Federated learning is a promising new technology in the field of IoT intelligence. However, exchanging model-related data in federated learning may leak the sensitive information of participants. To address this problem, we propose a novel privacy-preserving FL framework based on an innovative chained secure multi-party computing technique, named Chain-PPFL. Our scheme mainly leverages two mechanisms: Single-Masking mechanism which protects information exchanged between participants; Chained-Communication mechanism which enables masked information to be transferred between participants with a serial chain frame. We conduct extensive simulation-based experiments using two public datasets (MNIST and CIFAR-100) by comparing both training accuracy and leak-defence with other state-of-the-art schemes. We set two data sample distributions (IID and Non-IID) and three training models (CNN, MLP and L-BFGS) in our experiments. The experimental results demonstrate that the Chain-PPFL scheme can achieve a practical privacy-preservation (equivalent to differential privacy with approaching zero) for federated learning with some cost of communication and without impairing the accuracy and convergence speed of the training model.

P2P streaming tries to achieve scalability (like P2P file distribution) and at the same time meet real-time playback requirements. It is a challenging problem still not well understood. In this paper, we describe a simple stochastic model that can be used to compare different data-driven downloading strategies based on two performance metrics: continuity (probability of continuous playback), and startup latency (expected time to start playback). We first study two simple strategies: rarest first and greedy. The former is a well-known strategy for P2P file sharing that gives good scalability, whereas the latter an intuitively reasonable strategy to optimize continuity and startup latency from a single peer's viewpoint. Greedy, while achieving low startup latency, fares poorly in continuity by failing to maximize P2P sharing; whereas rarest first is the opposite. This highlights the trade-off between startup latency and continuity, and how system scalability improves continuity. Based on this insight, we propose a mixed strategy that can be used to achieve the best of both worlds. Our algorithm dynamically adapts to the peer population size to ensure scalability; at the same time, it reserves part of a peer's effort to the immediate playback requirements to ensure low startup latency.

Popular online video-on-demand (VoD) services all maintain a large catalog of videos for their users to access. The knowledge of video popularity is very important for system operation , such as video caching on content distribution network (CDN) servers. The video popularity distribution at a given time is quite well understood. We study how the video popularity changes with time, for different types of videos, and apply the results to design video caching strategies. Our study is based on analyzing the video access levels over time, based on data provided by a large video service provider. Our main finding is, while there are variations, the glory days of a video’s popularity typically pass by quickly and the probability of replaying a video by the same user is low. The reason appears to be due to fairly regular number of users and view time per day for each user, and continuous arrival of new videos. All these facts will affect how video popularity changes, hence also affect the optimal video caching strategy. Based on the observation from our measurement study, we propose a mixed replication strategy (of LFU and FIFO) that can handle different kinds of videos. Offline strategy assuming tomorrow’s video popularity is known in advance is used as a performance benchmark. Through trace-driven simulation, we show that the caching performance achieved by the mixed strategy is very close to the performance achieved by the offline strategy.

The recent increasing evolution of renewable energy technologies makes it possible for common residents to afford the cost of installing renewable energy devices (REDs) and energy storage systems (ESSs) in their own houses. With the prevalence of REDs and ESSs, it is a beneficial and also promising idea for residents in a community to share extra energy with others, especially, when they have different electricity usage patterns. However, considering the unpredictable energy usage patterns, radically intermittent characteristics of renewable energy generation, and dynamic electricity price, it would be difficult for residents in a community to intelligently share their energy with others and thus minimize the overall cost of the whole community. In this paper, we design an online algorithm, which can tackle cost-aware energy sharing among residents in a cooperative community. We formulate the problem as a stochastic constrained problem and the objective is to minimize the time-average cost in the whole community, which includes the cost of purchasing electricity from the main grid, and the cost of charging and discharging ESSs. By exploiting the dynamics of electricity price, we can determine the charging and discharging behaviors of ESSs. We explore our method based on the Lyapunov optimization theory, which does not need any future statistics and possesses low computational complexity. Through theoretical analysis of our algorithm, we can conclude that our strategy can approximate the optimality with provable bounds. Meanwhile, we design a revenue division algorithm based on the Nash bargaining theory to fairly share the revenue among residents. We also conduct extensive trace-driven simulations and results show that our algorithm can obtain nearly 12% of cost reduction for the community when compared with noncooperative algorithms, and ensure the fairness among residents in the meanwhile.

Federated Learning (FL) is an emerging decentralized learning framework through which multiple clients can collaboratively train a learning model. However, a major obstacle that impedes the wide deployment of FL lies in massive communication traffic. To train high dimensional machine learning models (such as CNN models), heavy communication traffic can be incurred by exchanging model updates via the Internet between clients and the parameter server (PS), implying that the network resource can be easily exhausted. Compressing model updates is an effective way to reduce the traffic amount. However, a flexible unbiased compression algorithm applicable for both uplink and downlink compression in FL is still absent from existing works. In this work, we devise the Model Update Compression by Soft Clustering (MUCSC) algorithm to compress model updates transmitted between clients and the PS. In MUCSC, it is only necessary to transmit cluster centroids and the cluster ID of each model update. Moreover, we prove that: 1) The compressed model updates are unbiased estimation of their original values so that the convergence rate by transmitting compressed model updates is unchanged; 2) MUCSC can guarantee that the influence of the compression error on the model accuracy is minimized. Then, we further propose the boosted MUCSC (B-MUCSC) algorithm, a biased compression algorithm that can achieve an extremely high compression rate by grouping insignificant model updates into a super cluster. B-MUCSC is suitable for scenarios with very scarce network resource. Ultimately, we conduct extensive experiments with the CIFAR-10 and FEMNIST datasets to demonstrate that our algorithms can not only substantially reduce the volume of communication traffic in FL, but also improve the training efficiency in practical networks.