Central Cloud Server Research Articles

Cost Minimization-Oriented Computation Offloading and Service Caching in Mobile Cloud-Edge Computing: An A3C-Based Approach

This paper considers computation offloading and service caching in a three-tier mobile cloud-edge computing structure, in which Mobile Users (MUs) have subscribed to the Cloud Service Center (CSC) for computation offloading services and paid related fees monthly or yearly, and the CSC provides computation services to subscribed MUs and charges service fees. Long transmission distance and communication resource shortage caused by the increasing number of offloaded MUs may make the CSC unable to satisfy the delay requirements of MUs. Hence, the CSC can purchase some computation and communication resources from Edge Servers (ESs) with limited caching capacities and computation resources to assist MUs in computation offloading. However, from the perspective of the CSC, it remains open to jointly optimize the strategies of computation offloading, service caching, and resource allocation to meet the delay requirements of MUs while reducing the cost of the CSC. Therefore, a novel Deep Reinforcement Learning-based Computation Offloading and Service Caching Mechanism, named DRLCOSCM is proposed to jointly optimize the offloading decision, service caching, and resource allocation strategies, so as to minimize the cost of the CSC while ensuring the delay requirements of MUs. In DRLCOSCM, the optimization problem is formulated as a Mixed Integer Non-Linear Programming (MINLP) problem, and an Asynchronous Advantage Actor-Critic-based (A3C-based) algorithm is proposed to solve the problem. The simulation results show that DRLCOSCM significantly outperforms the other baseline methods in different scenarios.

Energy-Efficient Computation Offloading With DVFS Using Deep Reinforcement Learning for Time-Critical IoT Applications in Edge Computing

Internet of Things (IoT) is a technology that allows ordinary physical devices to collect, process, and share data with other physical devices and systems over the internet. It provides pervasively connected infrastructures to support innovative applications and services that can automate otherwise intensely laborious manual effort. Edge computing (EC) complements the powerful centralized cloud servers by providing powerful computation capability close to the data source, minimizing communication latency, and securing data privacy. The energy consumption problem has continued to receive much attention from the IoT community in applying various techniques to reduce energy consumption while still meeting the computational demand. In this paper, we propose an application-deadline-aware data offloading scheme using deep reinforcement learning and Dynamic Voltage and Frequency Scaling (DVFS) in an edge computing environment to reduce the energy consumption of IoT devices. The proposed scheme learns the optimal data distribution policies and local computation DVFS frequency scaling by interacting with the system environment and learning the behavior of the device, network, and edge servers. The proposed scheme was tested on multiple edge computing environments with different IoT devices. Experimental results show that this scheme can reduce energy consumption while achieving the IoT application and services timing and computational goals. The proposed scheme has substantial energy savings when compared with the native Linux governors.

Artificial Intelligence-Empowered Logistic Traffic Management System Using Empirical Intelligent XGBoost Technique in Vehicular Edge Networks

Recent advancements in computation and communication technologies and the increasing adoption of the Internet of Things (IoT) and Artificial Intelligence (AI) technologies have paved the way to tremendous developments in modern transportation systems. Driven by the massive number of connected vehicles and the stringent requirements of the public traffic management system, the transportation of data to and from the centralized cloud servers poses a great challenge. As a result, to meet the computational requirements and handle the massive amount of sensory data efficiently, the potential solution is to process/analyze the data at the edge of the network. Motivated by the challenges mentioned above, in this paper, we design a new empirically intelligent XGboost (EIXGB)-enabled logistic transportation system at the edge network for analyzing the data efficiently. Besides that, the proposed EIXGB technique intends to obtain real-time results based on the monitoring parameters of the public traffic management system with higher accuracy and minimum error. Extensive simulation results demonstrate the efficiency of the proposed EIXGB technique over the standard machine learning techniques using a set of parameters. The proposed technique achieves 87-97% accuracy over the different sets of features of a real-time dataset as per the simulation results.

Cloud based IoT Electronic Healthcare Data Warehouse Integration in emerging 5G Health Grid Ecosystem

The integration of heterogeneous enterprise cloud data warehouses enables the formation of national health grid ecosystem that links public and private health databases to enable supervision of healthcare utilities, costs, quality of care and observance of national healthcare administrative protocols. The development of cloud data warehouse requires information communication technology to condense the costs of patient’s healthcare by supporting care, away from hospitals, where increasingly detailed data can move from patients to centralized cloud server data warehouse, allowing efficiency in diagnosis and treatment options. The global democratization of 5G telecommunication broadband creates entirely new use case scenarios for consumers addressing healthcare sector and industries, intending to improve citizen’s life expectancy. The improved data rate transmission revolutionizes healthcare sector and offers prospects that enable the telecommunication merchants to penetrate the supply chains and initiate partnerships that profit the entire healthcare business ecosystem. This paper analyses the 5G network implementation business potentials, focusing on the 5G business opportunities that originate from industrial healthcare automation, allowing patient data aggregation required for citizens’ healthcare management. The research entrenches the 5G radio frequency access network and distributed cloud IoT server systems in constructing a healthcare grid data warehouse to enable self-optimized service-level agreements. Moreover, this paper observes that the healthcare sector prioritized telecommunication operators when partnership issues were debated above every other service sector addressing healthcare development. The cloud IoT platform offers solution to synchronize-able global device connectivity management for e-healthcare and demonstrates how these improvements enable development of new systems for public healthcare policy formulation and delivery in Nigeria.

Blockchain-Based Continuous Knowledge Transfer in Decentralized Edge Computing Architecture

Edge computing brings computational ability to network edges to enable low latency based on deploying devices close to the environment where the data is generated. Nevertheless, the limitation of size and energy consumption constrain the scalability and performance of edge device applications such as deep learning, although, cloud computing can be adopted to support high-performance tasks with centralized data collection. However, frequently communicating with a central cloud server brings potential risks to security and privacy issues by exposing data on the Internet. In this paper, we propose a secure continuous knowledge transfer approach to improve knowledge by collaborating with multiple edge devices in the decentralized edge computing architecture without a central server. Using blockchain, the knowledge integrity is maintained in the transfer process by recording the transaction information of each knowledge improvement and synchronizing the blockchain in each edge device. The knowledge is a trained deep-learning model that is derived by learning the local data. Using the local data of each edge device, the model is continuously trained to improve performance. Therefore, each improvement is recorded as the contribution of each edge device immutably in the decentralized edge computing architecture.

MR-DRO: A Fast and Efficient Task Offloading Algorithm in Heterogeneous Edge/Cloud Computing Environments

With the rapid development of Internet of Things (IoT) and next-generation communication technologies, resource-constrained mobile devices (MDs) fail to meet the demand of resource-hungry and compute-intensive applications. To cope with this challenge, with the assistance of mobile-edge computing (MEC), offloading complex tasks from MDs to edge cloud servers (CSs) or central CSs can reduce the computational burden of devices and improve the efficiency of task processing. However, it is difficult to obtain optimal offloading decisions by conventional heuristic optimization methods, because the decision-making problem is usually NP-hard. In addition, there are shortcomings in using intelligent decision-making methods, e.g., lack of training samples and poor ability of migration under different MEC environments. To this end, we propose a novel offloading algorithm named meta reinforcement-deep reinforcement learning-based offloading, consisting of a meta-reinforcement learning (meta-RL) model, which improves the migration ability of the whole model, and a deep reinforcement learning (DRL) model, which combines multiple parallel deep neural networks (DNNs) to learn from historical task offloading scenarios. Simulation results demonstrate that our approach can effectively and efficiently generate near-optimal offloading decisions in IoT environments with edge and cloud collaboration, which further improves the computational performance and has strong portability when making offloading decisions.

Distributed Detection of Malicious Android Apps While Preserving Privacy Using Federated Learning.

Recently, deep learning has been widely used to solve existing computing problems through large-scale data mining. Conventional training of the deep learning model is performed on a central (cloud) server that is equipped with high computing power, by integrating data via high computational intensity. However, integrating raw data from multiple clients raises privacy concerns that are increasingly being focused on. In federated learning (FL), clients train deep learning models in a distributed fashion using their local data; instead of sending raw data to a central server, they send parameter values of the trained local model to a central server for integration. Because FL does not transmit raw data to the outside, it is free from privacy issues. In this paper, we perform an experimental study that explores the dynamics of the FL-based Android malicious app detection method under three data distributions across clients, i.e., (i) independent and identically distributed (IID), (ii) non-IID, (iii) non-IID and unbalanced. Our experiments demonstrate that the application of FL is feasible and efficient in detecting malicious Android apps in a distributed manner on cellular networks.

Edge-aided searchable data sharing scheme for IoV in the 5G environment

The development of 5G technology provides huge potential for the Internet of Vehicles (IoV). In the IoV scenario, the secure exchange of traffic warning data is necessary to guarantee the safety of pedestrians, vehicles, and public transport facilities. However, there remain a series of challenging issues to achieve data secure sharing while ensuring efficiency. Current solutions such as the data outsourcing storage of traditional centralized cloud servers may cause information leakage due to their incomplete credibility. To address these problems mentioned above, this paper proposes an edge-aided searchable data sharing scheme based on blockchain for IoV in a 5G environment. First, the proposed scheme stores the search index of the keyword and the hash value of the data ciphertext on the blockchain to ensure its integrity and authenticity, and the smart contract automatically verifies the search trapdoor. And then, an edge caching mechanism is designed to quickly feedback on users’ retrieval needs based on a cloud-edge collaboration model. In addition, attribute-based searchable encryption is used to ensure that only the users who meet the access attributes and policy can decrypt the encrypted traffic warning data, which can achieve fine-grained access control and keyword search simultaneously. Finally, security analysis and performance evaluation demonstrate that our scheme is secure and more efficient compared with other schemes.

Analysis of Communicable Disease Symptoms Using Bag-of-Neural Network at Edge Networks

Considering the increasing growth of communicable diseases worldwide such as COVID-19, it is recommended to stay at home for patients with fewer chronic health problems. In recent times, the high chance of COVID-19 spread and the lack of an excellent remote monitoring system make the situation challenging for hospital administrators. Inspired by these challenges, in this paper, we develop a new edge-centric healthcare framework for remote health monitoring and disease prediction using Wearable Sensors (WSs) and advanced Machine Learning (ML) model, namely Bag-of-Neural Network (BoNN), respectively. The epidemic model collects the health symptoms of the patient using various a set of WSs and preprocesses the data in distributed edge devices for preparing a useful dataset. Finally, the proposed BoNN model is applied over the refined dataset for detecting COVID-19 disease at centralized cloud servers using a set of random neural networks. To demonstrate the efficiency of the proposed BoNN model over the standard ML models, the system is fine-tuned and trained over a synthetic COVID-19 dataset before being evaluated on a benchmark Brazil COVID-19 dataset using various performance metrics. The experimental results demonstrate that the proposed BoNN model achieves 99.8% accuracy while analyzing the Brazil dataset.

Enabling All In-Edge Deep Learning: A Literature Review

In recent years, deep learning (DL) models have demonstrated remarkable achievements on non-trivial tasks such as speech recognition, image processing, and natural language understanding. One of the significant contributors to the success of DL is the proliferation of end devices that act as a catalyst to provide data for data-hungry DL models. However, computing DL training and inference still remains the biggest challenge. Moreover, most of the time central cloud servers are used for such computation, thus opening up other significant challenges, such as high latency, increased communication costs, and privacy concerns. To mitigate these drawbacks, considerable efforts have been made to push the processing of DL models to edge servers (a mesh of computing devices near end devices). Recently, the confluence point of DL and edge has given rise to edge intelligence (EI), defined by the International Electrotechnical Commission (IEC) as the concept where the data is acquired, stored, and processed utilizing edge computing with DL and advanced networking capabilities. Broadly, EI has six levels of categories based on the three locations where the training and inference of DL take place, e.g., cloud server, edge server, and end devices. This survey paper focuses primarily on the fifth level of EI, called all in-edge level, where DL training and inference (deployment) are performed solely by edge servers. All in-edge is suitable when the end devices have low computing resources, e.g., Internet-of-Things, and other requirements such as latency and communication cost are important such as in mission-critical applications (e.g., health care). Besides, 5G/6G networks are envisioned to use all in-edge. Firstly, this paper presents all in-edge computing architectures, including centralized, decentralized, and distributed. Secondly, this paper presents enabling technologies, such as model parallelism, data parallelism, and split learning, which facilitates DL training and deployment at edge servers. Thirdly, model adaptation techniques based on model compression and conditional computation are described because the standard cloud-based DL deployment cannot be directly applied to all in-edge due to its limited computational resources. Fourthly, this paper discusses eleven key performance metrics to evaluate the performance of DL at all in-edge efficiently. Finally, several open research challenges in the area of all in-edge are presented.

Research on a Fog Computing Architecture and BP Algorithm Application for Medical Big Data

Although the Internet of Things has been widely applied, the problems of cloud computing in the application of digital smart medical Big Data collection, processing, analysis, and storage remain, especially the low efficiency of medical diagnosis. And with the wide application of the Internet of Things and Big Data in the medical field, medical Big Data is increasing in geometric magnitude resulting in cloud service overload, insufficient storage, communication delay, and network congestion. In order to solve these medical and network problems, a medical big-data-oriented fog computing architecture and BP algorithm application are proposed, and its structural advantages and characteristics are studied. This architecture enables the medical Big Data generated by medical edge devices and the existing data in the cloud service center to calculate, compare and analyze the fog node through the Internet of Things. The diagnosis results are designed to reduce the business processing delay and improve the diagnosis effect. Considering the weak computing of each edge device, the artificial intelligence BP neural network algorithm is used in the core computing model of the medical diagnosis system to improve the system computing power, enhance the medical intelligence-aided decision-making, and improve the clinical diagnosis and treatment efficiency. In the application process, combined with the characteristics of medical Big Data technology, through fog architecture design and Big Data technology integration, we could research the processing and analysis of heterogeneous data of the medical diagnosis system in the context of the Internet of Things. The results are promising: The medical platform network is smooth, the data storage space is sufficient, the data processing and analysis speed is fast, the diagnosis effect is remarkable, and it is a good assistant to doctors’ treatment effect. It not only effectively solves the problem of low clinical diagnosis, treatment efficiency and quality, but also reduces the waiting time of patients, effectively solves the contradiction between doctors and patients, and improves the medical service quality and management level.

An Integrated Artificial Intelligence of Things Environment for River Flood Prevention.

River floods are listed among the natural disasters that can directly influence different aspects of life, ranging from human lives, to economy, infrastructure, agriculture, etc. Organizations are investing heavily in research to find more efficient approaches to prevent them. The Artificial Intelligence of Things (AIoT) is a recent concept that combines the best of both Artificial Intelligence and Internet of Things, and has already demonstrated its capabilities in different fields. In this paper, we introduce an AIoT architecture where river flood sensors, in each region, can transmit their data via the LoRaWAN to their closest local broadcast center. The latter will relay the collected data via 4G/5G to a centralized cloud server that will analyze the data, predict the status of the rivers countrywide using an efficient Artificial Intelligence approach, and thus, help prevent eventual floods. This approach has proven its efficiency at every level. On the one hand, the LoRaWAN-based communication between sensor nodes and broadcast centers has provided a lower energy consumption and a wider range. On the other hand, the Artificial Intelligence-based data analysis has provided better river flood predictions.

Eiffel: Efficient and Fair Scheduling in Adaptive Federated Learning

Emerging machine learning (ML) technologies, in combination with the increasing computational power of mobile devices, lead to the extensive adoption of ML-based applications. Different from conventional model training that needs to collect all the user data in centralized cloud servers, federated learning (FL) has recently drawn increasing research attention as it enables privacy-preserving model training. With FL, decentralized edge devices in participation, train their model copies locally over their siloed datasets, and periodically synchronize the model parameters. However, model training is computationally extensive which easily drains the battery of mobile devices. In addition, due to the uneven distribution of siloed datasets, the shared model may become biased. To address the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">efficiency</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">fairness</i> concerns in a resource-constrained federated learning setting, in this paper, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Eiffel</i> to judiciously select mobile devices to participate in the global model aggregation, and adaptively adjust the frequency of local and global model updates. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Eiffel</i> aims to make scheduling and coordination for the federated learning towards both resource efficiency and model fairness. We have conducted theoretical analysis of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Eiffel</i> from the perspectives of fairness and convergence. Extensive experiments with a wide variety of real-world datasets and models, both on a networked prototype system and in a larger-scale simulated environment, have demonstrated that while maintaining similar accuracy performance, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Eiffel</i> outperforms existing baselines with respect to reducing communication overhead by up to 6× for higher efficiency and improving the fairness metric by up to 57% compared to the state-of-the-art algorithms.

ADC-DL: Communication-efficient distributed learning with hierarchical clustering and adaptive dataset condensation

The rapid growth of modern mobile devices leads to a large number of distributed data, which is extremely valuable for learning models. Unfortunately, model training by collecting all these original data to a centralized cloud server is not applicable due to data privacy and communication costs concerns, hindering artificial intelligence from empowering mobile devices. Moreover, these data are not identically and independently distributed (Non-IID) caused by their different context, which will deteriorate the performance of the model. To address these issues, we propose a novel Distributed Learning algorithm based on hierarchical clustering and Adaptive Dataset Condensation, named ADC-DL, which learns a shared model by collecting the synthetic samples generated on each device. To tackle the heterogeneity of data distribution, we propose an entropy topsis comprehensive tiering model for hierarchical clustering, which distinguishes clients in terms of their data characteristics. Subsequently, synthetic dummy samples are generated based on the hierarchical structure utilizing adaptive dataset condensation. The procedure of dataset condensation can be adjusted adaptively according to the tier of the client. Extensive experiments demonstrate that the performance of our ADC-DL is more outstanding in prediction accuracy and communication costs compared with existing algorithms.

Identification of Multiple Attacks in Cloud Environment using Big Data

Since the Cloud environment is prone to many attacks we are implementing a Big Data based centralized log analysis system to identify the network traffic occurred by attackers through DDOS, SQL Injection, and Brute Force attacks. The log file is automatically transmitted to the centralized cloud server where big data is initiated and uses a tool called Hadoop to process the huge amount of log files that are being sent to big data. If an attacker attacks any files then it will be compared with the attack dataset that is maintained here to detect the attacks that are being used by the attacker. This system also helps in storing the information of all registered users, and their files which get uploaded to the cloud server and downloaded from the server and IP addresses in order to view any attacks that may occur in the future. All this stored information is maintained securely using SQL which is a backend process. Thus we are implementing a system that delivers a very high performance as well as very efficient results in categorizing the attacks. Since the Hadoop tool is being used in the system, this system is able to increase its scalability and achieves a faster detection of attacks like DDOS, SQL Injection, and Brute Force attacks. This system can play a vital role in various organizations to safeguard their privacy. Data integrity, Data confidentiality, and non-repudiation can be achieved by using this system. Finally, we can say that this system avoids any faults that occurred in the previous system that was invented before this.

Flexible access control mechanism for cloud stored EHR using consortium blockchain

The implementation of cloud computing to store and access electronic health records has shown substantial benefits for both clinical organizations and patients in managing electronic health records. The prime security issue of cloud-based electronic health records is that the patient is physically unable to own a medical record whereas a clinical organization can maintain one for them. The latter may collude with centralized cloud servers. So, there is a vulnerability of such records being tampered with in order to hide the medical malpractices. So, maintaining data integrity and data privacy becomes a significant challenge when deploying cloud computing. Therefore, in this paper, a consortium blockchain-based cloud-stored electronic health record is proposed which provides data integrity, data privacy, storage scalability, and fine-grained access control. Each process in outsourcing electronic health records to the cloud is incorporated as a transaction in a consortium ethereum blockchain through smart contracts. Through smart contracts, an attribute-based contract key is generated for the users that can decrypt the encrypted data stored in the cloud. The attribute-based contract key allows only users who are authorized to access the information ensuring data privacy and fine-grained access control. Moreover, the proposed scheme is proved to provide tamper-proof although the medical records are controlled by a group of clinical organizations.

Metaheuristics with federated learning enabled intrusion detection system in Internet of Things environment

AbstractBecause of increased applications of Internet of Things (IoT) environment in real‐time environment, confidential data gathered by the IoT devices are being communicated to the cloud environment to train the machine learning (ML) models in understanding the patterns that exist in the data. At the same time, the sensitive nature of the IoT data attracts malicious users into hacking efforts. An intrusion detection system (IDS) can be applied to ensure security in the IoT environment. In order to improve security, the ML models can be executed at the data source instead of centralized cloud server. Federated learning (FL) is a recent progression of ML model which enables the ML models to move into the data source rather than moving the data to centralized cloud and thereby resolves cybersecurity problems in the IoT environment. In this view, this study introduces an FL based IDS using bird swarm algorithm based feature selection with classification (FLIDS‐BSAFSC) model in IoT environment. The presented FLIDS‐BSAFSC model undergoes training on multiple aspects of IoT dataset in a decentralized format to classify, detect, and defend against attacks. The proposed FLIDS‐BSAFSC model initially applies min–max normalization technique to pre‐process the IoT data. Besides, BSA based feature selection (BSA‐FS) technique is designed to elect feature subsets. Finally, social group optimization algorithm with kernel extreme learning machine model is employed for identifying various kinds of classes. In the view of FL where the IoT dataset is not distributed to the server carries out profile aggregation competently with the advantage of peer learning. The experimental validation of the FLIDS‐BSAFSC model is tested using benchmark datasets and the results are inspected under several aspects. The experimental values highlighted the better performance of the FLIDS‐BSAFSC model over recent approaches.

Real-Time Survivor Detection System in SaR Missions Using Robots

This paper considers the issue of the search and rescue operation of humans after natural or man-made disasters. This problem arises after several calamities, such as earthquakes, hurricanes, and explosions. It usually takes hours to locate the survivors in the debris. In most cases, it is dangerous for the rescue workers to visit and explore the whole area by themselves. Hence, there is a need for speeding up the whole process of locating survivors accurately and with less damage to human life. To tackle this challenge, we present a scalable solution. We plan to introduce the usage of robots for the initial exploration of the calamity site. The robots will explore the site and identify the location of human survivors by examining the video feed (with audio) captured by them. They will then stream the detected location of the survivor to a centralized cloud server. It will also monitor the associated air quality of the selected area to determine whether it is safe for rescue workers to enter the region or not. The human detection model for images that we have used has a mAP (mean average precision) of 70.2%. The proposed approach uses a speech detection technique which has an F1 score of 0.9186 and the overall accuracy of the architecture is 95.83%. To improve the detection accuracy, we have combined audio detection and image detection techniques.

Adoption of Blockchain in IoT: Challenges and Solutions

Data is streamed from sensors, through fog devices, and onto a centralized Cloud server in traditional Internet of Things (IoT) ecosystems. Issues that arise include privacy concerns due to third-party management of Cloud servers, single points of failure, a bottleneck in data flows, and difficulties in regularly updating firmware for millions of smart devices from a point of security and maintenance perspective. Blockchain, the underlying technology of Bitcoin, was initially primarily intended for the transfer of monetary value. Nevertheless, researchers and security analysts from all over the world are focusing on the blockchain to address the security and privacy issues of IoT due to its decentralized architecture, fault tolerance, and cryptographic security benefits like pseudonymous identities, data integrity, and authentication. Blockchain technology protects users by avoiding reliable third parties. This has inspired researchers to investigate blockchain’s adoption into the IoT ecosystem. In this paper, let us understand more about blockchain, its application in IoT, challenges while handling IoT data on the blockchain, and its security solutions.

Application of Chaos Mutation Adaptive Sparrow Search Algorithm in Edge Data Compression.

In view of the large amount of data collected by an edge server, when compression technology is used for data compression, data classification accuracy is reduced and data loss is large. This paper proposes a data compression algorithm based on the chaotic mutation adaptive sparrow search algorithm (CMASSA). Constructing a new fitness function, CMASSA optimizes the hyperparameters of the Convolutional Auto-Encoder Network (CAEN) on the cloud service center, aiming to obtain the optimal CAEN model. The model is sent to the edge server to compress the data at the lower level of edge computing. The effectiveness of CMASSA performance is tested on ten high-dimensional benchmark functions, and the results show that CMASSA outperforms other comparison algorithms. Subsequently, experiments are compared with other literature on the Multi-class Weather Dataset (MWD). Experiments show that under the premise of ensuring a certain compression ratio, the proposed algorithm not only has better accuracy in classification tasks than other algorithms but also maintains a high degree of data reconstruction.