arXiv research

Proposes a regularization approach to model German power derivative market, identifying significant risk spillovers.

Paper examines power consumption in neural networks using various activation functions.

This paper considers the computational power of constant size, dynamic Bayesian networks. Although discrete dynamic Bayesian networks are no more powerful than hidden Markov models, dynamic Bayesian networks with continuous random variables and discrete children of continuous parents are capable of performing Turing-co…

Survey on GNNs' power and limitations.

Paper introduces reinforcement learning for managing power grids.

This work develops a novel power control framework for energy-efficient power control in wireless networks. The proposed method is a new branch-and-bound procedure based on problem-specific bounds for energy-efficiency maximization that allow for faster convergence. This enables to find the global solution for all of t…

kth-order invariant graph networks are as powerful as kth-order WL in distinguishing graphs.

Power of network tests degrades when vertices are misaligned.

This work optimizes DNN inference for energy-harvesting devices by compressing and selectively executing neural network exits.

The power law has been observed in the degree distributions of many biological neural networks. Sparse deep neural networks, which learn an economical representation from the data, resemble biological neural networks in many ways. In this paper, we study if these artificial networks also exhibit properties of the power…

Power system studies require the topological structures of real-world power networks; however, such data is confidential due to important security concerns. Thus, power grid synthesis (PGS), i.e., creating realistic power grids that imitate actual power networks, has gained significant attention. In this letter, we cas…

P2P lending activities have grown rapidly and have caused the huge and complex networks of debtor-creditor relationships. The aim of this study was to study the underlying structural characteristics of networks formed by debtor-creditor relationships. According attributes of P2P lending, this paper model the networks o…

Deep actor-critic learning optimizes power control in mobile networks.

This work investigates power laws in deep neural network ensembles and predicts their performance.

Graph Attention Networks predict power outage durations from natural disasters.

New method explains GNNs using power iteration clustering.

We experimentally achieve a 19% capacity gain per Watt of electrical supply power in a 12-span link by eliminating gain flattening filters and optimizing launch powers using machine learning by deep neural networks in a massively parallel fiber context.

Neural network predicts daily power consumption with high accuracy.

PowRL uses RL to manage power grids robustly, reducing overloads and maintaining power reliability.

New KWS neural networks improve accuracy and power efficiency.

The angular power spectrum characterizes neural network complexity.

A new method compares synthetic power networks to actual ones using multiscale flat norm.

Deep neural networks can approximate complex functions through repeated compositions of a fixed-size ReLU network.

A powerful network teaches a weak one, improving its performance.

New MPNNs match 2-WL, faster distinguishing graphs.

This paper explores how enforcing equivariance constraints limits neural network expressivity and proposes compensatory model size increases.

Characterizes a specific type of neural network for alternating group equivariance.

We consider the problem of downlink power control in wireless networks, consisting of multiple transmitter-receiver pairs communicating with each other over a single shared wireless medium. To mitigate the interference among concurrent transmissions, we leverage the network topology to create a graph neural network arc…

Survey of RL methods for optimizing power grid topologies.

A deep neural network (DNN) based power control method is proposed, which aims at solving the non-convex optimization problem of maximizing the sum rate of a multi-user interference channel. Towards this end, we first present PCNet, which is a multi-layer fully connected neural network that is specifically designed for…

Deep RL improves power control and scheduling for wireless multicast systems.

Paper tackles RL for power grid topology optimization.

PoET-BiN reduces power consumption in neural networks on embedded devices.

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 scena…

New algorithm extracts device profiles for short-term power predictions in commercial buildings.

Electronic power inverters are capable of quickly delivering reactive power to maintain customer voltages within operating tolerances and to reduce system losses in distribution grids. This paper proposes a systematic and data-driven approach to determine reactive power inverter output as a function of local measuremen…

Optimal resource allocation is a fundamental challenge for dense and heterogeneous wireless networks with massive wireless connections. Because of the non-convex nature of the optimization problem, it is computationally demanding to obtain the optimal resource allocation. Recently, deep reinforcement learning (DRL) has…

Improves neural network performance by enriching training dataset.

Network data appear in a number of applications, such as online social networks and biological networks, and there is growing interest in both developing models for networks as well as studying the properties of such data. Since individual network datasets continue to grow in size, it is necessary to develop models tha…

Fine-tuning normalization layers can reconstruct smaller networks.

Recent technological advances have proliferated the available computing power, memory, and speed of modern Central Processing Units (CPUs), Graphics Processing Units (GPUs), and Field Programmable Gate Arrays (FPGAs). Consequently, the performance and complexity of Artificial Neural Networks (ANNs) is burgeoning. While…

Improved bounds on neural network expressivity.

Neural Power Unit (NPU) learns arbitrary power functions on real numbers.

Deep reinforcement learning boosts throughput in RF-powered cognitive radio networks.

The approximation power of general feedforward neural networks with piecewise linear activation functions is investigated. First, lower bounds on the size of a network are established in terms of the approximation error and network depth and width. These bounds improve upon state-of-the-art bounds for certain classes o…

Wind energy forecasting helps to manage power production, and hence, reduces energy cost. Deep Neural Networks (DNN) mimics hierarchical learning in the human brain and thus possesses hierarchical, distributed, and multi-task learning capabilities. Based on aforementioned characteristics, we report Deep Belief Network …

Novel power transform unifies various mathematical functions.

Superposition accelerates training to a universal power-law exponent.