Towards a blockchain and machine learning-based framework for decentralised energy management

In this article, an agent-based transactive energy (TE) trading platform to integrate energy storage systems (ESSs) into the microgrids’ energy management system is proposed. Using this platform, two different types of energy storage market models are proposed to promote local-level (within the microgrid) and communal- or global-level ESSs’ participation in the intra- and intermicrogrid TE markets. Also, a reinforcement learning algorithm known as simulated-annealing-based $Q$ -learning is used to develop bidding strategies for ESSs to participate in the TE markets. Besides energy trading, the proposed system also accounts for the losses caused by energy transactions between ESSs and microgrids using a complex current-tracing-based loss allocation method. The overall efficacy of the proposed energy market management system is demonstrated using a modified IEEE 123-bus distribution system with multiple microgrids and ESSs. Based on simulation results, it is observed that the proposed model can effectively reinforce the balance between the supply and the demand in the microgrids using the mix of local and global ESSs.

Energy trading scheme based on consortium blockchain and game theory

Deep reinforcement learning for energy trading and load scheduling in residential peer-to-peer energy trading market

Given the ongoing transition towards a more decentralised and adaptive energy system, the potential of blockchain-enabled smart contracts for the energy sector is being increasingly recognised. Due to their self-executing, customisable and tamper-proof nature, they are seen as a key technology for enabling the transition to a more efficient, transparent and transactive energy market. The applications of smart contracts include coordination of smart electric vehicle charging, automated demand-side response, peer-to-peer energy trading and allocation of the control duties amongst the network operators. Nevertheless, their use in the energy sector is still in its early stages as there are many open challenges related to security, privacy, scalability and billing. In this paper, we systematically review 178 peer-reviewed publications and 13 innovation projects, providing a thorough analysis of the strengths and weaknesses of smart contracts used in the energy sector. This work offers a broad perspective on the opportunities and challenges that stakeholders using this technology face, in both current and emergent markets, such as peer-to-peer energy trading platforms. To provide a roadmap for researchers and practitioners interested in the technology, we propose a systematic model of the smart contracting process, by developing a novel 6-layer architecture, as well as presenting a sample energy contract in pseudocode form and as open-source code. Our analysis focuses on the two mainstream application areas we identify for smart contract use in this area: energy and flexibility trading, and distributed control. The paper concludes with a comprehensive, critical discussion of the advantages and challenges that must be addressed in the area of smart contracts and blockchains in energy, and a set of recommendations that researchers and developers should consider when applying smart contracts to energy system settings.

SummaryWith the advent and popularity of electric vehicles (EVs), the intelligent transportation system has adopted them as an alternative to fossil fuel or gasoline vehicles owing to their benefits of reduced greenhouse gas emissions. However, it becomes critical to schedule the vast EVs at the charging station (CS) efficiently while maintaining security, privacy, and optimality during the energy trading. Therefore, we propose a blockchain and zero‐sum game theory‐based energy trading scheme, that is, DEVS, for optimal and secure EV charging at the CS. We incorporate the Interplanetary File System with the blockchain to ameliorate the cost‐efficiency and reliability of EV energy trading. Furthermore, we implement the zero‐sum game theory between players EV and CS to yield an optimal payoff based on pure and mixed strategies during the energy trading procedure. Moreover, we deploy and execute the smart contract (SC) of the blockchain‐based proposed DEVS scheme in the Remix integrated development environment to secure EV energy trading transactions. Additionally, the security of the proposed DEVS scheme is checked and analyzed using a fuzzing‐based Echidna tool for protected energy trading. Finally, the performance evaluation of the proposed DEVS scheme is analyzed using various standard metrics such as profit comparison based on strategies, energy price comparison, CS profit comparison for pure strategy (based on arrival time), convergence comparison, and profit (EV and CS) at saddle point and mixed strategy to avail preserved and optimal energy trading for EVs.

Peer-to-peer trading in energy networks is expected to be exclusively conducted by the prosumers of the network with negligible influence from the grid. This raises the critical question: how can enough prosumers be encouraged to participate in peer-to-peer trading so as to make its operation sustainable and beneficial to the overall electricity network? To this end, this paper proposes how a motivational psychology framework can be used effectively to design peer-to-peer energy trading to increase user participation. To do so, first, the state-of-the-art of peer-to-peer energy trading literature is discussed by following a systematic classification, and gaps in existing studies are identified. Second, a motivation psychology framework is introduced, which consists of a number of motivational models that a prosumer needs to satisfy before being convinced to participate in energy trading. Third, a game-theoretic peer-to-peer energy trading scheme is developed, its relevant properties are studied, and it is shown that the coalition among different prosumers is a stable coalition. Fourth, through numerical case studies, it is shown that the proposed model can reduce carbon emissions by 18.38% and 9.82% in a single day in Summer and Winter respectively compared to a feed-in-tariff scheme. The proposed scheme is also shown to reduce the cost of energy up to 118 ¢ and 87 ¢ per day in Summer and Winter respectively. Finally, how the outcomes of the scheme satisfy all the motivational psychology models is discussed, which subsequently shows its potential to attract users to participate in energy trading.

Currently, solar power generation has significantly increased in the electricity energy markets. The cost of Solar PV panels has continually declined. More consumers turn into prosumers. Many countries have energy trading policies and are developing energy trading infrastructure, especially electricity trading, which can be traded directly between two parties (peer-to-peer). Understanding the electricity market and trading behaviors is the key to make peer-to-peer electricity trading feasible. This paper presents a simulation framework for peer-to-peer electricity trading and price determination mechanism. The simulation has three main steps, including biding quantity and price, matching, and settlement. The Monte Carlo model was applied to determine trading quantity and price in the first step. The price matching and settlement in the second and third steps are based on the double auction method. The simulation yields daily trading quantity and equilibrium price. The proposed framework provides insight and understanding in peer-to-peer energy trading in various scenarios.

In a transactive energy (TE) framework, prosumers can participate in peer-to-peer (P2P) energy trading with neighbors. TE also allows prosumers to participate in grid services by trading their excess energy or energy consumption flexibility with the grid operators, energy suppliers, and third-party energy companies (e.g., Aggregators). This paper presents a novel bidding strategy for small-scale residential prosumers for energy trading in the day-ahead TE market using the flexibilities of residential battery energy storage systems to maximize the profit from energy trading. The bidding model is formulated as a bi-level optimization problem that determines energy trading bids to maximize profits for the prosumer in the upper level, while the lower-level problem schedules the operation of residential storage units with respect to minimum storage degradation and optimum user comfort. A comprehensive storage model is developed that incorporates the operational constraints and the degradation of storage units when they undergo frequent charge-discharge cycles for the energy trading. The proposed bidding model is evaluated via a case study for a typical Australian prosumer and results indicate the efficacy of the proposed model in terms of profit maximization for the prosumer while satisfying user preferences and constraints related to the operation of the storage units.

This paper investigates a fully decentralized model for electricity trading within a transactive energy market. The proposed model presents a peer-to-peer (P2P) trading framework between the clients. The model is incorporated for industrial, commercial, and residential energy hubs to serve their associated demands in a least-cost paradigm. The alternating direction method of multipliers (ADMM) is implemented to address the decentralized power flow in this study. The optimal operation of the energy hubs is modeled as a standard mixed-integer linear programming (MILP) optimization problem. The corresponding decision variables of the energy hubs operation are transferred to the peer-to-peer (P2P) market, and ADMM is applied to ensure the minimum data exchange and address the data privacy issue. Two different scenarios have been studied in this paper to show the effectiveness of the electricity trading model between peers, called integrated and coordinated operation modes. In the integration mode, there is no P2P energy trading while in the coordinated framework, the P2P transactive energy market is taken into account. The proposed model is simulated on the modified IEEE 33-bus distribution network. The obtained results confirm that the coordinated model can efficiently handle the P2P transactive energy trading for different energy hubs, addressing the minimum data exchange issue, and achieving the least-cost operation of the energy hubs in the system. The obtained results show that the total operating cost of the hubs in the coordinated model is lower than that of the integrated model by $590.319, i.e. 11.75 % saving in the costs. In this regard, the contributions of the industrial, commercial, and residential hubs in the total cost using the integrated model are $3441.895, $596.600, and $988.789, respectively. On the other hand, these energy hubs contribute to the total operating cost in the coordinated model by $2932.645, $590.155, and $914.165 respectively. The highest decrease relates to the industrial hub by 14.8 % while the smallest decrease relates to the residential hub by 1 %. Furthermore, the load demand in the integrated and coordinated models is mitigated by 13 % and 17 %, respectively. These results indicate that the presented framework could effectively and significantly reduce the total load demand which in turn leads to reducing the total cost and power losses.

This research addresses a demand side management (DSM) system coordinated with Peer-to-Peer (P2P) energy trading among the households in the smart grid. It considers the components which have significant impact on cost optimization, e.g., storage, renewables, and microgrid. The model utilizes load and source scheduling, and energy trading strategies for cost optimization. It also addresses the inconvenience created to the users by delaying certain tasks. The contributions of the research are threefold. First, to our knowledge, this is the first optimal model which integrates DSM with P2P energy trading. The solutions of the proposed model determine optimal microgrid energy and price for P2P trading, which was not considered previously. Second, P2P energy trading in the microgrid potentially results in an unfair cost distribution among the participating households. We address this unfair cost distribution problem by employing Pareto optimality, ensuring that no households will be worse off to improve the cost of others. Third, our proposed trading strategy considers total cost optimization in a microgrid. The model utilizes all available energy to minimize energy cost. Therefore, there is a very low risk of energy waste, which is typically neglected in other energy trading strategies.

Design and implementation of an open-Source IoT and blockchain-based peer-to-peer energy trading platform using ESP32-S2, Node-Red and, MQTT protocol

Chapter 4 - The role of peer-to-peer energy trading strategy in future modern energy networks

A decentralized peer-to-peer energy trading strategy considering flexible resource involvement and renewable energy uncertainty

Recent research highlights the potential of consumption-based feedback for water conservation, emphasizing the need for Non Intrusive Water Monitoring (NIWM). However, existing NIWM studies often rely on small datasets, a pre-selected class of models, and inaccessible software. Here, we introduce PyNIWM, a machine learning-based open-source Python framework for NIWM. PyNIWM enables water end-use classification via (i) data characterization and feature engineering, (ii) water end-use event classification with four machine learning classifiers, and (iii) performance assessment. We demonstrate PyNIWM on a real-world dataset containing around 800,000 labeled end-use events from 762 homes across the USA and Canada. The four PyNIWM classifiers achieve F1 scores above 0.85, indicating high suitability for water end-use classification. However, a tradeoff between accuracy and computational cost exists. Finally, data balancing through oversampling enhances classification of low-represented end-use classes, but does not improve overall classification. We release PyNIWM as an open-source software, aiming for collaborative and reproducible research.

An energy trading system is essential for the successful integration of Electric Vehicles (EVs) into the smart grid. In this paper, leveraging blockchain technology, we first propose a privacy-preserving charging-station-to-vehicle (CS2V) energy trading scheme. The CS2V scheme is useful in crowded cities where there is a need for a charging infrastructure that can charge many EVs daily. We also propose a privacy-preserving vehicle-to-vehicle (V2V) energy trading scheme. The V2V scheme is useful when charging stations are not available or far and cheaper prices can be offered from EVs, e.g., if they charge from renewable energy sources. In the V2V scheme, the privacy of both charging and discharging EVs including location, time, and amount of power are preserved. To preserve privacy in both schemes, EVs are anonymous, however, a malicious EV may abuse the anonymity to launch Sybil attacks by pretending as multiple non-exiting EVs to launch powerful attacks such as Denial of Service (DoS) by submitting multiple reservations/offers without committing to them, to prevent other EVs from charging and make the trading system unreliable. To thwart the Sybil attacks, we use a common prefix linkable anonymous authentication scheme, so that if an EV submits multiple reservations/offers at the same timeslot, the blockchain can identify such submissions. To further protect the privacy of EV drivers, we introduce an anonymous and efficient blockchain-based payment system that cannot link individual drivers to specific charging locations. Our experimental results indicate that our schemes are secure and privacy-preserving with low communication and computation overheads.