.
[0014] A smart street lamp automatic control method, based on a smart street lamp automatic control system, the method comprises the following steps:
[0015] Based on the trusted institution, the edge computing gateway is key-generated and identity-registered, and the public-private key pair and signature information of each edge computing gateway are obtained. The private key and signature information in the public-private key pair are sent to the corresponding edge computing gateway, and the public key in the public-private key pair is published to the control center.
[0016] Based on the control center, build data analysis models, automatic control models and network detection models, and deploy the data analysis models, automatic control models and network detection models to each edge computing gateway with successful identity registration;
[0017] Based on the edge computing base station, the real-time monitoring data of the smart street lamps in the smart street lamp unit and the real-time auxiliary data of the third-party data platform are collected, and the data analysis model is used to perform data analysis based on the real-time monitoring data and real-time auxiliary data to obtain real-time data analysis results;
[0018] Based on the edge computing base station, according to the real-time data analysis results, the automatic control model is used to perform automatic control, obtain the real-time automatic control strategy, generate real-time automatic control instructions according to the real-time automatic control strategy, and control the corresponding switch cabinet and smart street lamp according to the real-time automatic control instructions;
[0019] Based on the edge computing base station, the real-time network signal data of the current network channel between the smart street light unit and the control center is collected, and the network detection model is used to perform network detection based on the real-time network signal data to obtain real-time network detection results;
[0020] If the real-time network detection result is normal, the real-time monitoring data, the real-time data analysis results and the real-time automatic control strategy are compressed and packaged to obtain a real-time compressed package, and then proceed to the next step; otherwise, the current network channel is switched and the network detection step is repeated;
[0021] Based on the edge computing base station, the real-time compressed package is encrypted and signed according to the private key and signature information in the public-private key pair, and the encrypted real-time compressed package and signature data are obtained, and uploaded to the control center through the current network channel;
[0022] Based on the control center, a trusted organization is called to perform signature verification on the signature data. After the signature verification is passed, the encrypted real-time compressed package is decrypted according to the public key in the public-private key pair to obtain the decrypted real-time compressed package, and the decrypted real-time compressed package is stored.
[0023] Furthermore, based on the control center, a data analysis model, an automatic control model, and a network detection model are constructed, and the data analysis model, the automatic control model, and the network detection model are deployed to each edge computing gateway where the identity is successfully registered, including the following steps:
[0024] Based on the control center, some historical monitoring data and some historical auxiliary data from the third-party data platform are collected, and pre-processed and randomly spliced to obtain some pre-processed data analysis samples;
[0025] Based on the control center, according to several pre-processed data analysis samples, a deep learning algorithm is used to build a data analysis model and generate several historical data analysis results;
[0026] Based on the control center, the automatic control model is constructed using the reinforcement learning algorithm according to the analysis results of several historical data and the preset automatic control strategy;
[0027] Based on the control center, a number of historical network signal data are collected and preprocessed to obtain a number of preprocessed historical network signal data;
[0028] Based on the control center, a network detection model is constructed using a deep learning algorithm based on some pre-processed historical network signal data;
[0029] Based on the control center, obtain the model metadata of the data analysis model, automatic control model and network detection model, and send the model metadata to each edge computing gateway whose identity is successfully registered;
[0030] Based on the edge computing gateway, the corresponding data analysis model, automatic control model and network detection model are deployed according to the model metadata.
[0031] Furthermore, based on the control center, according to some pre-processed historical network signal data, a network detection model is constructed using a deep learning algorithm, including the following steps:
[0032] Based on the control center, a network signal dynamic sub-model is constructed according to the data parameters of the pre-processed historical network signal data;
[0033] Based on the control center, according to a number of pre-processed historical network signal data, a network signal dynamic sub-model is used to generate a number of historical network signal dynamic data;
[0034] Based on the control center, a network detection model is constructed using a deep learning algorithm based on several pre-processed historical network signal data and the corresponding historical network signal dynamic data.
[0035] Furthermore, the data analysis model is built based on the RF-BiSLTM algorithm; the automatic control model is built based on the DQN algorithm; and the network detection model is built based on the MLP-Attention algorithm.
[0036] Furthermore, according to the real-time automatic control strategy, a real-time automatic control instruction is generated, and according to the real-time automatic control instruction, the corresponding switch cabinet and the smart street lamp are controlled, including the following steps:
[0037] Based on the edge computing gateway, according to the real-time automatic control strategy, real-time automatic control instructions including real-time street lamp brightness adjustment instructions and real-time street lamp switch control instructions are generated;
[0038] Sending real-time street light brightness adjustment instructions to the corresponding smart street light controller, and sending real-time automatic control instructions to the corresponding switch drive device;
[0039] Based on the switch driving device, according to the real-time street light switch control instruction, the control switch of the corresponding smart street light in the switch cabinet is controlled to be turned on or off;
[0040] The controller based on the smart street lamp adjusts the brightness of the corresponding smart street lamp according to the real-time street lamp brightness adjustment instruction.
[0041] The beneficial effects of the present invention are:
[0042] The present invention discloses an automatic control system and method for smart street lamps. The edge computing technology is adopted to deploy a data analysis model, an automatic control model and a network detection model on an edge computing gateway, thereby realizing localized processing of data, reducing network delay, and improving response speed and data processing capability. In the process of data transmission, an asymmetric encryption algorithm and a digital signature technology are adopted to encrypt and sign the data to ensure the security of data transmission. Through the network detection model, real-time detection of network signals is realized, and network channels are automatically switched when the network is abnormal, thereby ensuring network stability and transmission reliability. Through the data analysis model, the monitoring data of the smart street lamps is analyzed in combination with other auxiliary data such as weather, traffic, and pedestrian flow, thereby improving the degree of intelligence and analysis accuracy, and providing support for the generation of automatic control strategies. Through the automatic control model, a real-time automatic control strategy is generated, and dynamic adjustment of the control strategy is realized. The strategy has the ability to dynamically adjust according to the real-time environment and demand, thereby avoiding energy waste and improving lighting effects and control flexibility. The system architecture is flexible, easy to expand and maintain, and suitable for large-scale smart street lamp networks.
[0043] Other beneficial effects of the present invention will be further described in the specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 It is a structural block diagram of the intelligent street lamp automatic control system in the present invention.
[0045] Figure 2 It is a flowchart of the intelligent street lamp automatic control method in the present invention. DETAILED DESCRIPTION
[0046] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.
[0047] Embodiment 1:
[0048] like Figure 1 As shown, this embodiment provides a smart street light automatic control system, including a control center, a trusted organization and a number of smart street light units. The control center and the trusted organization are respectively connected to the smart street light units in communication, and the control center is also connected to the trusted organization in communication. Each smart street light unit is connected to an external third-party data platform in communication.
[0049] The trusted institution is used to generate keys and register identities for edge computing gateways, obtain the public-private key pair and signature information of the edge computing gateway in each smart street light unit, send the private key and signature information in the public-private key pair to the corresponding edge computing gateway, and publish the public key in the public-private key pair to the control center;
[0050] The control center is used to build data analysis models, automatic control models and network detection models, and deploy the data analysis models, automatic control models and network detection models to the edge computing gateway of each smart street light unit with successful identity registration; call the trusted institution to perform signature verification on the signature data. After the signature verification is passed, the encrypted real-time compressed package is decrypted according to the public key in the public-private key pair to obtain the decrypted real-time compressed package, and the decrypted real-time compressed package is stored;
[0051] The smart street light unit is used to collect real-time monitoring data of the smart street lights in the smart street light unit and real-time auxiliary data of the third-party data platform, and use the data analysis model to perform data analysis based on the real-time monitoring data and real-time auxiliary data to obtain real-time data analysis results; according to the real-time data analysis results, use the automatic control model to perform automatic control to obtain a real-time automatic control strategy, generate real-time automatic control instructions based on the real-time automatic control strategy, and control the corresponding switch cabinet and smart street lights according to the real-time automatic control instructions; collect the real-time network signal data of the current network channel between the smart street light unit and the control center, and use the network detection model to perform network detection based on the real-time network signal data to obtain real-time network detection results; compress and package the real-time monitoring data, real-time data analysis results and real-time automatic control strategy to obtain a real-time compressed package; encrypt and sign the real-time compressed package according to the private key and signature information in the public-private key pair to obtain the encrypted real-time compressed package and signature data, and upload them to the control center through the current network channel.
[0052] Preferably, the smart street light unit includes an edge computing base station, a switch cabinet and several smart street lights. The edge computing base station is electrically connected to the switch cabinet and the several smart street lights, respectively, and the edge computing base station is communicatively connected to the controller, control center, trusted organization and external third-party data platform of the smart street light, respectively.
[0053] Preferably, the edge computing base station includes an edge computing gateway, several electric signal edge computing gateways, several environmental edge computing gateways and several switch driving devices. The edge computing gateway is electrically connected to all electric signal edge computing gateways, all environmental edge computing gateways and all switch driving devices respectively, and the edge computing gateway is respectively communicated with the controllers, control center, trusted institutions and external third-party data platforms of all smart street lamps. Each electric signal edge computing gateway is electrically connected to the power supply line of a smart street lamp in the switch cabinet one by one, each environmental edge computing gateway is arranged at a smart street lamp one by one, and each switch driving device is electrically connected to the control switch of a smart street lamp in the switch cabinet one by one;
[0054] The electrical signal edge computing gateway is used to collect real-time electrical signal data of smart street lights in the power supply line of the smart street lights in the switch cabinet;
[0055] Environmental edge computing gateway, used to collect real-time environmental data of smart street lights in the setting environment of smart street lights;
[0056] The edge computing gateway is used to generate real-time monitoring data of the corresponding smart street lamps based on real-time electrical signal data and real-time environmental data; collect real-time auxiliary data from a third-party data platform, and use a data analysis model to perform data analysis based on the real-time monitoring data and real-time auxiliary data to obtain real-time data analysis results; use an automatic control model to perform automatic control based on the real-time data analysis results to obtain a real-time automatic control strategy, and generate a real-time automatic control instruction based on the real-time automatic control strategy; and control the corresponding smart street lamps based on the real-time automatic control instructions;
[0057] The switch driving device is used to control the control switch of the corresponding switch cabinet according to the real-time automatic control instruction.
[0058] Preferably, the edge computing gateway is provided with a data transmission module, a network detection module, a data processing module, an encryption and decryption module, a digital signature module, a data analysis module, an automatic control module and an instruction generation module which are connected in sequence. The data transmission module is respectively communicated with the controller, the control center, the trusted organization and the external third-party data platform of the smart street lamp. The data processing module is respectively electrically connected with several electrical signal edge computing gateways and several environmental edge computing gateways. The instruction generation module is electrically connected with several switch driving devices. The data analysis module is provided with a data analysis model. The automatic control module is provided with an automatic control model. The network detection module is provided with a network detection model.
[0059] The data transmission module is used to receive the private key and signature information in the public-private key pair sent by the trusted institution; receive the model metadata of the data analysis model, automatic control model and network detection model sent by the control center; send the real-time automatic control command to the controller of the smart street lamp; upload the encrypted real-time compressed package and signature data to the control center;
[0060] The network detection module is used to collect the real-time network signal data of the current network channel between the smart street light unit and the control center, and use the network detection model to perform network detection based on the real-time network signal data to obtain real-time network detection results; according to the real-time network detection results, the current network channel is switched;
[0061] The data processing module is used to compress and package the real-time monitoring data, the real-time data analysis results and the real-time automatic control strategy to obtain a real-time compressed package;
[0062] The encryption and decryption module is used to encrypt the real-time compressed package according to the private key in the public-private key pair to obtain the encrypted real-time compressed package; when receiving the model metadata sent by the control center, the encrypted model metadata is usually transmitted, and the encrypted model metadata is decrypted according to the private key in the public-private key pair to obtain the decrypted model metadata;
[0063] The digital signature module is used to sign the encrypted real-time compressed package according to the signature information to obtain the signature data of the encrypted real-time compressed package;
[0064] The data analysis module is used to perform data analysis using a data analysis model based on the real-time monitoring data sent by the electrical signal edge computing gateway and the environmental edge computing gateway and the real-time auxiliary data sent by the third-party data platform to obtain real-time data analysis results;
[0065] The automatic control module is used to perform automatic control based on the real-time data analysis results and use the automatic control model to obtain a real-time automatic control strategy;
[0066] The instruction generation module is used to generate real-time automatic control instructions according to the real-time automatic control strategy.
[0067] Preferably, the control center is provided with a preprocessing unit, a model training unit, a model deployment unit and a database unit connected in sequence;
[0068] The preprocessing unit is used to preprocess and randomly splice a number of historical monitoring data and a number of historical auxiliary data from a third-party data platform to obtain a number of preprocessed data analysis samples; and preprocess a number of historical network signal data to obtain a number of preprocessed historical network signal data;
[0069] The model training unit is used to construct a data analysis model based on a number of pre-processed data analysis samples using a deep learning algorithm and generate a number of historical data analysis results; to construct an automatic control model based on a number of historical data analysis results and a preset automatic control strategy using a reinforcement learning algorithm; and to construct a network detection model based on a number of pre-processed historical network signal data using a deep learning algorithm;
[0070] A model deployment unit, used to obtain model metadata of a data analysis model, an automatic control model, and a network detection model, and send the model metadata to each edge computing gateway whose identity is successfully registered;
[0071] The database unit is used to store the decrypted real-time compressed package and model metadata.
[0072] Embodiment 2:
[0073] like Figure 2 As shown, this embodiment provides a smart street lamp automatic control method, based on the smart street lamp automatic control system, the method includes the following steps:
[0074] S1: Based on the trusted institution, key generation and identity registration are performed for the edge computing gateway, and the public-private key pair and signature information of each edge computing gateway are obtained. The private key and signature information in the public-private key pair are sent to the corresponding edge computing gateway, and the public key in the public-private key pair is published to the control center, including the following steps:
[0075] S1-1: Based on the trusted institution, collect the attribute information and device ID of the edge computing gateway, initialize the key, and generate public parameters , Master Key and the initial key ; The formula is:
[0076]
[0077] In the formula, is a public parameter; is the master key; is the initial key; Integer domain A random number; Both are target hash functions; Both are cyclic groups The random number used as the generator in ; is a random number Bilinear mapping of ;
[0078] S1-2: Based on public parameters , Master Key , initial key And the attribute information of the edge computing gateway , generate the corresponding public-private key pair of the edge computing gateway, the formula is:
[0079]
[0080] In the formula, Edge computing gateway The private key of Integer domain A random number; Edge computing gateway The private key parameters; Public parameters The target hash hash function; Indicator for edge computing gateway; is the master key; is the initial key; Edge computing gateway 's public key; Both are cyclic groups The random number used as the generator in ; Edge computing gateway Attribute information of Edge computing gateway The public key parameters of
[0081] S1-3: According to the private key in the public-private key pair and the corresponding device ID, perform identity registration to obtain the signature information of the corresponding edge computing gateway. The formula is:
[0082]
[0083] In the formula, is a random number; Edge computing gateway Registration parameters; Edge computing gateway The signature ID of and the corresponding Signature information ; Hash function for target hash; Edge computing gateway Device ID; Edge computing gateway The private key of is a prime number order; It is the base point of the prime domain; is the remainder function;
[0084] S1-4: Send the private key and signature information in the public-private key pair to the corresponding edge computing gateway, and publish the public key in the public-private key pair to the control center;
[0085] S2: Based on the control center, build a data analysis model, an automatic control model, and a network detection model, and deploy the data analysis model, the automatic control model, and the network detection model to each edge computing gateway where the identity is successfully registered, including the following steps:
[0086] S2-1: Based on the control center, some historical monitoring data and some historical auxiliary data from the third-party data platform are collected, and pre-processed and randomly spliced to obtain some pre-processed data analysis samples;
[0087] S2-2: Based on the control center, according to several pre-processed data analysis samples, the Random Forest (RF)-Bi-directional Long Short-Term Memory (BiLSTM) algorithm is used to build a data analysis model and generate several historical data analysis results;
[0088] The RF module uses the internal Classification and Regression Tree (CART) to screen the key features of the input data and extract the key features related to the data labels. The BiLSTM network uses a multi-layer hidden layer structure to explore the potential connection between key features and data labels. It trains its own network structure through a large number of key features and predicts new data features, thus achieving fast, efficient and accurate prediction of data labels.
[0089] S2-3: Based on the control center, according to the analysis results of several historical data and the preset automatic control strategy, the Deep Q Network (DQN) algorithm is used to build an automatic control model, including the following steps:
[0090] S2-3-1: Use the automatic control strategy generation of smart street lights as the simulation environment of the DQN algorithm to build intelligent agents and experience replay pools;
[0091] S2-3-2: Define the state space of the DQN algorithm according to each analysis type corresponding to the historical data analysis results, and the parameters of the state space correspond to each analysis type;
[0092] S2-3-3: Define the action space of the DQN algorithm according to the actions that need to be output by the automatic control, including turning on or off any smart street light, adjusting the brightness of any smart street light, etc.
[0093] S2-3-4: Based on the possible impact of each action in the action space, define the reward function of the DQN algorithm to evaluate the quality or impact of the action;
[0094] S2-3-5: Construct the input layer, several hidden layers, and output layer of the deep Q network, connect the input layer to the state space, and connect the output layer to the action space;
[0095] S2-3-6: Based on the state space, action space and reward function, according to the analysis results of several historical data, the deep Q network and the agent are optimized and trained, an automatic control model is constructed, and several automatic control experiences generated are stored in the experience replay pool;
[0096] S2-4: Based on the control center, collect some historical network signal data, and perform preprocessing to obtain some preprocessed historical network signal data;
[0097] S2-5: Based on the control center, according to some pre-processed historical network signal data, a network detection model is constructed using the multilayer perceptron (MLP)-Attention algorithm, including the following steps:
[0098] S2-5-1: Based on the control center, a network signal dynamic sub-model is constructed according to the data parameters of the pre-processed historical network signal data;
[0099] The network signal dynamic sub-model includes the signal quality dynamic sub-model, the data transmission rate dynamic sub-model, the network delay dynamic sub-model and the network stability dynamic sub-model; it is used to analyze the real situation of the network signal, reflect the quality of the network channel, and provide support for subsequent network switching;
[0100] The formula of the signal quality dynamic sub-model is:
[0101]
[0102] In the formula, is the signal quality data; Calculate the function for signal quality; is the received signal strength value;
[0103] The formula for the data transmission rate dynamic sub-model is:
[0104]
[0105] In the formula, is the data transmission rate data; The amount of data transferred; is the transmission time;
[0106] The formula of the network delay dynamic sub-model is:
[0107]
[0108] In the formula, Delay data for the network; is the sending time; is the signal propagation time; is the signal processing time;
[0109] The formula of the dynamic sub-model of network stability is:
[0110]
[0111] In the formula, Network stability data; is the number of network interruptions; The total number of connection attempts;
[0112] S2-5-2: Based on the control center, according to a number of pre-processed historical network signal data, using the network signal dynamic sub-model, a number of historical network signal dynamic data are generated;
[0113] S2-5-3: Based on the control center, the network detection model is constructed using the MLP-Attention algorithm according to some pre-processed historical network signal data and the corresponding historical network signal dynamic data;
[0114] As a fully connected layer, the MLP network is characterized by that all neurons between layers are interconnected, which can extract data features of network signal data and network signal dynamic data, perform feature fusion, and better characterize network conditions; the Attention mechanism provides attention weights between different features, increases the influence of key features in model analysis, and improves model accuracy;
[0115] S2-6: Based on the control center, obtain the model metadata of the data analysis model, the automatic control model, and the network detection model, and send the model metadata to each edge computing gateway whose identity is successfully registered;
[0116] S2-7: Based on the edge computing gateway, deploy the corresponding data analysis model, automatic control model and network detection model according to the model metadata;
[0117] S3: Based on the edge computing base station, collect the real-time monitoring data of the smart street lamp in the smart street lamp unit and the real-time auxiliary data of the third-party data platform, and use the data analysis model to perform data analysis based on the real-time monitoring data and real-time auxiliary data to obtain real-time data analysis results, including the following steps:
[0118] S3-1: Based on the edge computing base station, collect the real-time monitoring data of the smart street lamps in the smart street lamp unit and the real-time auxiliary data of the third-party data platform;
[0119] Real-time monitoring data includes real-time electrical signal data of smart street lights collected by the electrical signal edge computing gateway and real-time environmental data of smart street lights collected by the environmental edge computing gateway. Real-time electrical signal data includes real-time current, real-time voltage, real-time power, etc. Real-time environmental data includes real-time light intensity, real-time temperature, real-time humidity, etc. of the environment where the smart street lights are located; real-time auxiliary data includes real-time weather data, real-time traffic data, real-time pedestrian flow data, etc.;
[0120] S3-2: Based on the real-time monitoring data and real-time auxiliary data, use the data analysis model to perform data analysis to obtain real-time data analysis results, including the following steps:
[0121] S3-2-1: Use the RF structure trained in the data analysis model to extract the feature contribution of several real-time candidate features in the real-time monitoring data and real-time auxiliary data;
[0122] The formula is:
[0123]
[0124] In the formula, For the Feature contribution of real-time candidate features; For the Real-time candidate features in random forest The feature contribution of each tree; is the CART tree indicator; It is a real-time alternative characteristic indicator; is the total number of CARTs;
[0125]
[0126] In the formula, CART tree node for random forest m ,node and nodes r The Gini index of CART tree node m Medium Category The proportion of is the total number of categories; m , , r is the node indicator; is the category indicator;
[0127] S3-2-2: normalizing the feature contributions of several real-time candidate features to obtain corresponding normalized feature contributions;
[0128] The formula is:
[0129]
[0130] In the formula, It is the contribution of the feature after normalization; J is the total number of real-time candidate features;
[0131] S3-2-3: Generate feature selection standard values for several real-time candidate features based on the normalized feature contribution;
[0132] The formula is:
[0133]
[0134] In the formula, For the Feature selection criteria values for real-time candidate features; For the The normalized feature contribution of real-time candidate features; is an alternative characteristic indicator;
[0135] S3-2-4: sort the real-time candidate features in descending order according to the feature selection standard value, and select the first N real-time candidate features as real-time key features to obtain N real-time key features, where N is the total number of real-time key features;
[0136] S3-2-5: Based on N real-time key features, use the BiLSTM structure of the data analysis model to perform data analysis and obtain real-time data analysis results;
[0137] S4: Based on the edge computing base station, according to the real-time data analysis results, use the automatic control model to perform automatic control, obtain the real-time automatic control strategy, generate real-time automatic control instructions according to the real-time automatic control strategy, and control the corresponding switch cabinet and smart street lamp according to the real-time automatic control instructions, including the following steps:
[0138] S4-1: Based on the edge computing base station, according to the real-time data analysis results, use the automatic control model to perform automatic control and obtain a real-time automatic control strategy, including the following steps:
[0139] S4-1-1: According to the real-time data analysis results, extract several matching historical automatic control experiences from the experience playback pool of the automatic control model;
[0140] S4-1-2: Update the action space of the automatic control model based on some historical automatic control experience to obtain an updated action space ,in, For the updated Action value, is the action indicator, is the total number of action space dimensions, For the updated Action value;
[0141] S4-1-3: Update the state space of the automatic control model according to the real-time data analysis results to obtain the updated state space ,in, For the updated Status value, is the state indicator; is the total number of state space dimensions, For the updated Status value;
[0142] S4-1-4: The state space to be updated As input to the automatic control model, a deep Q-network is used to generate an updated action space The Q value of each possible action in;
[0143] S4-1-5: Use the reward function to obtain the reward value of each possible action in the updated action space, and update the Q value of the possible action according to the reward value to obtain the updated Q value of the possible action;
[0144] The formula is:
[0145]
[0146] In the formula, The updated status value and the updated action value The corresponding updated Q value; Status value and action value The corresponding predicted Q value; is the learning rate; is the highest predicted Q value; It is a comprehensive indicator; Update weights for state values;
[0147] S4-1-6: Repeat the above steps until the iteration number threshold is reached, use the greedy strategy, take the possible action corresponding to the highest updated Q value as the execution action, and output the execution action as a real-time automatic control solution; for example, the real-time automatic control solution includes turning off smart street lights A and B, turning off smart street lights C and D, reducing the brightness of smart street lights E and F, and increasing the brightness of smart street lights G and H;
[0148] S4-2: Generate real-time automatic control instructions according to the real-time automatic control strategy, and control the corresponding switch cabinet and smart street lamp according to the real-time automatic control instructions, including the following steps:
[0149] S4-2-1: Based on the edge computing gateway, according to the real-time automatic control strategy, generate real-time automatic control instructions including real-time street lamp brightness adjustment instructions and real-time street lamp switch control instructions;
[0150] S4-2-2: Sending a real-time street light brightness adjustment instruction to a corresponding smart street light controller, and sending a real-time automatic control instruction to a corresponding switch drive device;
[0151] S4-2-3: Based on the switch driving device, according to the real-time street light switch control instruction, control the on or off of the control switch of the corresponding smart street light in the switch cabinet;
[0152] S4-2-4: Based on the controller of the smart street lamp, the brightness of the corresponding smart street lamp is adjusted according to the real-time street lamp brightness adjustment instruction;
[0153] S5: Based on the edge computing base station, collect the real-time network signal data of the current network channel between the smart street light unit and the control center, and use the network detection model to perform network detection based on the real-time network signal data to obtain real-time network detection results;
[0154] S6: If the real-time network detection result is normal, the real-time monitoring data, the real-time data analysis result and the real-time automatic control strategy are compressed and packaged to obtain a real-time compressed package, and then proceed to the next step; otherwise, the current network channel is switched and the network detection step is repeated;
[0155] S7: Based on the edge computing base station, the real-time compressed package is encrypted and signed according to the private key and signature information in the public-private key pair, the encrypted real-time compressed package and signature data are obtained, and uploaded to the control center through the current network channel;
[0156] The formula is:
[0157]
[0158] In the formula, Edge computing gateway The encrypted real-time compressed package uploaded to the control center; is an asymmetric encryption function; For real-time compression packages; Edge computing gateway The private key of Indicator for edge computing gateway;
[0159]
[0160] In the formula, is a random number; Hash function for target hash; Edge computing gateway Registration parameters; Edge computing gateway The signature ID of Edge computing gateway The encrypted real-time compressed package; Edge computing gateway The device ID of ; Both are edge computing gateways The signature parameters of is a prime number order; It is the base point of the prime domain;
[0161] S8: Based on the control center, the trusted institution is called to perform signature verification on the signature data. After the signature verification is passed, the encrypted real-time compressed package is decrypted according to the public key in the public-private key pair to obtain the decrypted real-time compressed package, and the decrypted real-time compressed package is stored;
[0162] The formula is:
[0163]
[0164] In the formula, Edge computing gateway The signature verification parameters of Edge computing gateway 's public key; Edge computing gateway The encrypted real-time compressed package; if the left formula is equal to the right formula, the signature verification is successful;
[0165]
[0166] In the formula, Edge computing gateway The decrypted real-time compressed package; is an asymmetric decryption function; Edge computing gateway 's public key; Edge computing gateway Encrypted real-time compression package.
[0167] The present invention discloses an automatic control system and method for smart street lamps. The edge computing technology is adopted to deploy a data analysis model, an automatic control model and a network detection model on an edge computing gateway, thereby realizing localized processing of data, reducing network delay, and improving response speed and data processing capability. In the process of data transmission, an asymmetric encryption algorithm and a digital signature technology are adopted to encrypt and sign the data to ensure the security of data transmission. Through the network detection model, real-time detection of network signals is realized, and network channels are automatically switched when the network is abnormal, thereby ensuring network stability and transmission reliability. Through the data analysis model, the monitoring data of the smart street lamps is analyzed in combination with other auxiliary data such as weather, traffic, and pedestrian flow, thereby improving the degree of intelligence and analysis accuracy, and providing support for the generation of automatic control strategies. Through the automatic control model, a real-time automatic control strategy is generated, and dynamic adjustment of the control strategy is realized. The strategy has the ability to dynamically adjust according to the real-time environment and demand, thereby avoiding energy waste and improving lighting effects and control flexibility. The system architecture is flexible, easy to expand and maintain, and suitable for large-scale smart street lamp networks.
[0168] The present invention is not limited to the above optional implementations, and anyone can derive other various forms of products under the enlightenment of the present invention. The above specific implementations should not be understood as limiting the scope of protection of the present invention. The scope of protection of the present invention should be based on the definition in the claims, and the description can be used to interpret the claims.
Claims
1. A smart street lamp automatic control system, characterized by: It includes a control center, a trusted institution and a plurality of smart street light units, wherein the control center and the trusted institution are respectively connected to the plurality of smart street light units in communication, and the control center is also connected to the trusted institution in communication, and each of the smart street light units is connected to an external third-party data platform in communication; The smart street lamp unit includes an edge computing base station, a switch cabinet and several smart street lamps. The edge computing base station is electrically connected to the switch cabinet and the several smart street lamps respectively, and the edge computing base station is respectively communicated with the controller, control center, trusted organization and external third-party data platform of the smart street lamp; The edge computing base station includes an edge computing gateway, several electric signal edge computing gateways, several environmental edge computing gateways and several switch driving devices. The edge computing gateway is electrically connected to all electric signal edge computing gateways, all environmental edge computing gateways and all switch driving devices respectively, and the edge computing gateway is respectively communicated with the controllers, control center, trusted institutions and external third-party data platforms of all smart street lamps. Each of the electric signal edge computing gateways is electrically connected to the power supply line of a smart street lamp in the switch cabinet one by one, each of the environmental edge computing gateways is arranged one by one at a smart street lamp, and each of the switch driving devices is electrically connected to the control switch of a smart street lamp in the switch cabinet one by one; The edge computing gateway is provided with a data transmission module, a network detection module, a data processing module, an encryption and decryption module, a digital signature module, a data analysis module, an automatic control module and an instruction generation module which are connected in sequence. The data transmission module is respectively connected to the controller, the control center, the trusted institution and the external third-party data platform of the smart street lamp in communication. The data processing module is respectively electrically connected to a number of electrical signal edge computing gateways and a number of environmental edge computing gateways. The instruction generation module is electrically connected to a number of switch driving devices. The data analysis module is provided with a data analysis model, the automatic control module is provided with an automatic control model, and the network detection module is provided with a network detection model. The system is used to implement a smart street lamp automatic control method, comprising the following steps: Based on the trusted institution, the edge computing gateway is key-generated and identity-registered, and the public-private key pair and signature information of each edge computing gateway are obtained. The private key and signature information in the public-private key pair are sent to the corresponding edge computing gateway, and the public key in the public-private key pair is published to the control center. Based on the control center, build data analysis models, automatic control models and network detection models, and deploy the data analysis models, automatic control models and network detection models to each edge computing gateway with successful identity registration; Based on the edge computing base station, the real-time monitoring data of the smart street lamps in the smart street lamp unit and the real-time auxiliary data of the third-party data platform are collected, and the data analysis model is used to perform data analysis based on the real-time monitoring data and real-time auxiliary data to obtain real-time data analysis results; Based on the edge computing base station, according to the real-time data analysis results, the automatic control model is used to perform automatic control, obtain the real-time automatic control strategy, generate real-time automatic control instructions according to the real-time automatic control strategy, and control the corresponding switch cabinet and smart street lamp according to the real-time automatic control instructions; Based on the edge computing base station, the real-time network signal data of the current network channel between the smart street light unit and the control center is collected, and the network detection model is used to perform network detection based on the real-time network signal data to obtain real-time network detection results; If the real-time network detection result is normal, the real-time monitoring data, the real-time data analysis results and the real-time automatic control strategy are compressed and packaged to obtain a real-time compressed package, and then proceed to the next step; otherwise, the current network channel is switched and the network detection step is repeated; Based on the edge computing base station, the real-time compressed package is encrypted and signed according to the private key and signature information in the public-private key pair, and the encrypted real-time compressed package and signature data are obtained, and uploaded to the control center through the current network channel; Based on the control center, a trusted organization is called to perform signature verification on the signature data. After the signature verification is passed, the encrypted real-time compressed package is decrypted according to the public key in the public-private key pair to obtain the decrypted real-time compressed package, and the decrypted real-time compressed package is stored.
2. According to claim 1, the intelligent street lamp automatic control system is characterized in that: The control center is provided with a preprocessing unit, a model training unit, a model deployment unit and a database unit which are connected in sequence.
3. A smart street light automatic control method, based on the smart street light automatic control system according to any one of claims 1-2, characterized in that: The method comprises the following steps: Based on the trusted institution, the edge computing gateway is key-generated and identity-registered, and the public-private key pair and signature information of each edge computing gateway are obtained. The private key and signature information in the public-private key pair are sent to the corresponding edge computing gateway, and the public key in the public-private key pair is published to the control center. Based on the control center, build data analysis models, automatic control models and network detection models, and deploy the data analysis models, automatic control models and network detection models to each edge computing gateway with successful identity registration; Based on the edge computing base station, the real-time monitoring data of the smart street lamps in the smart street lamp unit and the real-time auxiliary data of the third-party data platform are collected, and the data analysis model is used to perform data analysis based on the real-time monitoring data and real-time auxiliary data to obtain real-time data analysis results; Based on the edge computing base station, according to the real-time data analysis results, the automatic control model is used to perform automatic control, obtain the real-time automatic control strategy, generate real-time automatic control instructions according to the real-time automatic control strategy, and control the corresponding switch cabinet and smart street lamp according to the real-time automatic control instructions; Based on the edge computing base station, the real-time network signal data of the current network channel between the smart street light unit and the control center is collected, and the network detection model is used to perform network detection based on the real-time network signal data to obtain real-time network detection results; If the real-time network detection result is normal, the real-time monitoring data, the real-time data analysis results and the real-time automatic control strategy are compressed and packaged to obtain a real-time compressed package, and then proceed to the next step; otherwise, the current network channel is switched and the network detection step is repeated; Based on the edge computing base station, the real-time compressed package is encrypted and signed according to the private key and signature information in the public-private key pair, and the encrypted real-time compressed package and signature data are obtained, and uploaded to the control center through the current network channel; Based on the control center, a trusted organization is called to perform signature verification on the signature data. After the signature verification is passed, the encrypted real-time compressed package is decrypted according to the public key in the public-private key pair to obtain the decrypted real-time compressed package, and the decrypted real-time compressed package is stored.
4. The method for automatically controlling a smart street lamp according to claim 3 is characterized in that: Based on the control center, build a data analysis model, an automatic control model, and a network detection model, and deploy the data analysis model, the automatic control model, and the network detection model to each edge computing gateway where the identity is successfully registered, including the following steps: Based on the control center, some historical monitoring data and some historical auxiliary data from the third-party data platform are collected, and pre-processed and randomly spliced to obtain some pre-processed data analysis samples; Based on the control center, according to several pre-processed data analysis samples, a deep learning algorithm is used to build a data analysis model and generate several historical data analysis results; Based on the control center, the automatic control model is constructed using the reinforcement learning algorithm according to the analysis results of several historical data and the preset automatic control strategy; Based on the control center, a number of historical network signal data are collected and preprocessed to obtain a number of preprocessed historical network signal data; Based on the control center, a network detection model is constructed using a deep learning algorithm based on some pre-processed historical network signal data; Based on the control center, obtain the model metadata of the data analysis model, automatic control model and network detection model, and send the model metadata to each edge computing gateway whose identity is successfully registered; Based on the edge computing gateway, the corresponding data analysis model, automatic control model and network detection model are deployed according to the model metadata.
5. The method for automatically controlling a smart street lamp according to claim 4, characterized in that: Based on the control center, a network detection model is constructed using a deep learning algorithm based on some pre-processed historical network signal data, including the following steps: Based on the control center, a network signal dynamic sub-model is constructed according to the data parameters of the pre-processed historical network signal data; Based on the control center, according to a number of pre-processed historical network signal data, a network signal dynamic sub-model is used to generate a number of historical network signal dynamic data; Based on the control center, a network detection model is constructed using a deep learning algorithm based on several pre-processed historical network signal data and the corresponding historical network signal dynamic data.
6. The intelligent street lamp automatic control method according to claim 4 is characterized in that: The data analysis model is constructed based on the RF-BiSLTM algorithm; the automatic control model is constructed based on the DQN algorithm; and the network detection model is constructed based on the MLP-Attention algorithm.
7. The method for automatic control of a smart street lamp according to claim 3, characterized in that: According to the real-time automatic control strategy, a real-time automatic control instruction is generated, and according to the real-time automatic control instruction, the corresponding switch cabinet and smart street lamp are controlled, including the following steps: Based on the edge computing gateway, according to the real-time automatic control strategy, real-time automatic control instructions including real-time street lamp brightness adjustment instructions and real-time street lamp switch control instructions are generated; Sending real-time street light brightness adjustment instructions to the corresponding smart street light controller, and sending real-time automatic control instructions to the corresponding switch drive device; Based on the switch driving device, according to the real-time street light switch control instruction, the control switch of the corresponding smart street light in the switch cabinet is controlled to be turned on or off; The controller based on the smart street lamp adjusts the brightness of the corresponding smart street lamp according to the real-time street lamp brightness adjustment instruction.
Citation Information
Patent Citations
Lightweight data encryption method for intelligent lamp post system
CN116707993A
Smart city road lighting system
CN117042269A
5G-based smart city intelligent security system and method
CN118283548A
Centralized control system for intelligent lighting street lamp
WO2016086421A1
Dynamic data encryption
WO2020015877A1
