According to Figure 4 , each proposed ANN model has twelve inputs which are: month, day, hour, minute, outdoor air temperature, outdoor humidity, outdoor air pressure, wind speed, wind direction, visibility, number of occupants under the age of fifteen (e.g., zero, one, two, three, and so on), and current energy consumption; and single output as next thirty minutes’ energy consumption. In the proposed parallel ANN model, Buildings 1, 4 and 6 have 0 occupants under age of 15; Building 2 has three occupants who are under age of 15, who are also under age of 5 (they are staying in the house more than 6 h during the day); Building 3 has two occupants under age of 15, who are also above the age of 5 (they are not staying in the house more than 6 h during the day); and Building 5 has one occupant under age of 15, who is also under age of 5 (he/she is staying in the house more than 6 h during the day). Although PCA-MRA based pre-processing did not correlate electricity consumption and the opinion about the buildings’ temperature (i.e., if they were adequately warmed up), the authors wanted to see if there was a relationship among them by investigating the household budget, a proxy indicator for fuel poverty. As per rich data (i.e., questionnaire survey), respondents from all households believed that their houses were adequately warmed up and the ratio of annual fuel expenses and annual household income was less than 0.1 or 10%, the fuel poverty threshold. The historical energy consumption data were for 18 months. The first year’s data were used for training, while the remaining six months’ electricity consumption data were utilised for testing and validation. The training process for each building started with the determination of the best-performed training algorithm, as illustrated in in Table 1 , while keeping the other variables constant; e.g., maximum number of iteration as 5000; the learning rate as 0.01; and the momentum coefficient as 0.95. In addition, the number of hidden layers is kept as two, the numbers of the process elements in each hidden layer are kept as 25 for both layers, and the transfer function types in both two hidden layers and the output layer are selected as logarithmic sigmoid with maximum epoch number of 5000 with 10 repetitive runs. Further, the mean square error (MSE) for the parameter tuning during the training stage is set to 0.001, to keep the training error as low as possible. In this case, this value is found as 0.001 with empirical tests. Moreover, the dataset is normalised between 0 and 1.
Smart metering infrastructure allows for two-way communication and power transfer. Based on this promising technology, we propose a demand-side management (DSM) scheme for a residential neighbourhood of prosumers. Its core is a discrete time dynamic game to schedule individually owned home energy storage. The system model includes an advanced battery model, local generation of renewable energy, and forecasting errors for demand and genera- tion. We derive a closed-form solution for the best response problem of a player and construct an iterative algorithm to solve the game. Empirical analysis shows exponential convergence towards the Nash equilibrium. A comparison of a DSM scheme with a static game reveals the advantages of the dynamic game approach. We provide an extensive analysis on the influence of the forecasting error on the outcome of the game. A key result demonstrates that our approach is robust even in the worst-case scenario. This grants considerable gains for the utility company organising the DSM scheme and its participants.
The use of ANN for temperature forecasting aims at the prediction of the building indoor temperature for the optimal regulation of the energy devices as well as for ensuring occupants’ comfort. The input parameters concern the outdoor conditions, the indoor conditions as well as the occupants’ behavior. The forecasting time depends on the building thermal inertia and the energy regulation system. Each building is characterized by its time lag and the time of heat transmission delay [27-30]. Furthermore, the HVAC system constitutes an important factor in determining the prediction time. It depends on the operation schedule of the HVAC that may varies from building to another .
The European Union provides different initiatives as well as funds and regulates by law how European cities should deal with these challenges in order to become smart cities . The term ‘ smart city ’ was only developed quite recently. An exact approach to the definition of an optimal interpretation of ‘ smart development ’ and what ‘ smart ’ means for the city and its inhabitants is contro- versial. Every smart city design has a different focus on what ‘ smart ’ or ‘ smarter city ’ means and how to proceed with their specific development . In this context, de Jong et al. gave a good overview about attributes which in the course of time have been attached to the word ‘ city ’ to name urban planning-related activities of re- searchers, decision makers and city planners, with defi- nitions like liveable, green, intelligent, low carbon, sustainable, digital, information, knowledge, resilient, eco and ubiquitous . They come to the conclusion that so far, most articles use the word sustainable city and since 2009, it seems to be replaced by the term smart city. From the organisational perspective, a differentiation of term smart cities was classified into the following two hierarchically counter-directed approaches :
without considering physical models of the distributed generators (DGs) and various loads. In (Palma-behnke et al., 2013), authors employed an online approach called rolling horizon strategy to schedule energy storage devices and solve UC issues by using mixed integer programming optimization, based on two-day-ahead power forecasting results. Additionally, demand management mechanism was integrated to shift consumer’s behaviour and maximize renewable energy utilization. The performance showed that the operation cost was minimized with the proposed UC-rolling horizon method compared with the conventional offline UC approach. Olivares et al. (2011) constructed a centralized EMS for microgrid operating in stand-alone mode, which was composed of three main blocks, i.e. multi-stage economic load dispatch (ELD) block, generation/load forecasting block and UC block. The forecasting module was the premise for ELD and UC block. UC was responsible for providing the on-off decision for dispatchable DGs and state monitoring of the microgrid units. Once state information was received from UC, the multi-stage ELD calculated the optimal dispatch for DER and provided the reference signal to the lower device controller. Chaouachi, Kamel, Andoulsi, and Nagasaka ( 2013) formulated the microgrid energy control problem as a multi-objective problem. A multi-objective intelligent energymanagement (MIEM) control strategy was presented based on the online short-term power and load forecasting results, where a generalized neural network ensemble was utilized for making a prediction. The MIEM is composed of multi-objective (MO) linear programming and battery scheduling, where a fuzzy logic- based expert system is utilized for battery scheduling. The MO optimization is responsible for providing power reference signal for microgrid components. Similarly, many studies employed the multi-objective optimization method to address the energymanagement problem, where majority objectives were set to be the financial cost, the environmental impact and network operation conditions. Another multi-objective optimization model used in (Fan, Liu, & Zhang, 2015) aimed at minimizing financial cost and maintaining acceptable temperature with lower cost, on the basis of a heuristic technique, real-time pricing and the classification of household appliance. In (Wafaa & Dessaint, 2017), the authors investigated a vector objective function involving operating cost, voltage stability and emission effect. It aimed at reducing the risk of voltage instability and forecasting the voltage collapse point, which was challenged by the weather uncertainty.
The database creation is done with the help of the MySQL workbench, which is the unified tool for database creation. Workbench provides data modeling and a comprehensive administration tool for server configuration. The database architect visually designs an interface to generate and manage the pre-loaded data from its virtual memory. The data modeler is involved in creating complex models to deliver the feature changes in the data. In the server configuration, the initialization of serial data from the Arduino is patched through the serial transmission. The main database receives the information and it assigns the database id (e.g., 127.0.0.1). The server initially displays the data fetched with the help of PHP language. The PHP server-side script language is used for webpage development. The data read from the port like SOC and Amp/hour is displayed on the webpage. If the data fails to arrive from the serial port to the server it rolls back to its initial stage. Then the server enables the source and destination option for the user to access the data. Based on the user input the server tries to handle the preloaded data from its database management system. The charging station distance, price and slot availability may vary based on the updating of the server from the vendor side. Based on the availability, the user may prefer a charging station. By choosing the option book, the user can book a slot. Once the booking of a slot is done the server will update its database and send the information to the user and vendor.
The proposed work is set to open new avenues for smartenergymanagement on IoT and Big Data platform. The system design uses data analytics and scalable storage for building a smart EMS to aid different stakeholders with their respective privileges. The system empowers users to remotely monitor and control devices, an online bill generation via a friendly user interface Pc application. REFERENCES
According to literature, the most widely employed CI approaches for load forecasting were the multilayer perceptron (MLP), self-organizing maps (SOMs), deep learning (DL), extreme learning machine (ELM), SVM, fuzzy rule base (FRB), fuzzy C-means (FCM), wavelet transform (WT), particle swarm optimization (PSO), AIS, genetic programming (GP), firefly algorithm (FA), fruit fly optimization algorithm (FOA), differential evolutionary algorithm (DE), artificial bee colony (ABC), harmony search algorithm (HS), simulated annealing algorithm (SA), and K-shape clustering. These techniques were basically designed to deduce the relevant knowledge about the different load patterns via model feature identification and learning stage process. The results indicated that the sample complexity must be analyzed to extract information relevant for the forecasting process, and that a set of concepts related to the problem at hand were required to develop efficient learning algorithms.
Today’s energy crisis becomes global problem for the world. We need to reduce the wastage of electricity in day to day life. But the consumption of electricity increases year to year as more home appliances are installed. So, today’s the energy saving becomes first priority. Because of the limited fossil fuels, these generations have started the use of different ways of electricity generation like using the renewable energy sources. Solar, wind and water sources are easily available anywhere on earth. Renewable Energy Sources (RES) as an important approach to meeting rural energy needs, reducing pollution, and promoting economic development. A Smart Home is a house that uses new technologies to monitor the in-house temperature, out-house climate changes, control and monitor the home appliances and communicates with the worldwide. Smart homes have the potential for increasing energy efficiency, decreasing costs of energy use, decreasing the carbon footprint by including renewable resources, and trans-forming the role of the occupant.This project proposes a novel model of smart homes for rural areas where reaching or 24*7 power supply is one big question till date.
The design approach of the SSEMS is shown in block diagram form in Figure 1. It comprises photovoltaic (PV) modules that capture solar energy which the SSEMS smartly utilizes to serve several connected loads. Excess solar energy is stored in two (or more) independent battery banks (here labelled as A and B) for future usage, especially when the energy demand is greater than the energy input from the PV modules. The SSEMS includes a feature that allows for their selective charging and discharging in a user-defined order. Also shown in Figure 1 are sub circuits responsible for AC to DC conversion, DC to DC conversion for the purposes of battery charging, an automatic change-over switching circuit and a smart output unit. The duty of the automatic change- over switch is to source power from either the connected PV modules or from a DC converter AC supply. The sourced power is then fed into the smart output unit, whose duty is to efficiently manage the output energy supply. The smart output unit therefore comprise 5V and 12V USB ports, a light dependent resistor (LDR) output that switches on at dusk and goes off at dawn, and one (or more) timed DC output circuits that supply energy to user loads through an inverter. As can be observed in Figure 1, the system is design to power both AC and DC loads while also charging the connected battery banks in a user-defined order based on set parameters such as battery state of charge (SOC) and state of health (SOH). This set up allows batteries with similar SOH to be grouped together to form separate battery banks, thus allowing old batteries to be used alongside new ones instead of just discarding them. This feature is not found in the conventional solar energy systems. The above described SSEMS is a prototype system with an input/output power rating of 1000W. Its circuit design, simulation and hardware implementation are discussed in the following section. 3.1 Circuit design, simulation and implementation The design and simulation of the SSEMS was accomplished using an electronic workbench software . The software offers a wide range of components and an opportunity to vary component specifications to suite any desired output before the actual hardware implementation. This way, errors can easily be detected and correction effected while simulated output values can be obtained during the software test-run of the designed system. On successful completion of
Predictability is highly related to correlation. Two highly correlated series may be accurate predictors for each other. Therefore, if temperature is highly correlated to load, its use in load forecasting would improve the accuracy of the forecast. However, the nonlinear behaviour makes raw temperature data on its own insufficient to be used in load forecasting. Therefore, it is necessary to contextualize the temperature data and create an additional time-series that can be used as an input for the forecasting model.This problem has been tackled following different approaches. The scope of this paper is not to determine which approach is best but to provide with a methodology capable of using the aforementioned time-series to estimate the predictability of the load series. Therefore, the function defined throughout is used. This method is simple and easy to apply to time-series of any other nature (electricity prices, humidity, etc.) that may be considered as load driving factors. This function can be determined from recent historical data and its addition to the data base would provide with an alternate load series whose correlation with the original one may be used as a load predictor.
Abstract— Wireless sensor networks are rapidly gaining popularity so as to cater to the requirements of different applications. This system unifies various home appliances, smart sensors and energy technologies. The smartenergy market requires two types of ZigBee networks for device control and energymanagement. We use IEEE 802.15.4 and ZigBee to effectively deliver solutions for a energymanagement and efficiency for home automation. We present the design to evaluate the performance of the home automation users for a network-based smart home energy control. This paper designs smart home energymanagement descriptions and application environment. Current building control strategies are unable to incorporate occupant level comfort and meet the operation goals. In this, we present a building control strategy that optimizes the tradeoff between meeting user comfort and reduction in operation cost by reducing energy usage. We present an implementation of the proposed approach as an intelligent lighting control strategy that significantly reduces energy cost. Using this we can evaluate the network performance in smart homes.
With the deployment of distributed generation (DG) units into the power system, distributed approaches have been proposed in the literatures to solve various energymanagement problems as computational and communication efficiency alternatives – , , –. In a distributed energymanagement paradigm, since the local controller embedded in each controllable device only needs to exchange limited information with its neighbors, the system will also be scalable and robust to single points of failure. As customers sometimes privately own DGs, the distributed approach ensures customers’ privacy as well. In , , a distributed approach is proposed to solve the DCOPF by solving the first order optimality condition in a distributed manner. In – , distributed consensus based approaches are presented to solve the classic ED problem. In , a robust distributed system incremental cost estimation algorithm is presented to solve the classic ED problem while considering communications system imperfections. In , a consensus based algorithm to solve the ED problem considering transmission line losses (EDL) is presented. In , an incremental welfare consensus algorithm is proposed to solve the ED problem while considering demand side response.
system in the presence of wind and solar sources along with a battery is simulated using the proposed method. After the proposed hybrid system is simulated, a stochastic search-based method is proposed to minimize the amount of on/off and off/on switching of the wind turbine and solar system. This approach also minimizes the usage of the regulation ability of wind turbines, especially the anticipated output power of the wind and solar systems. The proposed method is a combination of the mutual information (MI), interaction gain (IG) of features, and neural network (NN) approaches [ 13 ]. In order to optimize the predictive engine parameters, a neural network-based stochastic seeking technique is used in feature selection. Analyzing the numerical results and comparison with actual values proves the high accuracy of the proposed prediction method. It is also seen that the amount of switching in wind turbines is reduced significantly. The main contributions of this research work are categorized as follows: a. In order to simulate battery behavior, a new method is proposed that is used in energy production
20.ª Conferência da Associação Portuguesa de Sistemas de Informação (CAPSI’2020) 3 Currently, there are several definitions about this concept that appeared for the first time in 1998 (Anthopoulos, 2015). According to Su, Li and Fu (2011), a smart city is a specific region, in which information and integrated management of the city are carried out. Further, from the same source, it can also be said that it is an intelligent and effective integration of planning ideas, modes of construction, management methods and development approaches. On the other hand, with the arrival of the concept of “Internet of Things” (IoT), Arasteh et al (2016) say that a smart city is equipped with different electronic devices, for different applications, such as, for example, surveillance cameras placed on the streets and sensors for transport systems, thus showing the importance of IoT in a smart city.
In the sections that follow in this paper, the “top-down" and “bottom-up" forecasting approaches are compared using two large smart meter data sets. The results in Section 5 indicate that a “bottom-up" approach incorporating smart meter data can give more accurate results than traditional “top-down" LDF-based forecasting, since LDF methods are based on the assumption that the demand pattern of each “child" node follows the demand pattern of its “par- ent" node. This assumption is often not valid at the distribution level, particularly if “smart grid" technologies such as electric vehicles, embedded generation, and energy storage are present in the demand. The following sections of the paper analyse the correlations between disaggregated demand and the variables which affect it, and discuss the effect of aggregation level on multi-nodal load forecasting.
The load scheduling of household is done to improve the energy efficiency of the building. The scheduling and priority of scheduling is left to the consumer’s comfort. The forecasting of demand is done by the periodic data and the energy consumption mode of appliances. To have a efficient scheduling the State of Charge (SOC) of the battery used for storing the Renewable resources are monitored regular intervals to make the scheduling efficient. The Renewable resource energy production such as wind and PV are highly fluctuating and which affects the stability of the system.
Forecasting the energy consumption has been studied since the mid-50s, when (Gillies, Bernholtz and Sandiford, 1956) presented his approach to predict peak load based on curve trends comparing the weather predictions to peak loads. In 1970 a STLF model for state estimation in a power system, based on regression algorithms, was presented by (Toyoda, Chen and Inoue, 1970). In the 80s several several authors introduced some non-liner models based on ANN. One of the main reference for this models can be found in (Hopfield, 1982), which gave its name to an specific model, the Hopfield Netowrk. Since then many authors have worked with these models, that ended up being very popular between the EDF researchers. (Raza and Khosravi, 2015) offers an extend analysis of different ANN models applied to electric load forecasting. Since those early studies on the EDF there has been a lot of authors using different models to predict energy demand with different time horizons and for different kind of loads. One of the best collection of load forecasting models can be found in (Hernandez et al., 2014). In their research the authors enlist over 70 previous real case-studies and applications of electric power demand forecasting, describing the model used, predictors, forecasts, horizons, application areas, error metrics and other information.
In this emerging context, infrastructure owners of, for instance, industrial facili- ties, buildings, wind parks, electric car fleets, offices, arenas, schools, convention centres, shopping complexes, hospitals, hotels, public lighting etc. look for new business opportunities  depending on the capabilities of the infrastructure they operate. Today most of them try to minimize their costs by, for instance, adjusting their energy consumption when its possible . However, the emer- gence of the Smart Grid may provide new capabilities for increased revenues for stakeholders. By making their energy footprint flexibility available to grid managers, stakeholders can charge for their energy behaviour adjustments . A typical example is the electric car fleet manager, who traditionally would try to minimize costs by charging the cars when the electricity prices are low. However now the trend is towards a multi-constraint goal, where the customer-needed QoS has to be guaranteed, e.g. an EV charged sufficiently to accomplish user’s next goal, but also take into consideration the broader context i.e. the management of a variable energy storage facility  that can store and feed-in energy back to the grid depending on specific KPIs e.g. on cost-benefit, performance, green energy usage, etc. In the same train of thought other infrastructures, such as the PLS, which although is much more constrained in comparison to other facilities, it may still be used as energy balancing party by adjusting its behaviour by, for instance, adjusting illumination according to their technical and regulatory capabilities.
The compactRIO and real time module which is used to measure the data through FPGA. With the help of LabVIEW program, programming and monitoring the compactRIO FPGA and storing the data into TDMS storage (Traditional Approaches to Measurement Data Storage). Using neural network in matlab for load forecasting. The System overview is shown in the flow chart given in Fig.1. (a).