Abstract : Offloading computation-intensive tasks (e.g., block chain agreement cycles and information handling undertakings) to the edge/cloud is a promising answer for block chain-enabled versatile edge figuring. Nonetheless, the conventional offloading approaches (e.g., sell off based and game-hypothesis draws near) neglect to change the strategy as per the changing climate and can't accomplish long haul execution. In addition, the current profound support gaining based offloading approaches experience the ill effects of the sluggish union brought about by high-layered activity space. In this paper, we propose another without model profound support learning-based web-based calculation offloading approach for block chain-enabled portable edge figuring in which both mining errands and information it are considered to handle assignments. In the first place, we plan the internet offloading issue as a Markov choice interaction by considering both the block chain mining errands and information handling undertakings. Then, to augment long haul offloading execution, we influence profound support figuring out how to oblige exceptionally unique conditions and address the computational intricacy. Besides, we bring a versatile hereditary calculation into the investigation of profound support figuring out how to stay away from pointless investigation and accelerate the union without lessening execution successfully. At last, our trial results show the way that our calculation can join rapidly and beat three benchmark approaches.
 ? Most of these existing works show how RL has been effectively applied to MEC based networks due to network dynamics. ? Random task generation and arrival exist for a mobile device since independent tasks are possibly sensed, collected, and generated by multiple types of applications stochastically. ? The existing DRL algorithms in terms of convergence, stability, and robustness, proposed a multiagent DRL-based cooperative computation offloading policy in the NOMA enabled MEC system with the aid of expert strategies, scatter networks, and hierarchical agents.
 ? The slow convergence caused by high-dimensional action space remains an urgent and challenging problem. ? In this paper, we study the computation offloading problem for both mining tasks and data processing tasks in multi-hop multi-user blockchain-empowered MEC. ? In our performance optimization problem, it is important to note that costs such as energy consumption and purchasing VMs should be paid immediately.
 • To minimize the expected long-term cost of task delay and dropping penalty, the optimal offloading decision making strategy was proposed in with the aid of long short-term memory (LSTM), dueling DQN, and double DQN algorithms. • In, a low-complexity DRL-based task execution time and energy consumption optimization is proposed to avoid frequent offloading decisions and resource allocation recalculations, considering time-varying wireless channels and dynamic edge computational resources. • A context-aware attention mechanism is proposed for the online weight adjustment of each action value.
 ? The performance of the algorithm is greatly affected by the convergence and accuracy of the deep Q-network (DQN). ? In this way, we can make the most of the evaluating role of critic network in exploration, avoiding useless exploration to a great extent without reducing the performance. ? A resource allocation algorithm based on deep Qlearning is proposed into optimize the performance of computation offloading in MEC. ? All these algorithms are constrained by the trade-off between efficiency and optimality.

We have more than 145000 Documents , PPT and Research Papers

Have a question ?

Mail us :