Identifying services for short-term load forecasting using data driven models in a Smart City platform

TLDR: A use case of short-term load forecasting in non-residential buildings in the University of Girona is provided, in order to practically explain the services embedded in the described general layers architecture.

About: This article is published in Sustainable Cities and Society.The article was published on 2017-01-01 and is currently open access. It has received 54 citations till now. The article focuses on the topics: Smart city & Reference architecture.

Figures

Figure 7: Block diagram of the forecasting model.

Figure 3: Consumption vs. hour.

Figure 1: Proposed layers architecture.

Table 2: Heating system features of the buildings.

Table 3: Cooling system features of the buildings.

Figure 12: Consumption vs. hour.

Frequently asked questions

Q1. What are the future works in "Identifying services for short-term load forecasting using data driven models in a smart city platform" ?

As a future work, more services have to be defined to help providing more information to the users in order to improve the energy efficiency of the buildings. For example, defining an index related to the efficiency of the building can be a good contribution to the subject. 

Q2. What contributions have the authors mentioned in the paper "Identifying services for short-term load forecasting using data driven models in a smart city platform" ?

The paper describes an ongoing work to embed several services in a Smart City architecture with the aim of achieving a sustainable city. With this object in mind, a use case of short-term load forecasting in nonresidential buildings in the University of Girona is provided, in order to practically explain the services embedded in the described general layers architecture. 

Q3. What are the main characteristics of the AR models?

In reference to the service layer, although occupancy and weather data are variables that partially explain consumption in buildings, the AR models are simple and quick. 

Q4. What is the main idea of the paper?

The paper [21] proposes a Smart City architecture with three parts: the physical network, the communications infrastructure and the flow of information. 

Q5. In what paper is the need of a smart energy manager system explained?

In order to organize the powerproduction of distributed generation sources in relation with energy storage system and reduce the operational costs of microgrids a smart energy manager system is provided in [10]. 

Q6. What is the MAPE indicator used to validate the model?

The mean absolute percentage error (MAPE) indicator is used to validate the model due to its popularity in the forecasting field. 

Q7. What are the steps to be taken to improve the efficiency of the AR model?

In relation with the case study, some actions to take for possible energy saving improvements can be derived from the system analysis:• Compress work schedules, reducing the hours flexibility. 

Q8. What is the effect of the increase of people in cities?

This increase of people has an impact on city services such as transportation, utilities, communications, waste management, health services and much other. 

Q9. How many instances of the Faculty of Law are there?

The number of instances of Faculty of Law is 27379, covering a total of 38 months, from 1st September, 2011 to 15th October, 2014. 

Q10. How many instances of the Faculty of Economics are there?

The number of instances of Faculty of Economics is 27379, covering a total of 38 months, from 1st September, 2011 to 15th October, 2014. 

Q11. How many instances of the Faculty of Science are there?

The number of instances of Faculty of Science is 27366, covering a total of 38 months, from 1st September, 2011 to 14th October, 2014. 

Q12. What is the main purpose of the paper?

The paper [9] describes a smart lighting solution which allows the integration of the communications and logic on the current street lighting infrastructure. 

Q13. What is the definition of a large CPS?

At different scale, neighbourhoods, communities or buildings can also be considered large CPS continuously operated accordingly to demand affected by the activities of users. 

Q14. What is the use case of the Smart City general layers architecture?

The work proposes a use case of short-term load forecasting in nonresidential buildings with real data in order to practically explain the services embedded in the described Smart City general layers architecture. 

Q15. How is the data transferred from the meters to the database?

Withthe devices properly configured, the data is transferred by the log inserter from each device to the database every 15 minutes. 

Q16. What is the first step towards getting to a smart city?

But what it really makes the city smart isPreprint submitted to Sustainable cities and society September 1, 2016to process and analyse the data and returns as response some kind of action to ensure the provision of services at satisfactory levels of quality. 

Q17. What is the structure of the proposed 5-layers architecture?

The proposed 5-layers architecture is composed by: data acquisition layer, data transmission layer, data storage layer, preprocessing layer, services layer and application layer, as shown in Figure 1.