Grid Trading Research Articles

LM jump detection-high frequency grid trading model based on LSTM prediction

In the computer era, high frequency trading is one of the hottest topics in the financial investment market. In order to develop a high-frequency trading strategy model with specific validity for different types of stocks, this paper proposes a LM jump detection-grid trading model based on LSTM prediction to construct a trading strategy for three types of stocks: blue chips, volatile stocks and stable stocks. The proposed model is a combination of a black-box model and a white-box model, which not only has the powerful learning capability of LSTM Model and but also the excellent scalability of LM Jump Detection Model and Grid Trading Model. These allow the model to have greater advantages in terms of trading strategies and the convenience of optimizing anomaly detection.

ANN and SSO Algorithms for a Newly Developed Flexible Grid Trading Model

In the modern era, the trading methods and strategies used in the financial market have gradually changed from traditional on-site trading to electronic remote trading, and even online automatic trading performed by pre-programmed computer programs. This is due to the conduct of trading automatically and self-adjustment in financial markets becoming a competitive development trend in the entire financial market, with the continuous development of network and computer computing technology. Quantitative trading aims to automatically form a fixed and quantifiable operational logic from people’s investment decisions and apply it to the financial market, which has attracted the attention of the financial market. The development of self-adjustment programming algorithms for automatically trading in financial markets has transformed to being a top priority for academic research and financial practice. Thus, a new flexible grid trading model incorporating the Simplified Swarm Optimization (SSO) algorithm for optimizing parameters for various market situations as input values and the Fully Connected Neural Network (FNN) and Long Short-Term Memory (LSTM) model for training a quantitative trading model for automatically calculating and adjusting the optimal trading parameters for trading after inputting the existing market situation are developed and studied in this work. The proposed model provides a self-adjust model to reduce investors’ effort in the trading market, obtains outperformed Return of Investment (ROI) and model robustness, and can properly control the balance between risk and return.

Effects of Environmental and Electrical Factors on Metering Error and Consistency of Smart Electricity Meters

The smart electricity meter (SEM) is an important part of smart power grid, and the accuracy of SEMs is the basis for power grid operation control and trade settlement between power supply and electricity consumption, but the evolution behaviors of metering error of SEMs under field operation conditions have not yet been identified. The SEMs were installed and operated on site, metering error data were collected under various temperature and current conditions. The influences of current, power coefficient, and temperature on metering error and consistency were analyzed separately with the help of quadratic polynomials, and then an integrated model elaborating the joint effects of multi-stress was developed based on a binary quadratic polynomial. We find that a lower temperature and a larger current result in a higher metering error of SEMs; however, the effects of current on metering error are determined by power coefficients. The results have reference value for remote metrological verification, error monitoring, and the optimization of the operation and maintenance scheme of SEMs.

Enabling Trustworthiness in Sustainable Energy Infrastructure Through Blockchain and AI-Assisted Solutions

Network trustworthiness is a critical component of network security, as it builds on positive inter-actions, guarantees, transparency, and accountability. And with the growth of smart city services and applications, trustworthiness is becoming more important. Most current network trustworthiness solutions are insufficient, particularly for critical infrastructures where end devices are vulnerable and easily hacked. In terms of the energy sector, blockchain technology transforms all currencies into digital modes, thereby allowing one person to manage and exchange energy with others. This has drawn the attention of experts in many fields as a safe, low-cost platform to track billions of transactions in a distributed energy economy. Security and trust issues are still relatively new in the current centralized energy management scheme. With blockchain technology, a decentralized energy infrastructure enables parties to establish micro- grid trading energy transactions and apply artificial intelligence (AI). Using AI in energy systems enables machines to learn various parameters, such as predicted required amounts, excess amounts, and trusted partners. In this article, we envision a cooperative and distributed framework based on cutting-edge computing, communication, and intelligence capabilities such as AI and blockchain in the energy sector to enable secure energy trading, remote monitoring, and trustworthiness. The proposed framework can also enable secure energy trading at the edge devices and among multiple devices. There are also discussions on difficulties, issues, and design principles, as well as spotlights on some of the more popular solutions.

Self-restrained energy grid with data analysis and blockchain techniques

ABSTRACT Efficient energy distribution and utilization play a significant role in the energy grid, especially with renewable sources. The existing grid system has problems in resource utilization, data privacy, wireless communication, and dynamic demand handling. An energy grid is proposed based on IoT, blockchain, and machine learning techniques to solve the problems. The proposed energy grid architecture controls energy flow according to the demand, predicts expected load, analyzes consumer behavior, and enables the users in the grid trade energy in peer to peer manner. Energy flow in storage modules controlled with high voltage relays, and it automates the charging and discharging of respective battery pools in the grid. Energy consumption and battery status in the grid uploaded to the distributed file system. The data clustering model deployed in the server analyses those data and divides the consumers into three groups according to the consumer’s consumption behavior: high, moderate, and low consumption. The Time series analysis model deployed to forecast the load and predict peak hours. The codes deployed as a smart contract in an Ethereum blockchain platform. Machine learning algorithms are deployed for forecasting and clustering. In forecasting, the average error rate is 37% less than other generally used algorithms, and in the clustering algorithm, the accuracy increases as the dataset increases, which is 30% more than other cluster models. The controlled energy storage model in this grid provides up to 500–600 extra charge cycles for batteries than other traditional methods. The distributed IPFS storage provides data security, and smart contracts support grid operational security and data privacy. The data analyzation module of the grid helps effective resource utilization.

Gambler’s ruin problem and bi-directional grid constrained trading and investment strategies

Bi-Directional Grid Constrained (BGC) trading strategies have never been studied academically until now, are relatively new in the world of financial markets and have the ability to out-perform many other trading algorithms in the short term but will almost surely ruin an investment account in the long term. Whilst the Gambler’s Ruin Problem (GRP) is based on martingales and the established probability theory proves that the GRP is a doomed strategy, this research details how the semimartingale framework is required to solve the grid trading problem (GTP), i.e. a form of BGC financial markets strategies, and how it can deliver greater return on investment (ROI) for the same level of risk. A novel theorem of GTP is derived, proving that grid trading, whilst still subject to the risk of ruin, has the ability to generate significantly more profitable returns in the short term. This is also supported by extensive simulation and distributional analysis. These results not only can be studied within mathematics and statistics in their own right, but also have applications into finance such as multivariate dynamic hedging, investment funds, trading, portfolio risk optimization and algorithmic loss recovery. In today’s uncertain and volatile times, investment returns are between 2%-5% per annum, barely keeping up with inflation, putting people’s retirement at risk. BGC and GTP are thus a rich source of innovation potential for improved trading and investing. Acknowledgement(s)Aldo Taranto was supported by an Australian Government Research Training Program (RTP) Scholarship. The authors would like to thank A/Prof. Ravinesh C. Deo and A/Prof. Ron Addie of the University of Southern Queensland for their invaluable advice on refining this paper.

Bi-directional grid absorption barrier constrained stochastic processes with applications in finance & investment

Whilst the gambler’s ruin problem (GRP) is based on martingales and the established probability theory proves that the GRP is a doomed strategy, this research details how the semimartingale framework is required for the grid trading problem (GTP) of financial markets, especially foreign exchange (FX) markets. As banks and financial institutions have the requirement to hedge their FX exposure, the GTP can help provide a framework for greater automation of the hedging process and help forecast which hedge scenarios to avoid. Two theorems are adapted from GRP to GTP and prove that grid trading, whilst still subject to the risk of ruin, has the ability to generate significantly more profitable returns in the short term. This is also supported by extensive simulation and distributional analysis. We introduce two absorption barriers, one at zero balance (ruin) and one at a specified profit target. This extends the traditional GRP and the GTP further by deriving both the probability of ruin and the expected number of steps (of reaching a barrier) to better demonstrate that GTP takes longer to reach ruin than GRP. These statistical results have applications into finance such as multivariate dynamic hedging (Noorian, Flower, & Leong, 2016), portfolio risk optimization, and algorithmic loss recovery.

Deep LSTM with Reinforcement Learning Layer for Financial Trend Prediction in FX High Frequency Trading Systems

High-frequency trading is a method of intervention on the financial markets that uses sophisticated software tools, and sometimes also hardware, with which to implement high-frequency negotiations, guided by mathematical algorithms, that act on markets for shares, options, bonds, derivative instruments, commodities, and so on. HFT strategies have reached considerable volumes of commercial traffic, so much so that it is estimated that they are responsible for most of the transaction traffic of some stock exchanges, with percentages that, in some cases, exceed 70% of the total. One of the main issues of the HFT systems is the prediction of the medium-short term trend. For this reason, many algorithms have been proposed in literature. The author proposes in this work the use of an algorithm based both on supervised Deep Learning and on a Reinforcement Learning algorithm for forecasting the short-term trend in the currency FOREX (FOReign EXchange) market to maximize the return on investment in an HFT algorithm. With an average accuracy of about 85%, the proposed algorithm is able to predict the medium-short term trend of a currency cross based on the historical trend of this and by means of correlation data with other currency crosses using techniques known in the financial field with the term arbitrage. The final part of the proposed pipeline includes a grid trading engine which, based on the aforementioned trend predictions, will perform high frequency operations in order to maximize profit and minimize drawdown. The trading system has been validated over several financial years and on the EUR/USD cross confirming the high performance in terms of Return of Investment (98.23%) in addition to a reduced drawdown (15.97 %) which confirms its financial sustainability.

Grid Trading System Robot (GTSbot): A Novel Mathematical Algorithm for Trading FX Market

Grid algorithmic trading has become quite popular among traders because it shows several advantages with respect to similar approaches. Basically, a grid trading strategy is a method that seeks to make profit on the market movements of the underlying financial instrument by positioning buy and sell orders properly time-spaced (grid distance). The main advantage of the grid trading strategy is the financial sustainability of the algorithm because it provides a robust way to mediate losses in financial transactions even though this also means very complicated trades management algorithm. For these reasons, grid trading is certainly one of the best approaches to be used in high frequency trading (HFT) strategies. Due to the high level of unpredictability of the financial markets, many investment funds and institutional traders are opting for the HFT (high frequency trading) systems, which allow them to obtain high performance due to the large number of financial transactions executed in the short-term timeframe. The combination of HFT strategies with the use of machine learning methods for the financial time series forecast, has significantly improved the capability and overall performance of the modern automated trading systems. Taking this into account, the authors propose an automatic HFT grid trading system that operates in the FOREX (foreign exchange) market. The performance of the proposed algorithm together with the reduced drawdown confirmed the effectiveness and robustness of the proposed approach.

Load balancing in decentralized smart grid trade system using blockchain

Load balancing in decentralized smart grid trade system using blockchain

Performance enhancement of online energy scheduling in a radial utility distribution microgrid

In this paper, an optimal power dispatch formulation is proposed in the operating horizon using real time measurements to enhance the performance of online energy scheduling in microgrid considering renewable energy, grid power trade and demand response. A stochastic weight tradeoff particle swarm optimization (SWT-PSO) based backward–forward sweep (BFS) optimal power flow (OPF) method is used by the microgrid central controller (MGCC) to obtain the online optimal schedules of distributed energy resources (DERs). The effectiveness of the suggested approach is investigated on the residential feeder of the CIGRE LV benchmark microgrid in terms of reduction in fuel & emission costs and voltage deviation. In addition, settling time in overall implementation is drastically reduced. Also, the paper analytically justifies the use of (1) renewable energy sources, grid trade and prioritized load curtailment, (2) SWT-PSO over priority listing method and (3) online OPF over online economic dispatch (ED).

Demand response governed swarm intelligent grid scheduling framework for social welfare

Abstract Peak load defines the generation, transmission and distribution capacity of interconnected power network. As load changes throughout the day and the year, electricity systems must be able to deliver the maximum load at all times, which will be hard trade for a practical power network. Smart grid technologies show strong potential to optimize asset utilization by shifting peak load to off peak times, thereby decoupling the electricity growth from peak load growth. Under Smart grid trade regulation, with continuous varying demand pattern, electricity price will be uneven as well. On this view point, in order to obtain a flatten demand, without affecting the welfare of the market participants, this paper presents an on-going effort to develop Demand Response (DR) governed swarm intelligence based stochastic peak load modeling methodology capable of restoring the market equilibrium during price and demand oscillations of the real-time smart power networks. This proposed DR based methodology allows generators and loads to interact in an automated fashion in real time, coordinating demand to flatten spikes and thereby minimizing erratic variations of price of electricity. For proper utilization of DR connectivity, a Curtailment Limiting Index (CLI) has been formulated, monitoring which in real time, for each of the Load Dispatch Centers (LDCs), the system operator can shape the electricity demand according to the available capacity of generation, transmission and distribution assets. The proposed methodology can also be highlighted for generating the most economical schedule for social welfare with standard operational status in terms of voltage profile, system loss and optimal load curtailment. The case study has been carried out in IEEE 30 bus scenario as well as on a practical 203 bus-265 line power network (Indian Eastern Grid) with both generator characteristics and price responsive demand characteristics or DR as inputs and illustrious Particle Swarm Optimization (PSO) technique has assisted the fusion of the proposed model and methodology. Encouraging simulation results suggest that, the effective deployment of this methodology may lead to an operating condition where an overall benefit of all the power market participants with standard operational status can be ensured and the misuse of electricity will be minimized.

Stochastic Effects of Renewable Energy and Loads on Optimizing Microgrid Market Benefits

Abstract This paper investigates the effects of uncertain renewable energy and loads on optimizing profit and cost in a microgrid power market. The optimal power scheduling problem is solved using interval arithmetic backward forward sweep (IA-BFS) and particle swarm optimization with time varying acceleration coefficients (PSO-TVAC) based optimal power flow (OPF). The effectiveness of the problem and the method is verified by studying the deviations in dispatch of conventional sources, operational cost and overall profit in residential feeder of the CIGRE LV benchmark microgrid with load curtailment, grid trade and wind, solar & conventional energy sources.

Static strategy and dynamic adjustment: An effective method for Grid task scheduling

Task scheduling is the key technology in Grid computing. Hierarchical organization is suitable for the computational Grid because of the dynamic, heterogeneous and autonomous nature of the Grid. Although a number of Grid systems adopt this organization, few of them has dealt with task scheduling for the hierarchical architecture. In this paper, we present an effective method, fully taking into account both historical Grid trade data and dynamic variation of the Grid market to improve the task scheduling for a hierarchical Grid market. The main idea of the proposed method is a combination of an off-line static strategy using time series prediction and an on-line dynamic adjustment using reinforcement learning. The superiority of this new scheduling algorithm, in improving the inquiry efficiency for resource consumers, getting better load balancing of the whole hierarchical Grid market, and achieving higher success rate of the Grid service request, is demonstrated by simulation experiments.

Competition in transmission: it's coming sooner or later

Properly structured grid trading under a competitive model will enable generation and transmission to serve as substitutes for one another. Without such an approach, we are likely to see only a muted market for power. The crucible of California's reform effort has already engaged players on both sides of the issues.

Completion of the Grid in Great Britain

THE fifth annual report of the Central Electricity Board, which has just been published, is of special interest as it is the last of the reports marking the construction of the grid in Great Britain. It has only taken six years to complete instead of the estimated eight years. The cost is less than 27 million pounds and is within 2½ per cent of the original estimate of the Electricity Commissioners, a very satisfactory result considering the work has been so accelerated. In future, the main business of the Central Board will in connexion with grid trading. The main function of the grid is to see that there is an abundant supply of electrical energy at each central station so that the engineers will have more time to devote to the increase of their sales. The report shows that continuous expansion is taking place in outlying areas supplied by secondary transmission lines. The Weir Committee thought that it would be best that most of the secondary transmission should be carried out by the distributing authorities, but the Central Board found it best to regard these lines as part of the grid and so help the distributors. Successful researches have been made on methods of cheapening the cost of tapping the grid. This is a step towards supplying sparsely populated districts with electric light and power and thus encourages rural development. Instead of a tapping costing £20,000, it is hoped to reduce it to £4,000. It was feared at one time that difficulty would be obtained in getting wayleaves, but out of twenty-one thousand wayleaves obtained, less than six hundred (2.83 per cent) had to be acquired compulsorily.