Offloading technique is an effective approach to migrate tasks from mobile devices to cloud to prolong the battery life. However, it cannot be guaranteed that all devices can successfully offload their tasks to cloud due to the limited network resources, thus offloading decisions should be made to coordinate devices. The existing works focus on how to maximize energy saving for a group of devices instead of the number of mobile devices that benefits from offloading. Therefore, how to maximize the number of energy-saving devices in the multi-user offloading scenario remains a challenging issue to be solved. In this paper, we aim to obtain a beneficial offloading group where all device can offloading tasks simultaneously to achieve energy saving and the number of beneficial offloading devices maximum for the group. In order to get such a group where each device can achieve its own benefit, firstly, we adopt game theory to model each device's demand of saving energy by offloading in OFDM communication system, and formulate multi-user offloading game problem (MUOG). Furthermore, we propose an offloading game mechanism (OGM), including: beneficial offloading threshold (BOT) algorithm and beneficial offloading group (BOG) algorithm. BOT algorithm can obtain the threshold of each device, i.e., the maximum number of mobile devices that the device can tolerate to offload tasks simultaneously while BOG algorithm can obtain a group of beneficial offloading devices. It can be proved that OGM strategy can achieve the Nash equilibrium of MUOG problem so as to obtain the maximum number of beneficial offloading devices. Experimental comparisons verify the number of beneficial offloading users and the overhead of the mechanism among different strategies. The results show that OGM can benefit more devices by offloading to save energy without high overhead compared with other offloading strategies.

Machine learning has been widely applied in structural health monitoring. While most existing methods, which are limited to forecasting structural state evolution of large infrastructures. forecast the structural state in a step-by-step manner, extracting feature of structural state trends and the negative effects of data collection under abnormal conditions are big challenges. To address these issues, a long-term structural state trend forecasting method based on long sequence time-series forecasting (LSTF) with an improved Informer model integrated with Fast Fourier transform (FFT) is proposed, named the FFT–Informer model. In this method, by using FFT, structural state trend features are represented by extracting amplitude and phase of a certain period of data sequence. Structural state trend, a long sequence, can be forecasted in a one-forward operation by the Informer model that can achieve high inference speed and accuracy of prediction based on the Transformer model. Furthermore, a Hampel filter that filters the abnormal deviation of the data sequence is integrated into the Multi-head ProbSparse self-attention in the Informer model to improve forecasting accuracy by reducing the effect of abnormal data points. Experimental results on two classical data sets show that the FFT–Informer model achieves high and stable accuracy and outperforms the comparative models in forecasting accuracy. It indicates that this model can effectively forecast the long-term state trend change of a structure and is proposed to be applied to structural state trend forecasting and early damage warning.

Echo state networks (ESNs), as efficient and powerful computational models for approximating nonlinear dynamical systems, have been successfully applied in financial time series forecasting. Reservoir constructions in standard ESNs rely on trials and errors in real applications due to a series of randomized model building stages. A novel form of ESN with deterministically constructed reservoir is competitive with standard ESN by minimal complexity and possibility of optimizations for ESN specifications. In this paper, forecasting performances of deterministic ESNs are investigated in stock price prediction applications. The experiment results on two benchmark datasets (Shanghai Composite Index and S&P500) demonstrate that deterministic ESNs outperform standard ESN in both accuracy and efficiency, which indicate the prospect of deterministic ESNs for financial prediction.