Search

There is an ever-growing number of photovoltaic (PV) installations in the US and worldwide. Many utilities do not have complete or up-to-date information of the PVs present within their grids. This research presents a deep neural network approach for estimating PV size, tilt, and azimuth using only behind-the-meter data. It is found that the proposed deep neural network (DNN) method can estimate PV size with an error of 2.09% in a data set with fixed tilt and azimuth values and 3.98% in a data set with varying tilt and azimuths. This is a lower error than the benchmark linear regression approach. A net load data resolution of 1 min provides the lowest error when estimating the PV size. The proposed DNN is also reasonably robust to erroneous training data. When applied to estimate PV tilt and azimuth, the proposed method achieves a mean absolute percentage error of 10.1% and 2.8% respectively. These error metrics are 2.0 × and 3.7 × lower, respectively, than the benchmark linear regression achieves. It was observed that a higher data resolution (1 min) does not provide significant gains in accuracy. It is recommended that a data resolution of 60 min is used to reduce the effects of phenomena such as cloud enhancements. The proposed deep neural network approach is also highly robust, maintaining reasonable accuracy with high levels of mislabeled training data.

The Infrastructure as a Service (IaaS) platform in cloud computing provides resources as a service from a pool of compute, network, and storage resources. One of the major challenges facing cloud computing is to predict the usage of these resources in real time. By knowing future demands, cloud data centres can dynamically scale resources to decrease energy consumption while maintaining a high quality of service. However cloud resource consumption is ever changing, making it difficult for accurate predictions to be produced. This motivates the research presented in this paper which aims to predict in advance the level of CPU consumption of a host. This research implements evolutionary Neural Networks (NN), a powerful machine learning method, to make these predictions. A number of state of the art swarm and evolutionary optimization algorithms are implemented to train the neural networks to predict host utilization: Particle Swarm Optimization (PSO), Differential Evolution (DE) and Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES). The results of this research demonstrate that CMA-ES converges faster to a better solution on the training data. However when evaluated on the test data, DE performs statistically equal to CMA-ES. The results also demonstrate that the trained networks are still accurate when applied to CPU utilization data from different hosts with no further training needed. When evaluated to predict multiple steps into the future, the accuracy of the network understandably decreases but still performs well on average.

Multi-objective optimisation has received considerable attention in recent years as many real world problems have multiple conflicting objectives. There is an additional layer of complexity when considering multi-objective problems in dynamic environments due to the changing nature of the problem. A novel Multi-Objective Neural Network trained with Differential Evolution (MONNDE) is presented in this research. MONNDE utilizes Neural Network function approximators to address dynamic multi-objective optimisation problems. Differential Evolution (DE) is a state of the art single objective global optimisation problems and will be used to evolve neural networks capable of generating Pareto fronts. The proposed MONNDE algorithm has the added advantage of developing an approximation of the problem that can produce further Pareto fronts as the environment changes with no further optimisation needed. The MONNDE framework is applied to the Dynamic Economic Emission Dispatch (DEED) problem and performs equally optimal when compared to other state of the art algorithms in terms of the 24 h cost and emissions. This research also compares the performance of fully and partially connected networks and discovers that dynamically optimising the topology of the neural networks performs better in an online learning environment than simply optimising the network weights.

The ability to accurately predict future power demands, power available from renewable resources and the environmental impact of power generation is vital to the energy sector for the purposes of planning, scheduling and policy making. Machine learning techniques, neural networks in particular, have proven to be very effective methods for addressing these challenging forecasting problems. This research utilizes the powerful evolutionary optimisation algorithm, covariance matrix adaptation evolutionary strategy, as a means of training neural networks to predict short term power demand, wind power generation and carbon dioxide intensity levels in Ireland over a two month period. The network is trained over one month and then tested over the following month. A neural network trained with covariance matrix adaptation evolutionary strategy performs very competitively when compared to other state of the art prediction methods when forecasting Ireland's energy needs, providing fast convergence, more accurate predictions and robust performance. The covariance matrix adaptation evolutionary strategy trained network also gives accurate predictions when predicting multiple time steps into the future.

Particle swarm optimisation (PSO) is a general purpose optimisation algorithm used to address hard optimisation problems. The algorithm operates as a result of a number of particles converging on what is hoped to be the best solution. How the particles move through the problem space is therefore critical to the success of the algorithm. This study utilises meta optimisation to compare a number of velocity update equations to determine which features of each are of benefit to the algorithm. A number of hybrid velocity update equations are proposed based on other high performing velocity update equations. This research also presents a novel application of PSO to train a neural network function approximator to address the watershed management problem. It is found that the standard PSO with a linearly changing inertia, the proposed hybrid Attractive Repulsive PSO with avoidance of worst locations (AR PSOAWL) and Adaptive Velocity PSO (AV PSO) provide the best performance overall. The results presented in this paper also reveal that commonly used PSO parameters do not provide the best performance. Increasing and negative inertia values were found to perform better.

The power sector is undergoing a period of significant change, in terms of the mix of generation technologies, as well as the structure of energy markets, regulation and assets ownership. The shift to a more liberalised electricity system has resulted in an increase in the number of decision makers. This paper demonstrates an agent-based approach for investigating the long-term investment in the GB power generation sector, whilst considering the operability of the system. A key focus of this study is to investigate the efficacy of a range of policies to reduce the emissions and facilitate investment in renewable generation and battery storage. In order to capture the value of battery storage, the hourly operation of the electricity system, considering short-term variation of demand, renewable generation and wholesale electricity prices (including negative prices during high renewable and low demand events), was incorporated in the long-term investment model. The modelling results show while the cost of battery storage is expected to decrease gradually in future, a substantial subsidy is still required to justify investment in battery storage. The deployment of battery storage provides a significant reduction in the overall power generation system cost, peak demand and carbon emissions.

Particle swarm optimisation (PSO) is a bio-inspired swarm based approach to solving optimisation problems. The algorithm functions as a result of particles traversing and evaluating the problem space, eventually converging on the optimum solution. This paper applies a number of PSO variants to the dynamic economic emission dispatch (DEED) problem. The DEED problem is a multi-objective optimisation problem in which the goal is to optimise two conflicting objectives: cost and emissions. The PSO variants tested include: the standard PSO (SPSO), the PSO with avoidance of worst locations (PSO AWL), and also a selection of different topologies including the PSO with a gradually increasing directed neighbourhood (PSO GIDN). The aim of the paper is to test the performance of different variants of the PSO AWL against variants of the SPSO on the DEED problem. The results show that the PSO AWL outperforms the SPSO for every topology implemented. The results are also compared to state of the art genetic algorithm (NSGA-II) and multi-agent eeinforcement learning (MARL). This paper then examines the performance of each PSO algorithm when the power demand is modified to form a triangle wave. The purpose of this experiment was to analyse the performance of different PSO variants on an increasingly constrained problem.

Reinforcement Learning (RL) is a powerful and well-studied Machine Learning paradigm, where an agent learns to improve its performance in an environment by maximising a reward signal. In multi-objective Reinforcement Learning (MORL) the reward signal is a vector, where each component represents the performance on a different objective. Reward shaping is a well-established family of techniques that have been successfully used to improve the performance and learning speed of RL agents in single-objective problems. The basic premise of reward shaping is to add an additional shaping reward to the reward naturally received from the environment, to incorporate domain knowledge and guide an agent’s exploration. Potential-Based Reward Shaping (PBRS) is a specific form of reward shaping that offers additional guarantees. In this paper, we extend the theoretical guarantees of PBRS to MORL problems. Specifically, we provide theoretical proof that PBRS does not alter the true Pareto front in both single- and multi-agent MORL. We also contribute the first published empirical studies of the effect of PBRS in single- and multi-agent MORL problems.