M Vaidehi, Alivia Pandit, Bhaskar Jindal, Minu Kumari · 5 authors
After the boom and bust in cryptocurrencies’ prices in recent years, Bitcoin has been totally regarded as an investment asset. As it is highly volatile in nature, there has been a need for good predictions for carrying base investment decisions. Although current study has used machine learning for more accurate Bitcoin price prediction, some of them did focused on the feasibility of applying different modeling techniques to the samples that has different data structures and dimension features. To predict Bitcoin price on different frequencies after using machine learning techniques, firstly we have to classify the Bitcoin price with daily price and high-frequency price. Here, we attempt to predict Bitcoin price as accurately as possible by taking into consideration various protocols that affect the Bitcoin value. Using the provided data we would predict the sign of daily price change with highest possible accuracy. We have used Random Forest Classifier and compared with benchmark results as daily price prediction, we achieve a better performance, with the highest accuracies of the statistical methods and machine learning algorithms of 99%. my investigation in Bitcoin price prediction can be considered as a pilot study for the importance of the sample dimension in the machine learning techniques. Keywords Bitcoin, Crypto Currency, Machine Learning, Blockchain, Long Short Term Memory(LSTM), Recurrent Neural Network(RNN), Prediction
In a Smart Grid environment the performance measure of the grid is calculated by considering the fact that how accurately and precisely a load forecasting (LF) is done. A true Load Forecasting is vital to make a current grid smarter and more reliable when it comes to its performance. Demand Response (DR) contracts is a type of program in smart grid where the customer is free to select a type of contract which is given by the utility and is one of the growing factor which affects the load forecasting results in the Smart Grid, therefore in order to do a complete evaluation of smart grid performance and to accomplish an accurate load forecasting results the different types of contracts should also be studied. The purpose of this study is to accomplish two goals. The first one is to develop a suitable model which can incorporate various factors that can affect the load forecasting results. The subsequent goal is to identify the impact of the demand response contracts on the load forecasting results. In the proposed study, Support Vector Machine-Regression (SVR) is selected as the base methodology to perform a Short — Term Load Forecasting (STLF) under smart grid environment.
Short-term load forecasting (STLF) models are very important for electric industry in the trade of energy. These models have many applications in the day-to-day operations of electric utilities such as energy generation planning, load switching, energy purchasing, infrastructure maintenance, and contract evaluation. A large variety of STLF models have been developed that trade off between forecast accuracy and convergence rate. This paper presents an accurate and fast converging STLF model for industrial applications in a smart grid. In order to improve the forecast accuracy, modifications are devised in two popular techniques: mutual information based feature selection; and enhanced differential evolution algorithm based error minimization. On the other hand, the convergence rate of the overall forecast strategy is enhanced by devising modifications in the heuristic algorithm and in the training process of the artificial neural network. Simulation results show that accuracy of the newly proposed forecast model is 99.5% with moderate execution time, i.e., we have decreased the average execution of the existing bilevel forecast strategy by 52.38%.
In the smart grid, large consumers can procure electricity energy from various power sources to meet their load demands. To maximize its profit, each large consumer needs to decide their energy procurement strategy under risks such as price fluctuations from the spot market and power quality issues. In this paper, an electric energy procurement decision-making model is studied for large consumers who can obtain their electric energy from the spot market, generation companies under bilateral contracts, the options market and self-production facilities in the smart grid. Considering the effect of unqualified electric energy, the profit model of large consumers is formulated. In order to measure the risks from the price fluctuations and power quality, the expected utility and entropy is employed. Consequently, the expected utility and entropy decision-making model is presented, which helps large consumers to minimize their expected profit of electricity procurement while properly limiting the volatility of this cost. Finally, a case study verifies the feasibility and effectiveness of the proposed model.
This paper proposes an efficient method for designing a contract model of the weather derivatives between energy utilities in Smart Grid. It is well-known that the weather conditions bring a profit decline or the increase of expenses to do damage to sound management. Weather derivatives are useful for solving such a problem. One of the ideas is to use the complementary relationship between electric power and gas companies in a sense that electric power companies are apt to make profits in hot summer while gas companies are inclined to reduce revenue. This paper focuses on how to create a reasonable contract model of the weather derivative. In this paper, EPSO (Evolutionary Particle Swarm Optimization) of meta-heuristics is applied to designing a contract model of the weather derivative. The proposed method aims at equalizing the mean and the variance of the payoffs between the power and gas companies. To enhance the model accuracy, DA clustering of global clustering is used to classify the historical data into clusters. The effectiveness of the proposed method is demonstrated for the real data in Tokyo, Japan.
Sérgio Ramos, João Duarte, João Soares, Zita Vale · 5 authors
The present research paper presents five different clustering methods to identify typical load profiles of medium voltage (MV) electricity consumers. These methods are intended to be used in a smart grid environment to extract useful knowledge about customer's behaviour. The obtained knowledge can be used to support a decision tool, not only for utilities but also for consumers. Load profiles can be used by the utilities to identify the aspects that cause system load peaks and enable the development of specific contracts with their customers. The framework presented throughout the paper consists in several steps, namely the pre-processing data phase, clustering algorithms application and the evaluation of the quality of the partition, which is supported by cluster validity indices. The process ends with the analysis of the discovered knowledge. To validate the proposed framework, a case study with a real database of 208 MV consumers is used.
Load forecasting is highly important for power system operation and planning. Demand response, as a valuable feature in smart grid, is growing dramatically as an effective demand management method. However, traditional load forecasting tools have limitations to reflect demand response customer behaviors into load predictions. The energy consumption by demand response customers is mostly guided by their signed contracts. Therefore, existing demand response contracts are reviewed in this study for both wholesale and retail markets. An illustrative example is provided to explore the impact of these contracts on load forecasting. A concept of proactive load forecasting considering contract types is then proposed and discussed for forecasting loads in a smart grid environment.