arXiv subjects

Sihai Zhang

Publications and source records attributed to Sihai Zhang.

11 recordsLinked to original sources

arXiv2025

A Model-Data Dual-Driven Resource Allocation Scheme for IREE Oriented 6G Networks

The rapid and substantial fluctuations in wireless network capacity and traffic demand, driven by the emergence of 6G technologies, have exacerbated the issue of traffic-capacity mismatch, raising concerns about wireless network energy consumption. To address this challenge, we propose a model-data dual-driven resource allocation (MDDRA) algorithm aimed at maximizing the integrated relative energy efficiency (IREE) metric under dynamic traffic conditions. Unlike conventional model-driven or data-driven schemes, the proposed MDDRA framework employs a model-driven Lyapunov queue to accumulate long-term historical mismatch information and a data-driven Graph Radial bAsis Fourier (GRAF) network to predict the traffic variations under incomplete data, and hence eliminates the reliance on high-precision models and complete spatial-temporal traffic data. We establish the universal approximation property of the proposed GRAF network and provide convergence and complexity analysis for the MDDRA algorithm. Numerical experiments validate the performance gains achieved through the data-driven and model-driven components. By analyzing IREE and EE curves under diverse traffic conditions, we recommend that network operators shall spend more efforts to balance the traffic demand and the network capacity distribution to ensure the network performance, particularly in scenarios with large speed limits and higher driving visibility.

cs.NI↗

arXiv2023

The Predictability of Stock Price: Empirical Study onTick Data in Chinese Stock Market

Whether or not stocks are predictable has been a topic of concern for decades.The efficient market hypothesis (EMH) says that it is difficult for investors to make extra profits by predicting stock prices, but this may not be true, especially for the Chinese stock market. Therefore, we explore the predictability of the Chinese stock market based on tick data, a widely studied high-frequency data. We obtain the predictability of 3, 834 Chinese stocks by adopting the concept of true entropy, which is calculated by Limpel-Ziv data compression method. The Markov chain model and the diffusion kernel model are used to compare the upper bounds on predictability, and it is concluded that there is still a significant performance gap between the forecasting models used and the theoretical upper bounds.Our work shows that more than 73% of stocks have prediction accuracy greater than 70% and RMSE less than 2 CNY under different quantification intervals with different models. We further take Spearman's correlation to reveal that the average stock price and price volatility may have a negative impact on prediction accuracy, which may be helpful for stock investors.

math.NA↗

arXiv2021

DACFL: Dynamic Average Consensus Based Federated Learning in Decentralized Topology

Federated learning (FL) is a burgeoning distributed machine learning framework where a central parameter server (PS) coordinates many local users to train a globally consistent model. Conventional federated learning inevitably relies on a centralized topology with a PS. As a result, it will paralyze once the PS fails. To alleviate such a single point failure, especially on the PS, some existing work has provided decentralized FL (DFL) implementations like CDSGD and D-PSGD to facilitate FL in a decentralized topology. However, there are still some problems with these methods, e.g., significant divergence between users' final models in CDSGD and a network-wide model average necessity in D-PSGD. In order to solve these deficiency, this paper devises a new DFL implementation coined as DACFL, where each user trains its model using its own training data and exchanges the intermediate models with its neighbors through a symmetric and doubly stochastic matrix. The DACFL treats the progress of each user's local training as a discrete-time process and employs a first order dynamic average consensus (FODAC) method to track the \textit{average model} in the absence of the PS. In this paper, we also provide a theoretical convergence analysis of DACFL on the premise of i.i.d data to strengthen its rationality. The experimental results on MNIST, Fashion-MNIST and CIFAR-10 validate the feasibility of our solution in both time-invariant and time-varying network topologies, and declare that DACFL outperforms D-PSGD and CDSGD in most cases.

cs.LG↗

arXiv2021

Resonant Beam Communications with Echo Interference Elimination

Resonant beam communications (RBCom) is capable of providing wide bandwidth when using light as the carrier. Besides, the RBCom system possesses the characteristics of mobility, high signal-to-noise ratio (SNR), and multiplexing. Nevertheless, the channel of the RBCom system is distinct from other light communication technologies due to the echo interference issue. In this paper, we reveal the mechanism of the echo interference and propose the method to eliminate the interference. Moreover, we present an exemplary design based on frequency shifting and optical filtering, along with its mathematic model and performance analysis. The numerical evaluation shows that the channel capacity is greater than 15 bit/s/Hz.

eess.SP↗

arXiv2020

Knowledge-Driven Machine Learning: Concept, Model and Case Study on Channel Estimation

The power of big data and machine learning has been drastically demonstrated in many fields during the past twenty years which somehow leads to the vague even false understanding that the huge amount of precious human knowledge accumulated to date no longer seems to matter. In this paper, we are pioneering to propose the knowledge-driven machine learning(KDML) model to exhibit that knowledge can play an important role in machine learning tasks. KDML takes advantage of domain knowledge to processes the input data by space transforming without any training which enable the space of input and the output data of the neural networks to be identical, so that we can simplify the machine learning network structure and reduce training costs significantly. Channel estimation problems considering the time selective and frequency selective fading in wireless communications are taken as a case study, where we choose least square(LS) and minimum meansquare error(MMSE) as knowledge module and Long Short Term Memory(LSTM) as learning module. The performance obtained by KDML channel estimator obviously outperforms that of knowledge processing or conventional machine learning, respectively. Our work sheds light on the new area of machine learning and knowledge processing.

eess.SP↗

arXiv2020

Semi-Federated Learning

Federated learning (FL) enables massive distributed Information and Communication Technology (ICT) devices to learn a global consensus model without any participants revealing their own data to the central server. However, the practicality, communication expense and non-independent and identical distribution (Non-IID) data challenges in FL still need to be concerned. In this work, we propose the Semi-Federated Learning (Semi-FL) which differs from the FL in two aspects, local clients clustering and in-cluster training. A sequential training manner is designed for our in-cluster training in this paper which enables the neighboring clients to share their learning models. The proposed Semi-FL can be easily applied to future mobile communication networks and require less up-link transmission bandwidth. Numerical experiments validate the feasibility, learning performance and the robustness to Non-IID data of the proposed Semi-FL. The Semi-FL extends the existing potentials of FL.

cs.LG↗

arXiv2020

Real Entropy Can Also Predict Daily Voice Traffic for Wireless Network Users

Voice traffic prediction is significant for network deployment optimization thus to improve the network efficiency. The real entropy based theorectical bound and corresponding prediction models have demonstrated their success in mobility prediction. In this paper, the real entropy based predictability analysis and prediction models are introduced into voice traffic prediction. For this adoption, the traffic quantification methods is proposed and discussed. Based on the real world voice traffic data, the prediction accuracy of N-order Markov models, diffusion based model and MF model are presented, among which, 25-order Markov models performs best and approach close to the maximum predictability. This work demonstrates that, the real entropy can also predict voice traffic well which broaden the understanding on the real entropy based prediction theory.

cs.NI↗

arXiv2019

Functional Gaussian Distribution Modelling of Mobility Prediction Accuracy for Wireless Users

Mobility entropy is proposed to measure predictability of human movements, based on which, the upper and lower bound of prediction accuracy is deduced, but corresponding mathematical expressions of prediction accuracy keeps yet open. In this work, we try to analyze and model prediction accuracy in terms of entropy based on the 2-order Markov chain model empirical results on a large scale CDR data set, which demonstrates the observation that users with the same level of entropy achieve different levels of accuracy\cite{Empirical}. After dividing entropy into intervals, we fit the probability density distributions of accuracy in each entropy interval with Gaussian distribution and then we estimate the corresponding mean and standard deviation of these distributions. After observing that the parameters vary with increasing entropy, we then model the relationship between parameters and entropy using least squares method. The mean can be modelled as a linear function, while the standard deviation can be modelled as a Gaussian distribution. Thus based on the above analysis, the probability density function of accuracy given entropy can be expressed by functional Gaussian distribution. The insights from our work is the first step to model the correlation prediction accuracy and predictability entropy, thus shed light on the further work in this direction.

cs.SI↗

arXiv2013

Traffic-Aware Relay Sleep Control to Improve Energy Efficiency in Joint Macro-Relay Networks

In this letter, we consider a joint macro-relay network with densely deployed relay stations (RSs) and dynamically varied traffic load measured by the number of users. An energy-efficient strategy is proposed by intelligently adjusting the RS working modes (active or sleeping) according to the traffic variation. Explicit expressions related to the network energy efficiency are derived based on stochastic geometry theory. Simulation results demonstrate that the derived analytic results are reasonable and the proposed strategy can significantly improve the network energy efficiency.

cs.NI↗

arXiv2012

A Stochastic Geometry Approach to Energy Efficiency in Relay-Assisted Cellular Networks

Though cooperative relaying is believed to be a promising technology to improve the energy efficiency of cellular networks, the relays' static power consumption might worsen the energy efficiency therefore can not be neglected. In this paper, we focus on whether and how the energy efficiency of cellular networks can be improved via relays. Based on the spatial Poisson point process, an analytical model is proposed to evaluate the energy efficiency of relay-assisted cellular networks. With the aid of the technical tools of stochastic geometry, we derive the distributions of signal-to-interference-plus-noise ratios (SINRs) and mean achievable rates of both non-cooperative users and cooperative users. The energy efficiency measured by "bps/Hz/W" is expressed subsequently. These established expressions are amenable to numerical evaluation and corroborated by simulation results.

cs.NI↗

arXiv2012

Combined Channel Aggregation and Fragmentation Strategy in Cognitive Radio Networks

In cognitive radio networks, channel aggregation (CA) and channel fragmentation (CF) techniques have been proposed to enhance the spectrum utilization. While most of the literature studies CA and CF independently, in this paper we combine CA and CF innovatively and present a new spectrum sharing strategy named CAF (Channel Aggregation and Fragmentation). We elaborate on the proposed CAF strategy and derive the balance equation by a continuous time Markov chain (CTMC) model. Then various system performance metrics including blocking probability, dropping probability, spectrum utilization and throughput of the secondary network are evaluated. Both analytical and simulation results show that our strategy lowers the blocking and dropping probabilities and enhances the spectrum utilization and throughput effectively. Moreover, by tuning the bandwidth requirement of each secondary user, different system performance can be achieved.

cs.NI↗