Leveraging Graph Convolutional-LSTM for Energy Efficient Caching in Blockchain-based Green IoT
ABSTARCT :
Nowadays, adopting blockchain technology to Internet of Things has become a trend and it is important to minimize energy consumption while providing a high quality of service (QoS) in Blockchain-based IoT networks. Pre-caching popular and fresh IoT content avoids activating sensors frequently, thus effectively reducing network energy consumption. However, the user equipment in regions covered by base stations will generate distributed and time-varying data requests, hence modeling the base station topology to capturing spatio-temporal request patterns is required for the data storage pre-allocation. Traditional solutions typically fail to pay attention to the topology, resulting in the sensor being activated redundantly. In this paper, we propose Request Graph Convolutional-LSTM to capture the spatio-temporal request patterns in Blockchain-based IoT networks and make predictions. Moreover, a heuristic algorithm based on the predictions is proposed to develop pre-caching strategy, which determines the data and location to be cached to minimize the mean data retrieval latency restricted by the cache space of IoT network entities and the freshness of IoT content. Experiments show that our proposed frame provides a low energy consumption.
EXISTING SYSTEM :
? An efficient algorithm combining DRL with GCN is proposed in, with up to 39.6% and 70.6% improvement on acceptance ratio and average revenue, compared with the existing state-ofthe-art solutions.
? However, network heterogeneity in 5G networks makes the multipath routing problem become more complex for the existing routing algorithms to handle.
? They are not only used to reconstruct the existing networks, but also used to model the non-existing networks, in order to provide an estimation of the unseen cases for network operators to make better network deployment decisions in the future.
? However, most of the existing studies for SFC use a supervised learning approach, which may not be suitable for dynamic VNF resources, various requests, and changes of topologies.
DISADVANTAGE :
? Reinforcement learning (RL) introduces ambient intelligence into the AIoT systems by providing a class of solution methods to the closed-loop problem of processing the sensory data to generate control decisions to react.
? However, there are many scenarios that it is not easy to determine the optimal locations for the agents, which may involve solving an RL problem in itself.
? Compared with valuebased methods, they can learn stochastic policies and solve RL problems with continuous actions.
? However in many real-world problems, total environment information cannot be observed by the agent accurately, usually due to the limitations in sensing and communications capabilities.
PROPOSED SYSTEM :
• To handle this situation, re-transmission mechanisms are proposed to enhance the robustness of GNN classifiers, for both uncoded and coded wireless communication systems.
• Beamforming is further considered, in which Message Passing Graph Neural Networks (MPGNNs) are proposed to solve both the power control and beamforming problems.
• Heterogeneous GNNs (HetGNNs) with a novel parameter sharing scheme are proposed for power control in multi-user multi-cell networks.
• The IAB topology design is formulated as a graph optimization problem and a combination of deep reinforcement learning and graph embedding is proposed for solving this problem efficiently.
ADVANTAGE :
? This is because that the network and computation performance, such as communication/computation delay, power consumption and network reliability, will have important impacts on the control performance of the physical system.
? This means there will be less overestimation of the Q-Learning values and more stability to improve the performance of the DRL method.
? Moreover, it can learn stochastic policies, which have better performance than deterministic policies in some situations.
? Cooperative communication is recognized as an important technology to improve the WSNs’ performance in data transmission rate and node coverage.
? Several performance metrics, such as connectivity, coverage, energy consumption and accuracy, can be improved by moving the nodes in the networks.
|