Block AIM A Neural Network-Based Intelligent Middleware For Large-Scale IoT Data Placement Decisions

Abstract : Current Internet of Things (IoT) infrastructures rely on cloud storage however, relying on a single cloud provider puts limitations on the IoT applications and Service Level Agreement (SLA) requirements. Recently, multiple decentralized storage solutions (e.g., based on blockchains) have entered the market with distinct architecture, Quality of Service (QoS) parameters and at lower price compared to the cloud storage. In this work, we introduce BAM: a neural network-based middleware designed for intelligent selection of storage technology for IoT applications. We first propose a blockchain-based data placement protocol and theoretically model a decision optimization problem, which jointly considers cloud, multi-cloud and decentralized storage technologies to select the appropriate medium to store large-scale IoT data, while ensuring data integrity, traceability, auditability and decision verifiability. We then propose a neural network-based maintenance reconfiguration, which aims to optimize the computational complexity of the middleware design along with the blockchain transaction and storage overhead by learning and predicting the applications parameters. We also propose the aggregation rate feedback functionality in our design and model it as a linear optimization problem to improve data quality and precision. Finally, we provide a reference implementation and perform extensive experiments, which demonstrate the effectiveness of the proposed design.

 EXISTING SYSTEM :

 ? The incremental model discussed in is the model that updates the parameters of the existing model depending on the previous incoming data, rather than constructing a new model from scratch. ? The benefit of applying semantic technology to sensor data is the conceptualization and abstract interpretation of the raw data, making them computer-definable, and interlinking the data with existing data web resources. ? This also allows access to domain information and related semantically enriched representations for other entities and/or existing data (on the web). ? It is observed that several works exist with each focusing on specific problems and issues associated with IoT sensor data.

 DISADVANTAGE :

 ? It investigates the robust standardization issue, security, software and hardware elements, cost decrease, scalability problems, and proper compatibility. ? Two main points are discussed, starting with the significant technological attempts used in IoT applications to address environmental and agro-industrial problems. ? Therefore, in this work, the authors tried to solve the problem by suggesting a transport protocol focusing on a loss recovery approach. ? Therefore, ubiquitous computing represents a fundamental requirement in ubiquitous IoT technology that displays several complex problems.

 PROPOSED SYSTEM :

 • The proposed technique involves the reconstruction of subspace-based data sampling. • The proposed method exhibits improvements in terms of accuracy and efficiency as regards removing the uncertainties and data aggregation of sensor data from the experimentation results. • Multiple feature extraction techniques and various classification algorithms were considered, as were the proposed processing depth and amplification of gain through efficient methods. • In real-time experimentation, the proposed data analytics framework exhibited efficient data aggregation and data outlier detection with high accuracy.

 ADVANTAGE :

 ? This is used in an IoT communication load susceptible to performance deprivation that occurs from traffic congestion. ? The obtained results show that the proposed algorithm has a more effective performance compared to various current super-resolution algorithms. ? The authors found it essential to conduct context awareness and to consider adopting the performance of distributed applications. ? The idea was to design a realistic simulation model of LoRaWAN that allowed the performance of network designs typically employed for industrial monitoring to be examined. ? However, the system is not over-charged with the update messages, which ensures a high-performance level for each node compared to centralized systems.