Electricity Price Forecasting for Cloud Computing Using an Enhanced Machine Learning Model

Geographically distributed data centens (GDCs) serving as infrastructures for cloud services, are growing in both number and scale. They usually consume enormous amount of electric power, which lead to high operational costs and this has been recognized as a main challenge in cloud computing. Energy cost can be reduced by directing the requests to the favor of data center with lower electricity price by incorporating spatially and temporally price diversity, especially in the multi-region electricity markets. If the electricity prices of data centers are predicted in advance, the cloud provider can reduce energy cost. An efficient electricity price prediction is needed for minimizing electricity bill of GDCs. This paper proposes electricity price prediction for GDCs in multi-region electricity markets. Experiment is conducted on real-life electricity price data sets with machine learning algorithms. By comparatively assessing the prediction accuracy of the models, the most accurate one is selected. Experiment results show that the prediction model can provide promising accuracy.

Electricity consumption of datacenters is increasing significantly with the growth in Information Technology sector. Electricity consumption of datacenters occupies approximately 2 % of total electricity consumption in the USA which makes IT Sector second most electricity-consuming sector. Cooling system in a traditional datacenter is responsible of 30-60% of final electricity consumption. In this study, a software is developed to estimate the final energy demand of a datacenter and electricity consumption of the datacenter for variable cooling systems by using Visual Studio C# interface and SQL server. Climate data, physical properties of the datacenter building and IT equipment situated in datacenter inputs are used in order to software to calculate annual energy demand of datacenter. Then electricity consumption of the datacenter is presented on monthly basis and electricity demand of datacenter for each cooling system is listed on annual basis. Developed software is validated by using power demand value, physical properties of datacenter building information and equipment list of an existing data center. Typical climate data insertion tool and economic analyses will be added to the software in order to be used worldwide. Therefore, this is an ongoing study.

In the open electricity market, accurate short-term electricity price prediction is crucial for market participants to formulate market strategies. This paper proposes an electricity price prediction method based on empirical mode decomposition and minimum gated memory network quantile regression. Empirical mode decomposition is used to decompose the electricity price sequence into several modal components, and the quantile regression (QR) and minimum gated memory network (MGM) combined with QR-MGM, a hybrid model, to predict each modal component under different quantiles, and use the kernel density estimation to obtain the probability density function of electricity price for the reconstructed prediction results. Taking the electricity price data of the American ERCOT power market as an example, it shows that the proposed combined forecasting method not only has higher accuracy of short-term electricity price prediction under the same training time, but also obtains a more reliable electricity price probability density function, which provides more effective information for market participants to formulate optimal market strategies.

Accurate electricity price prediction is key to the orderly operation of the electricity market. However, the uncertain, stochastic and fluctuant characteristics of electricity pricees make prediction difficult. With the aim of solving this issue, this investigation proposed a multi-stage intelligent model integrating the Beveridge–Nelson decomposition (B-N-D) model, the least square support vector machine (LSSVM), and a nature-inspired optimization model named the whale optimization algorithm (WOA). Firstly, the B-N-D model was utilized to decompose the hourly electricity price time series into determinacy component, periodic trend, and stochastic item. Secondly, the WOA–LSSVM model was proposed to forecast the future hourly data of three components respectively, of which the optimal parameters of LSSVM were determined by using WOA. Finally, the future hourly electricity price data were computed by multiplying the forecasted data of those terms. To verify the validity of the proposed electricity price prediction model in this paper, five comparison approaches based on the B-N-D approach were selected, which are auto-regressive integrated moving average (ARIMA), single LSSVM, LSSVM optimized by the fruit-fly optimization algorithm (FOA), LSSVM optimized by particle swarm optimization (PSO) models, and WOA–LSSVM without B-N-D. By comparatively analyzing the error criteria values of the above models through testing on the objective data of the Pennsylvania–New Jersey–Maryland (PJM) electricity market collected from 11 December 2017 to 18 December 2017, from 15 January 2018 to 22 January 2018, and from 1 February 2018 to 25 February 2018, we conclude that the constructed intelligent model in this paper can greatly enhance the prediction precision of electricity prices.

Deadline-constrained energy-aware workflow scheduling in geographically distributed cloud data centers

Energy savings in direct air-side free cooling data centers: A cross-system modeling and optimization framework

The participation of consumers and producers in demand response programs has increased in smart grids, which reduces investment and operation costs of power systems. Also, with the advent of renewable energy sources, the electricity market is becoming more complex and unpredictable. To effectively implement demand response programs, forecasting the future price of electricity is very crucial for producers in the electricity market. Electricity prices are very volatile and change under the influence of various factors such as temperature, wind speed, rainfall, intensity of commercial and daily activities, etc. Therefore, considering the influencing factors as dependent variables can increase the accuracy of the forecast. In this paper, a model for electricity price forecasting is presented based on Gated Recurrent Units. The electrical load consumption is considered as an input variable in this model. Noise in electricity price seriously reduces the efficiency and effectiveness of analysis. Therefore, an adaptive noise reducer is integrated into the model for noise reduction. The SAEs are then used to extract features from the de-noised electricity price. Finally, the de-noised features are fed into the GRU to train predictor. Results on real dataset shows that the proposed methodology can perform effectively in prediction of electricity price.

In the context of the clean and low-carbon transformation of power systems, addressing the challenge of day-ahead electricity market price prediction issues triggered by the strong stochastic volatility of power supply output due to high-penetration renewable energy integration, as well as problems such as limited dataset scales and short market cycles in test sets associated with existing electricity price prediction methods, this paper introduced an innovative prediction approach based on a multi-modal feature fusion and BiGRUSA-ResSE-KAN deep learning model. In the data preprocessing stage, maximum–minimum normalization techniques are employed to process raw electricity price data and exogenous variable data; the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and variational mode decomposition (VMD) methods are utilized for multi-modal decomposition of electricity price data to construct a multi-scale electricity price component matrix; and a sliding window mechanism is applied to segment time-series data, forming a three-dimensional input structure for the model. In the feature extraction and prediction stage, the BiGRUSA-ResSE-KAN multi-branch integrated network leverages the synergistic effects of gated recurrent units combined with residual structures and attention mechanisms to achieve deep feature fusion of multi-source heterogeneous data and model complex nonlinear relationships, while further exploring complex coupling patterns in electricity price fluctuations through the knowledge-adaptive network (KAN) module, ultimately outputting 24 h day-ahead electricity price predictions. Finally, verification experiments conducted using test sets spanning two years from five major electricity markets demonstrate that the introduced method effectively enhances the accuracy of day-ahead electricity price prediction, exhibits good applicability across different national electricity markets, and provides robust support for electricity market decision making.

Stochastic optimization can be used to generate optimal bidding strategies for virtual bidders in which the uncertain electricity prices are represented by using scenarios. This paper proposes a hybrid scenario generation method for electricity price using a seasonal autoregressive integrated moving average (SARIMA) model and historical data. The electricity price spikes are first identified by using an outlier detection method. Then, the historical data are decomposed into base and spike components. Next, the base and spike component scenarios are generated by using the SARIMA- and historical data-based methods, respectively. Finally, the electricity price scenarios are obtained by combining the base and spike component scenarios. Case studies are carried out for a virtual bidder in the PJM electricity market to validate the proposed method. The optimal bidding strategies of the virtual bidder are generated by solving a stochastic optimization problem using the electricity price scenarios generated by the proposed method, the SARIMA method, and a historical data-based method, respectively. Case study results show that the proposed method is better than the SARIMA method in preserving statistical properties of the electricity price in the generated scenarios and is better than the historical data-based method in predicting the future trend of the electricity price and, therefore, can help the virtual bidder earn more profit in the electricity market.

Day-ahead electricity price prediction applying hybrid models of LSTM-based deep learning methods and feature selection algorithms under consideration of market coupling

With the increasing popularity of Cloud computing and Mobile computing, individuals, enterprises and research centers have started outsourcing their IT and computational needs to on-demand cloud services. Recently geographical load balancing techniques have been suggested for data centers hosting cloud computation in order to reduce energy cost by exploiting the electricity price differences across regions. However, these algorithms do not draw distinction among diverse requirements for responsiveness across various workloads. In this paper, we use the flexibility from the Service Level Agreements (SLAs) to differentiate among workloads under bounded latency requirements and propose a novel approach for cost savings for geographical load balancing. We investigate how much workload to be executed in each data center and how much workload to be delayed and migrated to other data centers for energy saving while meeting deadlines. We present an offline formulation for geographical load balancing problem with dynamic deferral and give online algorithms to determine the assignment of workload to the data centers and the migration of workload between data centers in order to adapt with dynamic electricity price changes. We compare our algorithms with the greedy approach and show that significant cost savings can be achieved by migration of workload and dynamic deferral with future electricity price prediction. We validate our algorithms on MapReduce traces and show that geographic load balancing with dynamic deferral can provide 20-30% cost-savings.

More and more cloud computing services are handled by different Internet operators in distributed Internet data centers (IDCs), which incurs massive electricity costs. Today, the power usage of data centers contributes to more than 1.5% market share of electricity consumption across the United States. Minimization of these costs benefits cloud computing operators, and attracts increasing attentions from many research groups and industrial sectors. Along with the deployment of smart grid, the electrical real-time pricing policy promotes power consumers to adaptively schedule their electricity utilization for lower operational costs. This paper proposes a novel approach to enable electrical energy buffering in batteries to predictively minimize IDC electricity costs in smart grid. Batteries are charged when electricity price is low and discharged to power servers when electricity price is high. A power management controller is used per battery to arbitrate the charging and discharging actions of the battery. The controller is designed as a MPC-based (model predictive control) controller. To this end, an MPC power minimization problem is formulated based on a discrete state-space model with states of battery power level and cost. Extensive simulation results demonstrate the effectiveness of our approach based on real-life electricity prices in smart grid.

In recent decades, the traditional monopolistic energy exchange market has been replaced by deregulated, competitive marketplaces in which electricity may be purchased and sold at market prices like any other commodity. As a result, the deregulation of the electricity industry has produced a demand for wholesale organized marketplaces. Price predictions, which are primarily meant to establish the market clearing price, have become a significant factor to an energy company’s decision making and strategic development. Recently, the fast development of deep learning algorithms, as well as the deployment of front-end metaheuristic optimization approaches, have resulted in the efficient development of enhanced prediction models that are used for electricity price forecasting. In this paper, the development of six highly accurate, robust and optimized data-driven forecasting models in conjunction with an optimized Variational Mode Decomposition method and the K-Means clustering algorithm for short-term electricity price forecasting is proposed. In this work, we also establish an Inverted and Discrete Particle Swarm Optimization approach that is implemented for the optimization of the Variational Mode Decomposition method. The prediction of the day-ahead electricity prices is based on historical weather and price data of the deregulated Greek electricity market. The resulting forecasting outcomes are thoroughly compared in order to address which of the two proposed divide-and-conquer preprocessing approaches results in more accuracy concerning the issue of short-term electricity price forecasting. Finally, the proposed technique that produces the smallest error in the electricity price forecasting is based on Variational Mode Decomposition, which is optimized through the proposed variation of Particle Swarm Optimization, with a mean absolute percentage error value of 6.15%.

During periods of market stress, electricity prices can rise dramatically. This paper treats these abnormal episodes or price spikes as count events and attempts to build a model of the spiking process. By contrast to the existing literature, which either ignores temporal dependence in the spiking process or attempts to model the dependence solely in terms of deterministic variables (like seasonal and day of the week effects), this paper argues that persistence in the spiking process is an important factor in building an effective model. A Poisson autoregressive framework is proposed in which price spikes occur as a result of the latent arrival and survival of system stresses. This formulation captures the salient features of the process adequately, and yields forecasts of price spikes that are superior to those obtained from naïve models that do not account for persistence in the spiking process.

With the development of the national economy and the change of policies, the development of the electric power industry continues to expand. The New Electricity Reform proposes that electricity price is the core of electricity reform, and the power generation side is the main member of the market. Its quotation strategy affects the listing price in the electricity market. Therefore, this paper summarizes the electricity market trading models and bidding strategies on the power generation side, and discusses the bidding strategy based on electricity price prediction. As the core of electricity price forecasting, load forecasting is studied and discussed in detail in this paper. Finally, the future trend of bidding strategy in electricity market is forecasted.