PROJECT CYCLE PROBLEM: “Power Failures in a Specific Area“
A SOLUTION-ORIENTED APPROACH
NAME: Misha Bhatia
CLASS/SEC: X-E ROLL NO.: 19 1. PROBLEM SCOPING
o The problem scoping refers to the
identification of a problem and the vision to solve it. o Problem Scoping is the first stage of the AI project cycle. In this stage of AI development, problems will be identified. It is then followed by designing, developing, or building, and finally testing the project. o The process of finalizing the aim of a system or project means you scope the problem that you wish to solve with the help of your project. o It is a crucial analytical skill that can help you avoid wasting time, resources, and effort on irrelevant or poorly defined issues. 4W Canvas: o The 4Ws are very helpful in problem scoping. They are: o Who? – Refers that who is facing a problem and who are the stakeholders of the problem. The people living in that particular area. o What? – Refers to what is the problem and how you know about the problem. Power Failure is the problem o Where? – It is related to the context or situation or location of the problem. In northern and eastern India o Why? – Refers to why we need to solve the problem and what are the benefits to the stakeholders after solving the problem. During a power outage, you may be left without heating/air conditioning, lighting, hot water, or even running water. It is necessary to solve this 2.DATA ACQUISITION
o Data Acquisition consists of two words:
Data : Data refers to the raw facts , figures, or piece of facts, or statistics collected for reference or analysis. Acquisition: Acquisition refers to acquiring data for the project. o The stage of acquiring data from the relevant sources is known as data acquisition. o The data is presented, examined, and stored in a computer. • Methods of collecting data: • 1.Surveys • 2.Web Scraping • 3.Sensors • 4.Cameras • Things to keep in mind before collecting data: • The data should collected from reliable sources. • The data must be authentic. • The data should be related to the problem. • The data should be sufficient. 3.DATA EXPLORATION
• Data exploration refers to the initial step in data
analysis in which data analysts use data visualization and statistical techniques to describe dataset characterizations, such as size, quantity, and accuracy, in order to better understand the nature of the data. • Data exploration techniques include both manual analysis and automated data exploration software solutions that visually explore and identify relationships between different data variables, the structure of the dataset, the presence of outliers, and the distribution of data values. • This is done in order to reveal patterns and points of interest, enabling data analysts to gain greater insight into the raw data. • Different ways to divide data: 1.Flowcharts 2.Decision Tree 3.Mindmaps 4.System Maps
• There are two types of data:
1.Training Data- used in modelling stage 2.Testing Data- used in evaluation stage SOLUTION: • AI-driven solutions leverage the power of data to analyze and predict power disruptions. • By analyzing historical data, weather patterns, and power grid information, AI algorithms can quickly identify potential causes of outages, enabling power companies to take proactive measures. Key takeaways: • AI algorithms analyze historical data and weather patterns to predict power disruptions. • Proactive measures can be taken to prevent outages. • Cost savings by avoiding power outages and minimizing downtime. 4. MODELLING
• Modelling is the process in which
different models based on the visualized data can be created and even checked for the advantages and disadvantages of the model. • Modeling in AI essentially involves creating a mathematical framework that defines the relationships between different data points or parameters. • For this problem, a model can be formed which would tell people before time about power failure. And, this model formed through the training data. 5. EVALUATION
• Now, we are at the last stage of the AI
project cycle. Once you’ve created and trained a model, it’s crucial to thoroughly test it to evaluate how well it performs. To do this, we use a separate dataset called testing data. The model’s efficiency is then evaluated based on the following criteria: • Precision • Accuracy • Recall • F1 Score