Dongning Guo

Shamik Sarkar, Dongning Guo, Danijela Cabric

Spatial prediction of the radio propagation environment of a transmitter can assist and improve various aspects of wireless networks. The majority of research in this domain can be categorized as 'reactive' spatial prediction, where the predictions are made based on a small set of measurements from an active transmitter whose radio environment is to be predicted. Emerging spectrum-sharing paradigms would benefit from 'proactive' spatial prediction of the radio environment, where the spatial predictions must be done for a transmitter for which no measurement has been collected. This paper proposes a novel, supervised deep learning-based framework, ProSpire, that enables spectrum sharing by leveraging the idea of proactive spatial prediction. We carefully address several challenges in ProSpire, such as designing a framework that conveniently collects training data for learning, performing the predictions in a fast manner, enabling operations without an area map, and ensuring that the predictions do not lead to undesired interference. ProSpire relies on the crowdsourcing of transmitters and receivers during their normal operations to address some of the aforementioned challenges. The core component of ProSpire is a deep learning-based image-to-image translation method, which we call RSSu-net. We generate several diverse datasets using ray tracing software and numerically evaluate ProSpire. Our evaluations show that RSSu-net performs reasonably well in terms of signal strength prediction, 5 dB mean absolute error, which is comparable to the average error of other relevant methods. Importantly, due to the merits of RSSu-net, ProSpire creates proactive boundaries around transmitters such that they can be activated with 97% probability of not causing interference. In this regard, the performance of RSSu-net is 19% better than that of other comparable methods.

Arman Mollakhani, Jerayu Tiamraj, Shu-Jie Cao et al.

Large-scale low-Earth-orbit satellite constellations offer a promising platform for global low-latency networking, aided by faster propagation in free space than in fiber and copper. In such systems, end-to-end latency is largely determined by the inter-satellite link (ISL) topology. In particular, the network diameter, the maximum shortest path between any pair of satellites, serves as a key performance metric for time-sensitive applications. Designing diameter-optimal topologies is challenging due to degree constraints, line-of-sight limitations, and orbital dynamics. This paper proposes a two-stage optimization framework for ISL topology design. First, a continuous relaxation of the link selection problem is formulated as a convex program that maximizes the algebraic connectivity of the Laplacian, serving as a tractable surrogate for diameter minimization. Second, the resulting fractional solution is mapped to a feasible discrete topology using integer linear programming. An iterative local-search heuristic is also developed as a baseline. Extensive simulations on Walker-Delta constellations show that the proposed method consistently achieves smaller network diameters and improved robustness compared to conventional heuristics, while allowing trade-offs between latency and link persistence. The approach offers a principled framework for designing high-performance satellite mesh networks. For a constellation of 1,500 satellites, each equipped with four ISLs of up to 2,500 km, the network diameter can be reduced to as low as 12, yielding end-to-end delays under 90 ms between any two points on Earth.

Jinke Ren, Chonghe Liu, Guanding Yu et al.

Generative adversarial networks (GANs) are emerging machine learning models for generating synthesized data similar to real data by jointly training a generator and a discriminator. In many applications, data and computational resources are distributed over many devices, so centralized computation with all data in one location is infeasible due to privacy and/or communication constraints. This paper proposes a new framework for training GANs in a distributed fashion: Each device computes a local discriminator using local data; a single server aggregates their results and computes a global GAN. Specifically, in each iteration, the server sends the global GAN to the devices, which then update their local discriminators; the devices send their results to the server, which then computes their average as the global discriminator and updates the global generator accordingly. Two different update schedules are designed with different levels of parallelism between the devices and the server. Numerical results obtained using three popular datasets demonstrate that the proposed framework can outperform a state-of-the-art framework in terms of convergence speed.

Yasar Sinan Nasir, Dongning Guo

A wireless network operator typically divides the radio spectrum it possesses into a number of subbands. In a cellular network those subbands are then reused in many cells. To mitigate co-channel interference, a joint spectrum and power allocation problem is often formulated to maximize a sum-rate objective. The best known algorithms for solving such problems generally require instantaneous global channel state information and a centralized optimizer. In fact those algorithms have not been implemented in practice in large networks with time-varying subbands. Deep reinforcement learning algorithms are promising tools for solving complex resource management problems. A major challenge here is that spectrum allocation involves discrete subband selection, whereas power allocation involves continuous variables. In this paper, a learning framework is proposed to optimize both discrete and continuous decision variables. Specifically, two separate deep reinforcement learning algorithms are designed to be executed and trained simultaneously to maximize a joint objective. Simulation results show that the proposed scheme outperforms both the state-of-the-art fractional programming algorithm and a previous solution based on deep reinforcement learning.

Jing Li, Ling Ren, Dongning Guo

Bitcoin is a peer-to-peer electronic cash system invented by Nakamoto in 2008. While it has attracted much research interest, its exact latency and security properties remain open. Existing analyses provide security and latency (or confirmation time) guarantees that are too loose for practical use. In fact the best known upper bounds are several orders of magnitude larger than a lower bound due to a well-known private-mining attack. This paper describes a continuous-time model for blockchains and develops a rigorous analysis that yields close upper and lower bounds for the latency--security trade-off. For example, when the adversary controls 10\% of the total mining power and the block propagation delays are within 10 seconds, a Bitcoin block is secured with less than $10^{-3}$ error probability if it is confirmed after four hours, or with less than $10^{-9}$ error probability if confirmed after ten hours. These confirmation times are about two hours away from their corresponding lower bounds. To establish such close bounds, the blockchain security question is reduced to a race between the Poisson adversarial mining process and a renewal process formed by a certain species of honest blocks. The moment generation functions of relevant renewal times are derived in closed form. The general formulas from the analysis are then applied to study the latency--security trade-off of several well-known proof-of-work longest-chain cryptocurrencies. Guidance is also provided on how to set parameters for different purposes.

Yasar Sinan Nasir, Dongning Guo

Deep reinforcement learning offers a model-free alternative to supervised deep learning and classical optimization for solving the transmit power control problem in wireless networks. The multi-agent deep reinforcement learning approach considers each transmitter as an individual learning agent that determines its transmit power level by observing the local wireless environment. Following a certain policy, these agents learn to collaboratively maximize a global objective, e.g., a sum-rate utility function. This multi-agent scheme is easily scalable and practically applicable to large-scale cellular networks. In this work, we present a distributively executed continuous power control algorithm with the help of deep actor-critic learning, and more specifically, by adapting deep deterministic policy gradient. Furthermore, we integrate the proposed power control algorithm to a time-slotted system where devices are mobile and channel conditions change rapidly. We demonstrate the functionality of the proposed algorithm using simulation results.

Jinke Ren, Yinghui He, Dingzhu Wen et al.

In cellular federated edge learning (FEEL), multiple edge devices holding local data jointly train a neural network by communicating learning updates with an access point without exchanging their data samples. With very limited communication resources, it is beneficial to schedule the most informative local learning updates. In this paper, a novel scheduling policy is proposed to exploit both diversity in multiuser channels and diversity in the "importance" of the edge devices' learning updates. First, a new probabilistic scheduling framework is developed to yield unbiased update aggregation in FEEL. The importance of a local learning update is measured by its gradient divergence. If one edge device is scheduled in each communication round, the scheduling policy is derived in closed form to achieve the optimal trade-off between channel quality and update importance. The probabilistic scheduling framework is then extended to allow scheduling multiple edge devices in each communication round. Numerical results obtained using popular models and learning datasets demonstrate that the proposed scheduling policy can achieve faster model convergence and higher learning accuracy than conventional scheduling policies that only exploit a single type of diversity.

Jing Li, Dongning Guo

Bitcoin is a peer-to-peer payment system proposed by Nakamoto in 2008. Based on the Nakamoto consensus, Bagaria, Kannan, Tse, Fanti, and Viswanath proposed the Prism protocol in 2018 and showed that it achieves near-optimal blockchain throughput while maintaining a similar level of security as bitcoin. Previous probabilistic security guarantees for the bitcoin and Prism backbone protocols were either established under a simplified discrete-time model or expressed in terms of exponential order results. This paper presents a streamlined and strengthened analysis under a more realistic continuous-time model. A fully rigorous model for blockchains is developed with no restrictions on adversarial miners except for an upper bound on their aggregate mining rate. The only assumption on the peer-to-peer network is that all block propagation delays are upper bounded by a constant. A new notion of "t-credible blockchains" is introduced, which, together with some carefully defined "typical" events concerning block production over time intervals, is crucial to establish probabilisitic security guarantees in continuous time. A blockchain growth theorem, a blockchain quality theorem, and a common prefix theorem are established with explicit probability bounds. Moreover, under a certain typical event which occurs with probability close to $1$, a valid transaction that is deep enough in one credible blockchain is shown to be permanent in the sense that it must be found in} in all future credible blockchains.

Jing Li, Dongning Guo

Bitcoin is a peer-to-peer payment system proposed by Nakamoto in 2008. Properties of the bitcoin backbone protocol have been investigated in some depth: the blockchain growth property quantifies the number of blocks added to the blockchain during any time intervals; the blockchain quality property ensures the honest miners always contribute at least a certain fraction of the blockchain; the common prefix property ensures if a block is deep enough, it will eventually be adopted by all honest miners with high probability. Following the spirit of decoupling various functionalities of the blockchain, the Prism protocol is proposed to dramatically improve the throughput while maintaining the same level of security. Prior analyses of the bitcoin and Prism backbone protocols assume the lifespan of blockchain is finite. This paper presents a streamlined and strengthened analysis without the finite horizon assumption. Specifically, the results include a blockchain growth property, a blockchain quality property, and a common prefix property of the bitcoin backbone protocol, as well as the liveness and persistence of the Prism backbone protocol regardless of whether the blockchains have a infinite lifespan. We also express the properties of bitcoin and Prism backbone protocols in explicit expressions rather than order optimal results, which lead to tighter bounds and practical references for public transaction ledger protocol design.

Yasar Sinan Nasir, Dongning Guo

This work demonstrates the potential of deep reinforcement learning techniques for transmit power control in wireless networks. Existing techniques typically find near-optimal power allocations by solving a challenging optimization problem. Most of these algorithms are not scalable to large networks in real-world scenarios because of their computational complexity and instantaneous cross-cell channel state information (CSI) requirement. In this paper, a distributively executed dynamic power allocation scheme is developed based on model-free deep reinforcement learning. Each transmitter collects CSI and quality of service (QoS) information from several neighbors and adapts its own transmit power accordingly. The objective is to maximize a weighted sum-rate utility function, which can be particularized to achieve maximum sum-rate or proportionally fair scheduling. Both random variations and delays in the CSI are inherently addressed using deep Q-learning. For a typical network architecture, the proposed algorithm is shown to achieve near-optimal power allocation in real time based on delayed CSI measurements available to the agents. The proposed scheme is especially suitable for practical scenarios where the system model is inaccurate and CSI delay is non-negligible.