arXiv subjects

Tim Green

Publications and source records attributed to Tim Green.

5 recordsLinked to original sources

arXiv2020

Early Insights into System Impacts of Smart Local Energy Systems

A whole-system, investment-optimising model has been used to examine the change in total cost of meeting demand for electricity when Smart Local Energy Systems (SLES) are deployed. Our assumption is that SLES, alongside their other features, enhance the flexibility of electricity consumption through demand-side response (DSR) and facilitate use of local energy storage. We find that with the flexibility of SLES present, variable renewables such as offshore wind can displace firm but more expensive low-carbon sources such as CCS. Considering a 100 gCO2/kWh emissions target in 2030, a 10% penetration of SLES could reduce total costs by {\pounds}1.2bn/year relative to no SLES, while at higher penetration of 50% SLES, savings increase twofold to {\pounds}2.8bn/year. Under a more stringent emissions limit of 25 gCO2/kWh in 2040, the savings rise to {\pounds}2.9bn/year for 10% SLES uptake and rise threefold to {\pounds}8.7bn/year at 50% uptake. These results hold for costs of enabling DSR of less than {\pounds}100/kW and it is not until an unlikely {\pounds}5,000/kW that the savings are nullified. The savings from substituting wind for CCS remain substantial even if the anticipated reduction of cost of wind in 2040 does not materialise. Cost savings from the flexibility provided by SLES are affected by realisation of domestic DSR through other means. A 20% uptake level of non-SLES DSR in 2040 still allows SLES to create cost savings of {\pounds}6.8bn/year at 50% penetration (a 20% fall from {\pounds}8.7bn/year).

physics.soc-ph↗

arXiv2019

Impedance-Based Whole-System Modeling for a Composite Grid via Frame-Dynamics Embedding

The paper establishes a methodology to overcome the difficulty of dynamic frame alignment and system separation in impedance modeling of ac grids, and thereby enables impedance-based whole-system modeling of generator-converter composite power systems. The methodology is based on a frame-dynamics-embedding transformation via an intermediary steady frame between local and global frames, which yields a locally defined impedance model for each generator or converter that does not rely on a global frame but retains all frame dynamics. The individual impedance model can then be readily combined into a whole-system model even for meshed networks via the proposed closed-loop formulation without network separation. Compared to start-of-the-art impedance-based models, the proposed method retains both frame dynamics and scalability, and is generally applicable to various network topologies (meshed, radial, etc) and combinations of machines (generators, motors, converters, etc). The methodology is used to analyze the dynamic interaction between generators and converters in a composite grid, which yields important findings and potential solutions for unstable oscillation caused by PLL-swing coupling in low-inertia grids.

eess.SY↗

arXiv2018

Human-level performance in first-person multiplayer games with population-based deep reinforcement learning

Recent progress in artificial intelligence through reinforcement learning (RL) has shown great success on increasingly complex single-agent environments and two-player turn-based games. However, the real-world contains multiple agents, each learning and acting independently to cooperate and compete with other agents, and environments reflecting this degree of complexity remain an open challenge. In this work, we demonstrate for the first time that an agent can achieve human-level in a popular 3D multiplayer first-person video game, Quake III Arena Capture the Flag, using only pixels and game points as input. These results were achieved by a novel two-tier optimisation process in which a population of independent RL agents are trained concurrently from thousands of parallel matches with agents playing in teams together and against each other on randomly generated environments. Each agent in the population learns its own internal reward signal to complement the sparse delayed reward from winning, and selects actions using a novel temporally hierarchical representation that enables the agent to reason at multiple timescales. During game-play, these agents display human-like behaviours such as navigating, following, and defending based on a rich learned representation that is shown to encode high-level game knowledge. In an extensive tournament-style evaluation the trained agents exceeded the win-rate of strong human players both as teammates and opponents, and proved far stronger than existing state-of-the-art agents. These results demonstrate a significant jump in the capabilities of artificial agents, bringing us closer to the goal of human-level intelligence.

cs.LG↗

arXiv2017

Population Based Training of Neural Networks

Neural networks dominate the modern machine learning landscape, but their training and success still suffer from sensitivity to empirical choices of hyperparameters such as model architecture, loss function, and optimisation algorithm. In this work we present \emph{Population Based Training (PBT)}, a simple asynchronous optimisation algorithm which effectively utilises a fixed computational budget to jointly optimise a population of models and their hyperparameters to maximise performance. Importantly, PBT discovers a schedule of hyperparameter settings rather than following the generally sub-optimal strategy of trying to find a single fixed set to use for the whole course of training. With just a small modification to a typical distributed hyperparameter training framework, our method allows robust and reliable training of models. We demonstrate the effectiveness of PBT on deep reinforcement learning problems, showing faster wall-clock convergence and higher final performance of agents by optimising over a suite of hyperparameters. In addition, we show the same method can be applied to supervised learning for machine translation, where PBT is used to maximise the BLEU score directly, and also to training of Generative Adversarial Networks to maximise the Inception score of generated images. In all cases PBT results in the automatic discovery of hyperparameter schedules and model selection which results in stable training and better final performance.

cs.LG↗

arXiv2017

The Kinetics Human Action Video Dataset

We describe the DeepMind Kinetics human action video dataset. The dataset contains 400 human action classes, with at least 400 video clips for each action. Each clip lasts around 10s and is taken from a different YouTube video. The actions are human focussed and cover a broad range of classes including human-object interactions such as playing instruments, as well as human-human interactions such as shaking hands. We describe the statistics of the dataset, how it was collected, and give some baseline performance figures for neural network architectures trained and tested for human action classification on this dataset. We also carry out a preliminary analysis of whether imbalance in the dataset leads to bias in the classifiers.

cs.CV↗