Search

Your search keyword '"Samende, Cephas"' showing total 14 results
Start Over Author "Samende, Cephas"
14 results on '"Samende, Cephas"'

1. Battery and Hydrogen Energy Storage Control in a Smart Energy Network with Flexible Energy Demand using Deep Reinforcement Learning

Author

Samende, Cephas, Fan, Zhong, and Cao, Jun

Subjects
Electrical Engineering and Systems Science - Systems and Control, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Multiagent Systems
Abstract

Smart energy networks provide for an effective means to accommodate high penetrations of variable renewable energy sources like solar and wind, which are key for deep decarbonisation of energy production. However, given the variability of the renewables as well as the energy demand, it is imperative to develop effective control and energy storage schemes to manage the variable energy generation and achieve desired system economics and environmental goals. In this paper, we introduce a hybrid energy storage system composed of battery and hydrogen energy storage to handle the uncertainties related to electricity prices, renewable energy production and consumption. We aim to improve renewable energy utilisation and minimise energy costs and carbon emissions while ensuring energy reliability and stability within the network. To achieve this, we propose a multi-agent deep deterministic policy gradient approach, which is a deep reinforcement learning-based control strategy to optimise the scheduling of the hybrid energy storage system and energy demand in real-time. The proposed approach is model-free and does not require explicit knowledge and rigorous mathematical models of the smart energy network environment. Simulation results based on real-world data show that: (i) integration and optimised operation of the hybrid energy storage system and energy demand reduces carbon emissions by 78.69%, improves cost savings by 23.5% and renewable energy utilisation by over 13.2% compared to other baseline models and (ii) the proposed algorithm outperforms the state-of-the-art self-learning algorithms like deep-Q network., Comment: 13 pages, 10 figures

Published
2022

2. The role of living laboratories in unlocking the potential of low-carbon energy technologies on the journey to net-zero

Author

Fan, Zhong, Cao, Jun, Jamal, Taskin, Fogwill, Chris, Samende, Cephas, Robinson, Zoe, Polack, Fiona, Ormerod, Mark, George, Sharon, Peacock, Adam, and Healey, David

Subjects
Electrical Engineering and Systems Science - Systems and Control
Abstract

We demonstrate the potential role of one of the largest at scale multi-vector Smart Energy Network Demonstrator (SEND).

Published
2022

3. Multi-Agent Deep Deterministic Policy Gradient Algorithm for Peer-to-Peer Energy Trading Considering Distribution Network Constraints

Author

Samende, Cephas, Cao, Jun, and Fan, Zhong

Subjects
Electrical Engineering and Systems Science - Systems and Control
Abstract

In this paper, we investigate an energy cost minimization problem for prosumers participating in peer-to-peer energy trading. Due to (i) uncertainties caused by renewable energy generation and consumption, (ii) difficulties in developing an accurate and efficient energy trading model, and (iii) the need to satisfy distribution network constraints, it is challenging for prosumers to obtain optimal energy trading decisions that minimize their individual energy costs. To address the challenge, we first formulate the above problem as a Markov decision process and propose a multi-agent deep deterministic policy gradient algorithm to learn optimal energy trading decisions. To satisfy the distribution network constraints, we propose distribution network tariffs which we incorporate in the algorithm as incentives to incentivize energy trading decisions that help to satisfy the constraints and penalize the decisions that violate them. The proposed algorithm is model-free and allows the agents to learn the optimal energy trading decisions without having prior information about other agents in the network. Simulation results based on real-world datasets show the effectiveness and robustness of the proposed algorithm., Comment: 15 pages, 19 figures

Published
2021

4. High-level control algorithms for maximising energy efficiency of solar nano-grids designed for energy access

Author

Samende, Cephas and McCulloch, Malcom

Subjects
Renewable energy sources, Electrical engineering
Abstract

Peer-to-peer interconnection of households having on-site batteries, four-port DC-DC converters and solar panels to form four-port DC-DC converter-enabled solar nano-grids is an emerging bottom-up approach for providing affordable energy access to rural areas. However, power losses which include battery charge and discharge losses, distribution losses and converter losses are one of the technical barriers hindering the practical deployment and operation of solar nano-grids in rural areas. Power losses reduce the energy efficiency of solar nano-grids. This research aimed to answer the following research question: What control algorithms can be developed to address the problem of maximising the energy efficiency of four-port DC-DC converter-enabled solar nano-grids that are designed for energy access? Solar nano-grids with star and hybrid distribution network configurations were considered in this research. Three novel high-level control algorithms were developed to answer the research question. The first one was a centralised control algorithm, the second one was a quasi-consensus based distributed control algorithm and the third one was a distributed state-of-charge based droop control algorithm. Numerical and simulation results carried out in Python showed the effectiveness of the developed control algorithms for addressing the research question through the considered solar nano-grid configurations. The first and second control algorithms addressed the research question for the star solar nano-grid configuration through optimisation. Firstly, a high fidelity steady-state model of the solar nano-grid was developed and a new two-stage convex power loss optimisation problem was formulated. The formulated optimisation problem did not require either linearisation or convex relaxation of power flow equations, making it scalable and computationally efficient. Then, the first and second control algorithms were developed to solve the formulated optimisation problem in a centralised and quasi-distributed manner respectively. The third algorithm addressed the research question for both the star and hybrid solar nano-grid configurations through balancing the state-of-charge of the batteries in a distributed manner. In this algorithm, household distribution voltages were adjusted in proportional to the state-of-charge of their local batteries, creating an automatic power flow between the households each time there was a slight change in the battery state-of-charge. Due to the automatic power flow between the households, the magnitude of current flow at every time instant in the solar nano-grid was low, thus, keeping the power losses to a minimum. The present work aimed to contribute towards the universal energy access agenda by focussing specifically on the third target of the United Nation's Sustainable Development Goal 7 - doubling the global rate of improvement in energy efficiency by 2030. There is a lot of work that still needs to be done to achieve this goal. Nonetheless, the present research has made a significant step towards improving energy efficiency by developing control algorithms that minimise the solar nano-grid power losses.

Published
2020

7. Battery and hydrogen energy storage control in a smart energy network with flexible energy demand using deep reinforcement learning

Author

Universitat Politècnica de Catalunya. Departament d'Enginyeria Elèctrica, Universitat Politècnica de Catalunya. SEER - Sistemes Elèctrics d'Energia Renovable, Samende, Cephas, Fan, Zhong, Cao, Jun, Espinoza, Renzo Fabián, Baltas, Gregory Nicholas, Rodríguez Cortés, Pedro, Universitat Politècnica de Catalunya. Departament d'Enginyeria Elèctrica, Universitat Politècnica de Catalunya. SEER - Sistemes Elèctrics d'Energia Renovable, Samende, Cephas, Fan, Zhong, Cao, Jun, Espinoza, Renzo Fabián, Baltas, Gregory Nicholas, and Rodríguez Cortés, Pedro

Abstract

Smart energy networks provide an effective means to accommodate high penetrations of variable renewable energy sources like solar and wind, which are key for the deep decarbonisation of energy production. However, given the variability of the renewables as well as the energy demand, it is imperative to develop effective control and energy storage schemes to manage the variable energy generation and achieve desired system economics and environmental goals. In this paper, we introduce a hybrid energy storage system composed of battery and hydrogen energy storage to handle the uncertainties related to electricity prices, renewable energy production, and consumption. We aim to improve renewable energy utilisation and minimise energy costs and carbon emissions while ensuring energy reliability and stability within the network. To achieve this, we propose a multi-agent deep deterministic policy gradient approach, which is a deep reinforcement learning-based control strategy to optimise the scheduling of the hybrid energy storage system and energy demand in real time. The proposed approach is model-free and does not require explicit knowledge and rigorous mathematical models of the smart energy network environment. Simulation results based on real-world data show that (i) integration and optimised operation of the hybrid energy storage system and energy demand reduce carbon emissions by 78.69%, improve cost savings by 23.5%, and improve renewable energy utilisation by over 13.2% compared to other baseline models; and (ii) the proposed algorithm outperforms the state-of-the-art self-learning algorithms like the deep-Q network., This work was supported by the Smart Energy Network Demonstrator project (grant ref. 32R16P00706) funded by ERDF and BEIS. This work is also supported by the EPSRC EnergyREV project (EP/S031863/1) and the Horizon Europe project i-STENTORE (101096787) and FNR CORE project LEAP (17042283). This research received no external funding., Peer Reviewed, Postprint (published version)

Published
2023

Catalog

Books, media, physical & digital resources
See catalog results