Search

In the smart grid, the end-users have the opportunity to integrate renewable energy sources (RESs) and participate in two-way energy trading. At the same time, an increasing number of flexible loads (FLs) have been developed for use on the demand side. Thus, this article considers joint energy trading and load scheduling at a end-user with integrated renewable generation. With unknown statistics on renewable generation, loads and electricity prices, we aim at optimizing both energy trading and load scheduling to maximize the long-term average profit of the end-user, subject to load delay constraints. We employ the Lyapunov optimization theory to solve this stochastic problem with a series of problem corrections and transformations that enable us to design a dynamic energy trading and load scheduling algorithm. Within the performance analysis of the algorithm, we further demonstrate that the algorithm not only provides a bounded performance guarantee to the optimal solution that has complete future information, but is also asymptotically equivalent to it as the battery capacity or the delay time of FLs tend to infinity. The simulation results show that the proposed algorithm is superior to other algorithms both in terms of performance and service delay. Moreover, we can achieve a trade-off between comfort and total profit by adjusting the values of the parameters, and analyze the effect of battery capacity on algorithm performance to provide a theoretical basis for the end-user to determine battery capacity.

The problems of insufficient power consumption and delay sensitivity are challenging issues of Software Defined-Wireless Body Area Networks (SD-WBANs) for smart health monitoring. The migration and offloading problems in mobile edge computing (MEC) system complicate the resource allocation on low delay and energy consumption. In this paper, we propose an Asynchronous Advantage Actor-Critic (A3C)-based joint optimization offloading and migration algorithm to address this issue. Based on Actor-Critic network, the proposed algorithm optimizes the neural network with asynchronous gradient descent to maximize the long-term benefits of SD-WBAN. Moreover, we define the total system cost as the combination of SD-WBAN migration cost, offloading cost and quality of service. Simulation results show that this algorithm can effectively get better long-term benefits of different priority tasks and highly improve the service quality of the users.

Real-time and accurate short-term traffic prediction enables efficient operation of road traffic via real-time vehicle status information. However, the traffic prediction model based on deep learning or machine learning is generally not efficient due to the long training time. Thus, we propose a Bidirectional Connection Broad Learning System (Bi-BLS) model to characterize the relationship between road flow and vehicle speed, so as to perform real-time and short-term traffic prediction. The Bi-BLS consists of two parts, namely the mapped feature nodes layer and the enhancement nodes layer. The mapped nodes layer employs cascade connection to extract hierarchical features from the data set by edge computing servers. The enhancement nodes layer uses bidirectional connection to extract hierarchical features from the mapped nodes layer. Moreover, it can efficiently add enhancement nodes or mapped feature nodes. To validate the effectiveness of our proposed model, the simulations are conducted based on the England Freeway Data set. Numerical results show that our proposed model has better prediction performance in short-term traffic prediction than other benchmark models.

The smart grid, as the next-generation of electricity grid, is characterized with new features, such as dynamic electricity price distributed renewable energy sources, and two-way energy transmission between users and the grid. Technically, it offers an opportunity for end-users to make profits by purchasing/selling energy from/to the grid in low/high electricity prices. In this paper, we investigate the profit maximization problem for an elastic end-user equipped with renewable energy devices and a battery, which allow energy demands to be met within a certain delay time. First, we establish a novel two-way energy trading model, by considering the reduction of the number of battery charge and discharge cycles to extend the battery lifetime. Then, a dynamic energy trading and management algorithm is proposed based on the Lyapunov optimization. In theory, the proposed algorithm can achieve optimal performance without any prior knowledge of the energy demand, the energy harvesting, and the energy arrival process. Meanwhile it ensures that the maximum delay of energy demand cannot exceed a given value. Finally, simulations are carried out and results demonstrate that the proposed algorithm is superior to direct trading and inelastic energy demand trading. The benefits of different battery capacities to the end-user are also analyzed to enable choosing a battery size depending on their cost requirements.

Offloading application to cloud can augment mobile devices' computation capabilities for the emerging resource-hungry mobile application, however it can also consume both much time and energy for mobile device offloading application remotely to cloud. In this paper, we develop a newly adaptive application offloading decision-transmission scheduling scheme which can solve above problem efficiently. Specifically, we first propose an adaptive application offloading model which allows multiple target clouds coexisting. Second, based on Lyapunov optimization theory, a low complexity adaptive offloading decision-transmission scheduling scheme has been proposed. And the performance analysis is also given. Finally, simulation results show that, compared with that all applications are executed locally, mobile device can save 68.557% average execution time and 67.095% average energy consumption under situations.

In this paper, we investigate the problem of dynamic power allocation for a multiuser transmitter supplied by hybrid energy sources in details. Specifically, we focus on the hybrid energy sources which include both the traditional power grid and various renewable sources whereby there are a few issues in considerations: (1) The energy harvested jointly from various renewable sources is time-varying and possibly unpredictable and is stored in a limited capacity buffer with battery leakage. (2) At the meantime, the data arrives randomly to the transmitter and queues according to the individual receivers to wait to be transmitted. (3) In addition, the wireless channels fluctuate randomly due to fading. Taking into account the time variant and dynamic features of this system, we develop a dynamic power allocation algorithm for the transmitter with the aim of minimizing the average amount of energy consumption from the power grid over an infinite horizon, subject to all data in queues cannot exceed a given deadline of receivers. The research question is formulated as a stochastic optimization problem, then we utilize Lyapunov optimization to exploit an online algorithm with low complexity, and it does not require prior statistical knowledge of the stochastic processes. Performance analysis of the proposed algorithm is carried out in theory, which shows that the proposed algorithm performs arbitrarily close to the optimal objective value; meanwhile, the algorithm ensures that the maximum delay of all data queues cannot exceed a given value. Finally, performance comparison shows that our proposed algorithm provides not only better performance but also less time delay than other two algorithms.

In this paper, we consider a wireless communication node with hybrid energy harvesting (EH) sources which results in great difficulty in obtaining the statistical knowledge of joint EH process. In addition, the wireless channel fluctuates randomly due to fading. Our goal is, under this condition, to develop a dynamic power control policy for the transmitter such that the time average throughput of the system is maximized over an infinite horizon, taking into account the circuit energy consumption and inefficiency of the rechargeable battery. Such a dynamic power control problem is formulated as a stochastic network optimization problem. The problem is solved by utilizing Lyapunov optimization and an efficient on-line algorithm with quite low complexity is obtained. Simulation results illustrate that the proposed algorithm has the same performance as the optimal one with giving statistical knowledge of the stochastic processes.

In this work, we consider a multiuser communication system in fading channels where the transmitter is supplied by hybrid energy sources including power grid and various renewable sources. Specially, the energy harvested from various renewable sources is stored in a limited capacity buffer, and the joint energy incoming is time-varying and possibly unpredictable. In addition, data arrives randomly to the transmitter and queues according to the individual receivers, the wireless channels fluctuate randomly due to fading. Our goal is, under this condition to develop a dynamic power allocation algorithm so as to minimize the time average amount of energy consumed from the power grid over an infinite horizon, subjecting to all data queues stability. The issue is formulated as a stochastic optimization problem and solved by Lyapunov optimization technique which does not require the statistical probabilities of energy harvesting process, data arrivals process and channel state. Simulation results demonstrate that our proposed algorithm provides obviously better performance than other two simple greedy algorithms, meanwhile the algorithm gives a guarantee that the maximum delay of all data queues cannot exceed a given value.