Search

In this paper, we address the discrete-time dynamic average consensus (DAC) of a multi-agent system in the presence of adversarial attacks. The adversarial attack is considered to be of Byzantine type, which compromises the computation capabilities of the agent and sends arbitrary false data to its neighbours. We assume a few of the agents cannot be compromised by adversaries, which we term trusted agents. We first formally define resilient DAC in the presence of Byzantine adversaries. Then we propose our novel Resilient Dynamic Average Consensus (ResDAC) algorithm that ensures the trusted and ordinary agents achieve resilient DAC in the presence of adversarial agents. The only requirements are that of the trusted agents forming a connected dominating set and the first-order differences of the reference signals being bounded. We do not impose any restriction on the tolerable number of adversarial agents that can be present in the network. We also do not restrict the reference signals to be bounded. Finally, we provide numerical simulations to illustrate the effectiveness of the proposed ResDAC algorithm., Comment: Initial Draft

In this article, we investigate the distributed DC-Optimal Power Flow (DC-OPF) problem against a backdrop of online convex optimization with coupled constraints. While the classical OPF problem refers to a time-invariant optimization environment across the power distribution network, the online variant involves time-varying objectives and equality constraints, with the cost functions gradually being disclosed to the generating agents in the network. The agents (generators and loads) in the network are only privy to their own local objectives and constraints. To this end, we address the problem by proposing a distributed online algorithm based on the modified primal-dual approach, which deals with the online equality-constrained issue. It has been theoretically demonstrated that the proposed algorithm exhibits a sublinearly bounded \textit{static} regret and constraint violation with a suitable choice of descending stepsizes. Finally, we corroborate the results by illustrating them with numerical examples., Comment: 11 pages, 4 figures, Under Review

This paper considers the design of a distributed state-observer for discrete-time Linear Time-Invariant (LTI) systems in the presence of sensor attacks. We assume there is a network of observer nodes, communicating with each other over an undirected graph, each with partial measurements of the output corrupted by some adversarial attack. We address the case of sparse attacks where the attacker targets a small subset of sensors. An algorithm based on Alternating Direction Method of Multipliers (ADMM) is developed which provides an update law for each observer which ensures convergence of each observer node to the actual state asymptotically., Comment: 7 pages, 6 figures

We consider the problem of achieving average consensus among multiple agents, where the inter-agent communication network is depicted by a graph. We consider the discrete-time consensus protocol where each agent updates its value as a weighted average of its own value and those of its neighbours. Given a graph, it is known that there exists a set of 'optimal weights' such that the agents reach average consensus asymptotically with an optimal rate of convergence. However, existing methods require the knowledge of the entire graph to compute these optimal weights. We propose a method for each agent to compute its set of optimal weights locally, i.e., each agent only has to know who are its neighbours. The method is derived by solving a matrix norm minimization problem subject to linear constraints in a distributed manner using the Alternating Direction Method of Multipliers (ADMM). We illustrate our results using numerical examples and compare our method with an existing method called the Metropolis weights, which are also computed locally.