An adaptive data compression and transmission method and apparatus based on SSD thermal behavior in an edge network environment

Abstract

This invention belongs to the field of communication technology, and specifically relates to an adaptive data compression and transmission method and apparatus based on SSD thermal behavior in an edge network environment. Its main features include the following steps: S1, deploying an edge box device between a mobile terminal device and a local network; the mobile terminal device connects to the edge box device via a wired connection; the edge box device connects to a 5G base station via a 5G CPE (Network Premises Equipment); S2, the mobile terminal device uploads the data to be transmitted to the edge box; the edge box performs security verification on the user's identity and the data to be transmitted; if the verification is successful, proceed to step S3; otherwise, terminate the transmission and display an illegal operation message; S3, the data to be transmitted is fragmented, and each data fragment is compressed and stored using a multi-threaded parallel approach; simultaneously, the temperature of the SSD storage medium is monitored to dynamically adjust the number of parallel compression threads and the SSD storage strategy; S4, the compressed data fragments are distributed to multiple communication paths and transmitted to a private cloud according to a multi-path load balancing strategy; the integrity of the data fragment transmission is monitored synchronously, and retransmission is performed for data that fails to transmit. While ensuring the long-term safe operation of SSDs, this invention can balance system throughput and hardware lifespan, achieving the goals of high throughput, high reliability, and low latency in edge data transmission systems.

Description

Technical Field

[0001] This invention belongs to the field of communication technology, and in particular relates to an adaptive data compression and transmission method and apparatus based on SSD thermal behavior in an edge network environment. Background Technology

[0002] With the rapid development of mobile internet, IoT, and cloud computing technologies, a large amount of business data from mobile terminal devices needs to be processed and transmitted locally through edge nodes. These edge nodes often utilize SSDs with higher read / write performance to achieve lower latency and improve user experience. Meanwhile, for high-throughput data transmission at the edge, technologies such as data compression, fragmented transmission, and multi-path load balancing are commonly used to improve bandwidth utilization and transmission reliability. For example, some solutions fragment the data to be transmitted and use multi-threaded parallel compression to improve overall throughput; simultaneously, they combine multiple access links such as 5G, dedicated lines, and Wi-Fi, and load balance the data fragments based on link bandwidth, latency, and other indicators to fully utilize the resources of multiple communication paths. Furthermore, some technologies propose fragment verification and retransmission during transmission to ensure that the data ultimately arrives at the destination intact.

[0003] However, in the existing solutions mentioned above, the thermal behavior of the SSD storage media used in edge nodes and its impact on system performance and reliability are often not fully considered. In particular, multi-threaded parallel compression and high-frequency SSD read / write operations can impose significant I / O pressure and power load on the SSD in a short period of time, causing the SSD temperature to rise rapidly. When the temperature exceeds a certain threshold, the SSD will usually trigger a speed-down protection mechanism, resulting in problems such as decreased read / write performance and increased transmission latency fluctuations. In severe cases, it may even affect the lifespan of the storage media and data security. Common practices in existing technologies are mostly simple threshold alarms or passive speed-down, lacking a fine-grained dynamic adjustment mechanism based on temperature feedback, making it difficult to control the SSD within a safe temperature range in a timely and smooth manner.

[0004] Furthermore, existing edge data transmission solutions primarily rely on network-side metrics such as bandwidth, latency, and packet loss rate for multi-path load balancing, failing to integrate the SSD's current thermal state and cache load with transmission scheduling strategies for optimization. If an edge node receives a sudden surge in data traffic within a short period, the compression and write operations increase dramatically. The SSD may already be in a high-risk temperature range before significant performance degradation occurs, potentially leading to localized overheating, increased compression latency, and consequently impacting end-to-end transmission performance and reliability.

[0005] In summary, although existing technologies have adopted methods such as data fragmentation compression, multi-threaded parallel processing, multi-path load balancing, and failure retransmission in edge network environments to improve transmission efficiency and reliability, they generally lack a mechanism to adaptively and collaboratively control compression parallelism, SSD storage strategies, and transmission scheduling by combining the thermal behavior characteristics of SSDs. As a result, it is difficult to maintain high-throughput data compression and transmission capabilities while ensuring the long-term safe and reliable operation of SSDs.

[0006] Therefore, how to introduce a dynamic control method based on SSD thermal behavior in the edge network environment to achieve adaptive adjustment of data compression, caching and multipath transmission processes has become one of the technical problems that urgently need to be solved by those skilled in the art. Summary of the Invention

[0007] This invention aims to address the problems of rapid temperature rise in SSD storage media caused by multi-threaded high-concurrency operations during data compression and transmission in existing edge networks, leading to decreased write speed, latency fluctuations, shortened lifespan, and even thermal protection write stoppage. Existing solutions generally lack dynamic control methods for SSD thermal behavior, failing to effectively coordinate compression concurrency, caching strategies, and transmission scheduling, making it difficult to maintain high-efficiency data processing capabilities while ensuring SSD safety. This invention proposes an adaptive data compression and transmission method and apparatus based on SSD thermal behavior in edge network environments. By introducing a nonlinear PI temperature control algorithm based on SSD thermal behavior, it coordinates the control of the number of compression threads, adaptive caching strategies, and multi-path load balancing strategies to achieve comprehensive optimization that balances SSD safety, system throughput, and transmission reliability. Specifically, it includes the following steps:

[0008] S1. Deploy an edge box device between the mobile terminal device and the local network. The mobile terminal device is connected to the edge box device via a wired connection. The edge box device is connected to the 5G base station via the 5G CPE terminal network device.

[0009] S2. The mobile terminal device uploads the data to be transmitted to the edge box. The edge box performs security verification on the user's identity and the data to be transmitted. If the verification is successful, step S3 is executed; otherwise, the transmission is terminated and an illegal operation is prompted.

[0010] S3. The data to be transmitted is segmented and each data segment is compressed and stored in a multi-threaded parallel manner. At the same time, the temperature of the SSD storage medium is monitored to dynamically adjust the number of parallel compression threads and the SSD storage strategy.

[0011] S4. Based on the multi-path load balancing strategy, the compressed data is fragmented and distributed to multiple communication paths and transmitted to the private cloud. The integrity of the data fragment transmission is monitored synchronously, and retransmission is performed for data that fails to be transmitted.

[0012] Furthermore, the edge box device mainly includes an access control module, a fragmentation and compression module, an adaptive caching module, a transmission load control module, and a monitoring module.

[0013] Furthermore, the mobile terminal device uploads the data to be transmitted to the edge box. The edge box uses a permission verification module to perform security verification on the user's identity and the data to be transmitted using pre-configured user credentials and data signature information. Only after the verification is successful is compression and transmission allowed to continue; otherwise, the transmission is terminated and an illegal operation is prompted.

[0014] Furthermore, the data fragmentation and compression module divides the data into multiple fragments according to a predetermined size, and uses a multi-threaded parallel approach to compress the data fragments. The initial number of parallel threads can be configured based on the device's capabilities or experience.

[0015] Furthermore, the compressed data fragments are written to the SSD storage medium, and the adaptive caching module monitors the collected SSD storage medium temperature in real time and records the historical temperature change curves.

[0016] Furthermore, the SSD thermal behavior is approximated as a first-order kinetic system. Using the real-time SSD temperature as feedback, a nonlinear PI controller is employed to dynamically adjust the number of parallel compression threads and the SSD storage strategy. This ensures the SSD operates within a safe temperature range while maximizing compression throughput. The change in SSD temperature over time is approximated as:

[0017]

[0018] Where T is the measured SSD temperature, T env τ is the ambient temperature, k is the thermal time constant, k is the average contribution of each concurrent thread to the temperature rise, and N is the current number of threads.

[0019] Furthermore, the nonlinear PI temperature control algorithm sets the target control temperature of the SSD to T. set The highest temperature allowed by the hardware is T. max Shift down by a safety margin Δ, and define the temperature deviation e at the current moment. t =T set -T t The number of threads N is updated in discrete time:

[0020]

[0021] Wherein, α×(T) set -T t The parameter represents a proportional element. When the SSD temperature is lower than the target temperature, the number of threads is increased appropriately, and when the temperature is higher than the target temperature, the number of threads is decreased appropriately. This is the integral term, used to eliminate long-term steady-state deviations and bring the average temperature closer to the target value. -β×(T t -T set ) 3 As a non-linear suppression term, when the temperature exceeds the target value and the deviation increases, the suppression strength is amplified in a cubic form, thereby rapidly reducing the number of threads when approaching or exceeding the threshold to avoid triggering hardware thermal protection.

[0022] Furthermore, to ensure availability and stability, boundary and saturation constraints are applied to the number of threads N, and the magnitude of each update is limited to avoid performance fluctuations caused by sudden changes in the number of threads. When N reaches its upper or lower limits, an anti-integral saturation strategy is implemented, freezing or reversing the integral term. When the actual SSD temperature is detected to exceed the maximum temperature T... max The N is forced to drop to a lower safe level, and can only be increased again after the temperature returns to the safe range with a margin.

[0023] Furthermore, considering the noise inherent in temperature sensors and the inherent inertia of SSD thermal response, the adaptive caching module performs exponential smoothing or low-pass filtering on the acquired temperature signal, updating the control every 0.5-2 seconds. Initial parameters α, β, and γ can be given empirically within a reasonable range. τ and k are identified through simple step experiments by recording the time series of "temperature-thread count-throughput," and the control gain is fine-tuned based on this to balance response speed and avoid oscillations.

[0024] Furthermore, the transmission load control module dynamically adjusts the allocation ratio of data fragments among the paths based on the real-time bandwidth and packet loss rate information of each communication path, so as to optimize network resource utilization and ensure high-reliability transmission.

[0025] Furthermore, during transmission, the monitoring module monitors the temperature of the SSD storage medium and feeds it back to the adaptive caching module in real time. In scenarios where the SSD exhibits segmented throughput behavior (such as a sudden drop in write rate after the SLC cache is exhausted), the monitoring module can also incorporate feedforward corrections based on throughput fluctuations or additional rate-limiting strategies into the temperature control law, taking into account abrupt changes in throughput and I / O latency. This prevents the maintenance of a high thread count when the hardware has already entered a performance degradation phase, further enhancing robustness.

[0026] Furthermore, during transmission, the monitoring module performs integrity verification based on the check information attached to each fragment, and triggers the retransmission of the fragment when any error or loss is detected, so as to ensure that the data eventually arrives completely in the private cloud. Attached Figure Description

[0027] Figure 1This is a network topology diagram of an adaptive data compression and transmission method and device based on SSD thermal behavior in an edge network environment.

[0028] Figure 2 This is a structural diagram of an adaptive data compression and transmission method and apparatus based on SSD thermal behavior in an edge network environment according to the present invention.

[0029] Figure 3 This is a flowchart illustrating an adaptive data compression and transmission method and apparatus based on SSD thermal behavior in an edge network environment according to the present invention. Detailed Implementation

[0030] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0031] This invention proposes an adaptive data compression and transmission method and apparatus based on SSD thermal behavior in an edge network environment, specifically including the following steps:

[0032] S1. Deploy an edge box device between the mobile terminal device and the local network. The mobile terminal device is connected to the edge box device via a wired connection. The edge box device is connected to the 5G base station via the 5G CPE terminal network device.

[0033] S2. The mobile terminal device uploads the data to be transmitted to the edge box. The edge box performs security verification on the user's identity and the data to be transmitted. If the verification is successful, step S3 is executed; otherwise, the transmission is terminated and an illegal operation is prompted.

[0034] S3. The data to be transmitted is segmented and each data segment is compressed and stored in a multi-threaded parallel manner. At the same time, the temperature of the SSD storage medium is monitored to dynamically adjust the number of parallel compression threads and the SSD storage strategy.

[0035] S4. Based on the multi-path load balancing strategy, the compressed data is fragmented and distributed to multiple communication paths and transmitted to the private cloud. The integrity of the data fragment transmission is monitored synchronously, and retransmission is performed for data that fails to be transmitted.

[0036] like Figures 1-3 In this embodiment, an adaptive data compression and transmission method and apparatus based on SSD thermal behavior in an edge network environment includes the following steps:

[0037] S1: Deploy an edge box device between the mobile terminal device and the local network. The mobile terminal device and the edge box device are connected via a network cable. The edge box device accesses the 5G base station through the 5G CPE (Network Premises Equipment) to achieve connectivity between the edge box and the operator's 5G core network and the backend private cloud. The edge box device structure is as follows: Figure 2 As shown, it mainly includes an authorization verification module, a fragmentation and compression module, an adaptive caching module, a transmission load control module, and a monitoring module.

[0038] The system comprises several modules: an access control module verifies user identity and data validity to ensure secure transmission; a data fragmentation and compression module handles data fragmentation and multi-threaded parallel compression, with the number of threads dynamically adjusted; an adaptive caching module uses a non-linear PI algorithm to adjust the number of compression threads based on SSD temperature; a transmission load control module balances data transmission based on network conditions; and a monitoring module monitors SSD temperature, verifies transmission integrity, and triggers retransmissions upon failure. All modules are connected via a bus or internal communication interface to exchange data and control information.

[0039] S2: The mobile terminal device uploads the data to be transmitted to the edge box. The edge box performs security verification on the user's identity and the data to be transmitted. If the verification is successful, step S3 is executed; otherwise, the transmission is terminated and an illegal operation is prompted.

[0040] S21: Authenticate the connected mobile terminal based on pre-configured user credentials (such as device ID, authorization token, certificate, etc.).

[0041] S22: Verify the signature information and digest information carried in the data to be transmitted to verify that the data has not been tampered with after it was generated on the terminal side.

[0042] S23: After successful verification, the data task is registered in the processing queue, and a processing instruction is sent to the subsequent fragmentation and compression module. If authentication or data integrity verification fails, the transmission request is rejected, and an illegal operation is indicated.

[0043] S3: The data to be transmitted is segmented and each data segment is compressed and stored in parallel using a multi-threaded approach. At the same time, the temperature of the SSD storage medium is monitored to dynamically adjust the number of parallel compression threads and the SSD storage strategy.

[0044] S31: Verification is successful. The data to be transmitted is fragmented, and each data fragment is compressed in a multi-threaded parallel manner.

[0045] S311: The fragmentation and compression module first divides the data to be transmitted into multiple data fragments according to a predetermined size. The fragment size can be set according to the service type and system configuration.

[0046] S312: System initialization parallel compression thread pool. The initial number of threads can be configured based on experience such as the number of CPU cores and SSD write capability.

[0047] S313: Each data shard is assigned to a thread in the compression thread pool, and is compressed using a fast compression algorithm to generate the corresponding compressed shard.

[0048] S32: Stores compressed data in segments while monitoring the temperature of the SSD storage medium.

[0049] S321: After compression, the data fragments are submitted to the write queue, and the adaptive cache module completes the write operation on the SSD storage medium.

[0050] S322: The adaptive cache module obtains the temperature of the SSD storage medium by reading information from the monitoring module and records the temperature value at fixed time intervals to form a historical temperature change curve.

[0051] S323: To reduce the impact of measurement noise, the acquired temperature values ​​can be exponentially smoothed or low-pass filtered, and updated with a sampling period of 0.5 to 2 seconds.

[0052] S33: The thermal behavior of the SSD is approximated as a first-order dynamic system. With the real-time temperature of the SSD as feedback, a nonlinear PI controller is used to dynamically adjust the number of parallel compression threads, thereby maximizing the compression throughput while ensuring that the SSD is within a safe temperature range.

[0053] S34: In addition to adjusting the number of parallel compression threads, the adaptive caching module can also dynamically adjust the SSD storage strategy based on the current SSD temperature and queue length, including: adjusting the maximum length of the write queue or the write rate; when the SSD temperature is high, prioritizing the temporary storage of some data in the memory cache or slowing down the write speed; when the temperature returns to normal and the SSD load is low, gradually restoring the write rate and number of threads to achieve a balance between performance and security.

[0054] S4: Distribute compressed data fragments to multiple communication paths and transmit them to the private cloud according to the multi-path load balancing strategy. Simultaneously monitor the integrity of data fragment transmission and perform retransmission for data that fails to be transmitted.

[0055] S41: Based on the multi-path load balancing strategy, the compressed data is fragmented and distributed to multiple communication paths and transmitted to the private cloud.

[0056] S411: The transmission load control module collects real-time status information such as bandwidth, latency, and packet loss rate of each communication path.

[0057] S412: Dynamically adjusts the distribution ratio of compressed data fragments among various communication paths according to a pre-set load balancing strategy.

[0058] S413: When a certain path experiences an increase in packet loss rate or a decrease in available bandwidth, reduce the proportion of fragments allocated to that path and schedule more fragments to paths in better condition to improve overall transmission efficiency and reliability.

[0059] S42: During transmission, the monitoring module monitors the temperature of the SSD storage medium and feeds it back to the adaptive cache module in real time. In scenarios where the SSD exhibits segmented throughput behavior (such as a sudden drop in write rate after the SLC cache is exhausted), the monitoring module can also incorporate feedforward correction based on throughput fluctuations or add rate limiting strategies to the temperature control law, taking into account sudden changes in throughput and I / O latency. This prevents the hardware from maintaining a high thread count when it has already entered a performance degradation phase, further enhancing robustness.

[0060] S43: Perform integrity verification based on the check information attached to each fragment, and trigger the retransmission of the fragment if any error or loss is found, so as to ensure that the data eventually arrives in the private cloud intact.

[0061] S431: Each data fragment is compressed and includes integrity verification information. The private cloud uses this verification information to perform integrity verification after receiving the fragment.

[0062] S432: If a fragment is found to be faulty or lost, the monitoring module will trigger a retransmission mechanism to resend the fragment to one or more available paths.

[0063] S433: After all data fragments have been received and verified, the data is reassembled and decompressed in the private cloud to restore the complete original data.

[0064] This invention primarily addresses common problems in existing systems within a "mobile terminal—edge box—5G—private cloud" architecture, where large volumes of data require centralized compression, caching, and uploading at the edge. These problems include SSD overheating, performance degradation, and a lack of coordination between compression processing, caching, and multi-path transmission. This invention introduces first-order dynamic modeling based on SSD thermal behavior and a nonlinear PI temperature control algorithm into the edge box. Using SSD temperature as feedback, it dynamically adjusts the number of parallel compression threads and the SSD storage strategy, and integrates with multi-path load balancing and fragmented retransmission mechanisms to achieve integrated adaptive optimization of compression, storage, and transmission. While ensuring the long-term safe operation of the SSD, this invention balances system throughput and hardware lifespan, achieving high throughput, high reliability, and low latency for edge data transmission systems.

[0065] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An adaptive data compression and transmission method and apparatus based on SSD thermal behavior in an edge network environment, specifically comprising the following steps: S1. Deploy an edge box device between the mobile terminal device and the local network. The mobile terminal device is connected to the edge box device via a wired connection. The edge box device is connected to the 5G base station via the 5G CPE terminal network device. S2. The mobile terminal device uploads the data to be transmitted to the edge box. The edge box performs security verification on the user's identity and the data to be transmitted. If the verification is successful, step S3 is executed; otherwise, the transmission is terminated and an illegal operation is prompted. S3. The data to be transmitted is segmented and each data segment is compressed and stored in a multi-threaded parallel manner. At the same time, the temperature of the SSD storage medium is monitored to dynamically adjust the number of parallel compression threads and the SSD storage strategy. S4. Based on the multi-path load balancing strategy, the compressed data is fragmented and distributed to multiple communication paths and transmitted to the private cloud. The integrity of the data fragment transmission is monitored synchronously, and retransmission is performed for data that fails to be transmitted.

2. The edge box device according to claim 1 mainly includes an access verification module, a fragmentation compression module, an adaptive caching module, a transmission load control module, and a monitoring module.

3. The rights verification module of claim 2, wherein, User identity is confirmed and data validity is verified through pre-configured user credentials and data signature verification.

4. The fragmentation compression module of claim 2, wherein, The data is divided into multiple fragments according to a predetermined size, and each fragment is compressed in parallel using a fast compression algorithm according to the control strategy of the adaptive caching module, so as to improve compression speed and throughput.

5. The adaptive cache module of claim 2, wherein, The thermal load of the SSD storage medium is predicted based on its current temperature and historical temperature rise trend, and a control strategy is output to the sharding compression module based on the temperature control algorithm to dynamically limit its maximum number of parallel compression threads.

6. The temperature control algorithm of claim 5, wherein, The thermal behavior of an SSD is viewed as a simple first-order dynamic system. A non-linear PI controller with temperature feedback is used to adjust the number of parallel compression threads, thereby keeping the SSD within a safe temperature range.

7. The transmitting load control module of claim 2, wherein, The allocation ratio of data fragments among different paths is dynamically adjusted based on real-time bandwidth and packet loss rate information for each communication path, in order to optimize network resource utilization and ensure high-reliability transmission.

8. The monitoring module of claim 2, wherein, The system monitors the temperature of the SSD storage medium and feeds it back to the adaptive cache module in real time. It performs integrity verification based on the check information attached to each shard and triggers the retransmission of the shard when any error or loss is detected, so as to ensure that the data eventually arrives in the private cloud intact.

Images